WO2020073301A1

WO2020073301A1 - Systems and methods for monitoring a blockchain-based energy grid

Info

Publication number: WO2020073301A1
Application number: PCT/CN2018/109958
Authority: WO
Inventors: Jianjun Zhang; Kun Xu
Original assignee: Powerchaintech Beijing Company
Priority date: 2018-10-12
Filing date: 2018-10-12
Publication date: 2020-04-16

Abstract

A system for monitoring an energy grid is provided. The system may include a plurality of nodes connected with the energy grid configured to form a blockchain network, a plurality of smart objects connected with the energy grid, and/or an artificial intelligence server in communication with the energy grid, the plurality of nodes, and/or the plurality of smart objects. Each of the plurality of nodes may be in communication with each of other nodes of the plurality of nodes, and/or may be capable of generating node data related to the blockchain network. Each of the plurality of smart objects may be associated with one of a plurality of grid elements in the energy grid, and/or may be capable of generating intelligent data. The artificial intelligence server may be configured to send a command to perform an automated remediation.

Description

SYSTEMS AND METHODS FOR MONITORING A BLOCKCHAIN-BASED ENERGY GRID

TECHNICAL FIELD

The present disclosure generally relates to energy grid monitoring, and in particular, to systems and methods for monitoring energy grid, via a blockchain network, based on an Internet of Things and an artificial intelligence technology.

BACKGROUND

Conventionally, staffs are required to collect, normalize, correlate and/or analyze massive volumes of information technology operational data across an entire digital delivery chain and solve consequent problems (e.g., an abnormal state of a node) . With the development of information technology (IT) , the overall entropy of data generated by infrastructures and applications outpaces the capacity of traditional IT services. It is difficult for manual operation and/or management to handle the challenges of sustained growth of data. Furthermore, with the development of Internet of Things (IOT) and blockchain technology, the operations and management of distributed infrastructures (e.g., an energy grid) and business transactions become more challenging. Recently, the artificial intelligence for IT operations (AIOps) , which applies artificial intelligence to the operation and management of infrastructures, has emerged, providing a more effective way for data analysis. Therefore, it is desirable to provide effective systems and methods for monitoring a blockchain-based energy grid, and energy transactions thereof using artificial intelligence.

SUMMARY

In one aspect of the present disclosure, a system for monitoring smart objects is provided. The system may include a plurality of smart objects and/or an artificial intelligence server in communication with the plurality of smart objects via a network. Each of the plurality of smart objects may be associated with one of a plurality of grid elements. Each of the plurality of smart objects may be capable of generating a set of intelligent data. The artificial intelligence server may be configured to: obtain the sets of intelligent data from the plurality of smart objects; generate an analysis result based on the sets of intelligent data using one or more analytic models associated with the sets of intelligent data; and/or determine whether an anomaly exists in the plurality of smart objects based on the analysis result.

In another aspect of the present disclosure, a system for monitoring a blockchain network is provided. The system may include an artificial intelligence server in communication with the blockchain network. The artificial intelligence server may be configured to: obtain node information relating to a plurality of nodes of the blockchain network; and/or detect an operating state of the blockchain network based on the node information and/or one or more analytic models. The blockchain network may be configured to facilitate an energy transaction. Each of the plurality of nodes of the blockchain network may be configured to endorse, order, and/or validate data related to the energy transaction.

In yet another aspect of the present disclosure, a system for monitoring energy transactions in an energy grid is provided. The system may include a plurality of grid elements in communication with each other via a blockchain network, and/or an artificial intelligence server configured to monitor energy transactions between the plurality of grid elements based on one or more analytic models. Each of the plurality of grid elements may be registered in the energy grid.

In yet another aspect of the present disclosure, a system for monitoring an energy grid is provided. The system may include a plurality of nodes connected with the energy grid configured to form a blockchain network, a plurality of smart objects connected with the energy grid, and/or an artificial intelligence server in communication with the energy grid, the plurality of nodes, and/or the plurality of smart objects. Each of the plurality of nodes may be in communication with each of other nodes of the plurality of nodes, and/or may be capable of generating node data related to the blockchain network. Each of the plurality of smart objects may be associated with one of a plurality of grid elements in the energy grid, and/or may be capable of generating intelligent data based on output of at least one sensor in the each of the plurality of smart objects. The artificial intelligence server may be configured to: obtain the intelligent data from the each of the plurality of smart objects; obtain the node data from the each of the plurality of nodes; determine an event type based on the intelligent data and the node data; generate an analysis result based on the intelligent data, the node data and/or one or more analytic models associated with the event type; determine whether an anomaly exists in the system and/or the energy grid based on the analysis result; and/or in response to a determination that the anomaly exists in the system and/or the energy grid, send a command to at least one of the plurality of smart objects, and/or at least one of the plurality of nodes to perform an automated remediation. The intelligent data may include a description of an event. The node data may include node information and/or transaction information. The event type may include a working condition of the plurality of smart objects, a working condition of the plurality of nodes in the system, and/or a transaction condition.

In some embodiments, the one or more analytic models may be trained using a machine learning algorithm based on historical intelligent data of the plurality of smart objects.

In some embodiments, the historical intelligent data may include a cause, a disposition, an event result, and/or one or more log files of a plurality of events of the plurality of smart objects.

In some embodiments, the analysis result may specify a state of the plurality of smart objects.

In some embodiments, the anomaly may include an abnormal data stream relating to at least one of the plurality of smart objects, and/or a physical failure of the at least one of the plurality of smart objects.

In some embodiments, the set of intelligent data may be associated with at least one of an energy production, an energy consumption, and/or an energy transaction.

In some embodiments, the plurality of smart objects may include intelligent energy meters.

In some embodiments, the system may further include a plurality of user terminals in communication with the artificial intelligence server. Each of the plurality of user terminals may be associated with at least one of the plurality of grid elements.

In some embodiments, the artificial intelligence server may be further configured to: in response to a determination that the anomaly exists in the plurality of smart objects, identify one or more target smart objects associated with the anomaly; and/or send a command including a disposition of the anomaly to the one or more target smart objects.

In some embodiments, the artificial intelligence server may be further configured to transmit a notification to at least one user terminal associated with the one or more target smart objects.

In some embodiments, the one or more target smart objects may be configured to perform an automated remediation according to the command. The automated remediation may include resetting a smart object, repairing a smart object, replacing a smart object, activating a smart object, and/or turning off a smart object.

In some embodiments, the one or more target smart objects may be further configured to send a result of the disposition to the artificial intelligence server.

In some embodiments, the system may further include a storage configured to store information relating to the anomaly, the disposition of the anomaly, and/or the result of the disposition.

In some embodiments, at least one of the plurality of smart objects may be connected to a blockchain network or set as a node of the blockchain network.

In some embodiments, each of the plurality of user terminals may be in communication with the blockchain network.

In some embodiments, the artificial intelligence server may be connected to the blockchain network.

In some embodiments, the network may be a blockchain network.

In some embodiments, the one or more analytic models may be trained using a machine learning algorithm based on historical node information relating to the plurality of nodes of the blockchain network.

In some embodiments, the historical node information may include functionality, capacity, and/or topological relation of the plurality of nodes.

In some embodiments, the operating state of the blockchain network may specify a state of each of the plurality of nodes.

In some embodiments, the artificial intelligence server may be further configured to determine whether an anomaly exists in the plurality of nodes based on the operating state of the blockchain network. The anomaly may include insufficient capacity, Crash Failure, Crash-Recovery Failure, and/or Byzantine Failure.

In some embodiments, the artificial intelligence server may be further configured to: in response to a determination that the anomaly exists in the plurality of nodes, send a command including an automated remediation of at least one of the plurality of nodes to the blockchain network. The automated remediation may include resetting a node, repairing a node, replacing a node, deleting a node, and/or adding a node of the plurality of nodes.

In some embodiments, the system may further include an administrator terminal in communication with the artificial intelligence server. The administrator terminal may be associated with an administrator of the blockchain network.

In some embodiments, the artificial intelligence server may be further configured to transmit a notification associated with the automated remediation to the administrator terminal.

In some embodiments, the system may further include a plurality of user terminals in communication with the artificial intelligence server. Each of the plurality of user terminals may be associated with one of the plurality of grid elements. Each of the plurality of user terminals may be configured to generate a transaction proposal associated with an energy transaction.

In some embodiments, the blockchain network may be configured to generate a plurality of messages based on the transaction proposal.

In some embodiments, the artificial intelligence server may be further configured to monitor the energy transactions based on the plurality of messages and/or the one or more analytic models.

In some embodiments, the one or more analytic models may be trained using a machine learning algorithm based on historical transaction data.

In some embodiments, the artificial intelligence server may be further configured to generate an analysis result based on the energy transactions between the plurality of grid elements using the one or more analytic models; and/or determine whether an anomaly exists in the energy transactions based on the analysis result. The anomaly may include an unauthorized operation, a payment failure, and/or a transaction dispute.

In some embodiments, the artificial intelligence server may be further configured to in response to a determination that the anomaly exists in the energy transactions, send a command including a disposition of the energy transactions to the blockchain network.

In some embodiments, the blockchain network may be configured to automatically process the energy transactions to eliminate the anomaly according to the command.

In some embodiments, at least partial of the plurality of smart objects may be intelligent energy meters configured to automatically execute a smart contract, settle an energy consumption, and/or act according to the command of the artificial intelligence server.

In some embodiments, for each of the plurality of smart objects, the intelligent data may be generated according to a smart contract embedded in the smart object. The smart contract may include at least one of a time stamp, an ID of the smart contract, a type of the energy to be traded, an amount of the energy, a transaction method, or a transaction price of the energy.

In some embodiments, the one or more analytic models may be associated with at least one of an anomaly detection, an anomaly positioning, a root cause identification, and/or an anomaly prediction.

In some embodiments, the anomaly prediction may include performance bottleneck analysis, capacity forecasting, and/or fault prediction.

In some embodiments, the analysis result may include an event type, a potential cause, a location, a time, and/or a recommended disposition of the event.

In some embodiments, the system may further include at least one storage device configured to store at least one of the analysis result, the command, and/or an outcome of an action.

In some embodiments, the artificial intelligence server may be configured to send the analysis result and/or the outcome of the action to a user terminal in communication with the artificial intelligence server, the plurality of nodes, and/or the plurality of smart objects.

In some embodiments, the one or more analytic models may be trained using a machine learning algorithm based on historical operation data associated with events of the determined event type. The historical operation data may include a cause, a disposition and an event result, and/or log files of the events.

Additional features will be set forth in part in the description which follows, and in part will become apparent to those skilled in the art upon examination of the following and the accompanying drawings or may be learned by production or operation of the examples. The features of the present disclosure may be realized and attained by practice or use of various aspects of the methodologies, instrumentalities, and combinations set forth in the detailed examples discussed below.

BRIEF DESCRIPTION OF THE DRAWINGS

The present disclosure is further described in terms of exemplary embodiments. These exemplary embodiments are described in detail with reference to the drawings. These embodiments are non-limiting exemplary embodiments, in which like reference numerals represent similar structures throughout the several views of the drawings, and wherein:

FIG. 1 is a schematic diagram illustrating an exemplary energy grid management system according to some embodiments of the present disclosure;

FIG. 2 is a schematic diagram illustrating an exemplary blockchain network according to some embodiments of the present disclosure;

FIG. 3 is a schematic diagram illustrating an exemplary artificial intelligence server with AIOps according to some embodiments of the present disclosure;

FIG. 4 is a flowchart illustrating an exemplary process for monitoring an energy grid according to some embodiments of the present disclosure;

FIG. 5 is a flowchart illustrating an exemplary process for monitoring smart objects according to some embodiments of the present disclosure;

FIG. 6 is a flowchart illustrating an exemplary process for monitoring a blockchain network according to some embodiments of the present disclosure;

FIG. 7 is a flowchart illustrating an exemplary process for monitoring energy transactions in an energy grid according to some embodiments of the present disclosure;

FIG. 8 is a schematic diagram illustrating an exemplary process of an energy transaction based on a blockchain network according to some embodiments of the present disclosure;

FIG. 9 is a schematic diagram illustrating an exemplary smart contract according to some embodiments of the present disclosure;

FIG. 10 is a schematic diagram illustrating exemplary hardware and/or software components of a computing device according to some embodiments of the present disclosure; and

FIG. 11 is a schematic diagram illustrating exemplary hardware and/or software components of a mobile device according to some embodiments of the present disclosure.

DETAILED DESCRIPTION

The following description is presented to enable any person skilled in the art to make and use the present disclosure and is provided in the context of a particular application and its requirements. Various modifications to the disclosed embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the present disclosure. Thus, the present disclosure is not limited to some embodiments shown but is to be accorded the widest scope consistent with the claims.

The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting. As used herein, the singular forms “a, ” “an, ” and “the” may be intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprise, ” “comprises, ” and/or “comprising, ” “include, ” “includes, ” and/or “including, ” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

These and other features, and characteristics of the present disclosure, as well as the methods of operation and functions of the related elements of structure and the combination of parts and economies of manufacture, may become more apparent upon consideration of the following description with reference to the accompanying drawings, all of which form a part of this disclosure. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended to limit the scope of the present disclosure. It is understood that the drawings are not to scale.

The flowcharts used in the present disclosure illustrate operations that systems implement according to some embodiments of the present disclosure. It is to be expressly understood, the operations of the flowchart may be implemented not in order. Conversely, the operations may be implemented in inverted order, or simultaneously. Moreover, one or more other operations may be added to the flowcharts. One or more operations may be removed from the flowcharts.

FIG. 1 is a schematic diagram illustrating an exemplary energy grid management system 100 according to some embodiments of the present disclosure. The energy grid management system 100 may function as a monitoring and/or maintenance platform that maintain a normal operation of the energy grid. In some embodiments, the energy grid management system 100 may also function as an intelligent communication and management platform that can provide services, such as energy-trading, contract management, transaction settlement, energy demand forecasting, energy efficiency analyzing, energy distribution, user management, information publishing, transaction monitoring, marketing analysis, or the like, or any combination thereof.

The energy grid may be a distributed energy network including one or more grid elements. As used herein, a grid element may refer to an entity that can participate in an energy exchange and/or transaction. The energy exchanged and/or traded within the energy grid may include any type of energy, such as electric energy, solar energy, wind energy, fuel energy (e.g., gas, petroleum, or coal) , hydroelectric power, nuclear energy, marine energy, osmotic energy, biomass energy, geothermal energy, or the like, or any combination thereof.

Exemplary grid elements of the energy grid may include an energy supplier, an energy consumer, an energy storage, an energy broker, an energy prosumer, or the like, or any combination thereof. The energy supplier may include any entity that is capable of suppling energy. Exemplary energy suppliers may include a wind power plant, a photovoltaic (PV) power device, a PV power plant, a nuclear power plant, a hydroelectric power plant, a thermal power plant, a marine power plant, an osmotic power plant, a biomass energy plant, or the like, or any combination thereof. The energy consumer may include any entity that can consume energy. Exemplary energy consumers may include a building (e.g., a residential building, a commercial building, an industrial building) , an institution, an electric equipment (e.g., a laptop, a smartphone, an electric car) , or the like, or any combination thereof. The energy storage may include any entity that is capable of storing energy. Exemplary energy storage may include a pumped storage, a compressed air energy storage, a superconducting magnetic energy storage, a battery/rechargeable battery, a thermal energy storage, a hydrogen storage, a flywheel energy storage, or the like, or any combination thereof. The energy prosumer may include any entity that can both produce and consume energy, for example, a household with rooftop photovoltaic panels that can sell self-produced energy to peers and neighbors. Merely by way of example, as shown in FIG. 1, the grid elements of the energy grid may include a building 120, a power convert system 130, a thermal power plant 140, a PV power device 150, and an electric car 160.

In some embodiments, a grid element may be associated with a plurality of types of devices, such as an energy-supplying device, an energy-consuming device, and an energy storage device. In such cases, a grid element may both be an energy supplier, an energy consumer, and/or an energy storage. For example, the building 120 including a plurality of electric equipment and a PV power device can not only consume power but also generate power. As another example, the PV power device 150 may supply energy and include a solar pond used to store solar energy. In some embodiments, a grid element may both be an energy supplier and an energy prosumer. In some embodiments, a grid element together with the associated device (s) may operate as an integrated grid element. Additionally or alternatively, a device associated with the grid element may operate as an independent grid element that participate in an energy exchange and/or transaction in the energy grid management system 100. Merely by way of example, the building 120 and the devices therein may be regarded as the grid element of building 120. Additionally or alternatively, the PV power device of the building 120 may operate as an independent grid element.

In some embodiments, two or more grid elements of the energy grid may be connected to each other to exchange energy. Merely by way of example, the power convert system 130, the thermal power plant 140, and/or the PV power device 150 may supply electricity to the building 120 and the electric car 160. As another example, the power convert system 130 may obtain energy from one or more other grid elements and store the energy. As another example, the building 120, the thermal power plant 140, and the PV power device 150 may obtain energy from or provide energy to the power convert system 130.

The blockchain network 110 may be configured to process and/or store an energy transaction occurred in the energy grid management system 100. As used herein, an energy transaction may refer to any successful or failed energy transaction. The energy transaction may be started by any grid element in the energy grid. For example, the energy transaction may be an energy buying transaction started by an energy consumer or an energy selling transaction started by an energy supplier.

The blockchain network 110 may utilize a decentralized, distributed, and public digital ledger to maintain a continuously growing list of transaction records. The blockchain network 110 may guarantee that the transaction records can be stored in a verifiable and permanent way and not be modified retroactively. The blockchain network 110 may be of any type of blockchain network, such as a public blockchain network, a private blockchain network, a semi-private blockchain network, a consortium blockchain network, or the like, or any combination thereof.

In operation, the blockchain network 110 may allow a user associated with a grid element (e.g., an energy supplier and/or an energy consumer) to sell energy to and/or buy energy from another grid element. For example, an energy supplier may sell energy to its neighboring grid element (e.g., a grid element within a certain distance away from the energy supplier) . The user of the grid element may participate in the blockchain network 110 by starting a transaction via a user terminal (not shown in FIG. 1) . In response to the transaction, the blockchain network 110 may validate the transaction according to a smart contract, and store the transaction into a block that is sealed with a lock (also referred to as a “hash” ) if the transaction is valid. Details regarding the terminal device and the energy transaction process may be found elsewhere in the present disclosure (e.g., FIGs. 2 and 8 and the relevant descriptions thereof) .

In some embodiments, each grid element may be associated with at least one smart object. Merely by way of example, as shown in FIG. 1, the building 120 may be in communication with (or be equipped with) a smart object 170-1. The power convert system 130 may be in communication with (or be equipped with) a smart object 170-2. The thermal power plant 140 may be in communication with (or be equipped with) a smart object 170-3. The PV power device 150 may be in communication with (or be equipped with) a smart object 170-4. The electric car 160 may be in communication with (or be equipped with) a smart object 170-5. In some embodiments, the plurality of smart objects 170 may collect and/or transmit intelligent data of corresponding grid elements to an artificial intelligence server 180 for further analysis. In some embodiments, the plurality of smart objects 170 may collect and/or transmit intelligent data of themselves to the artificial intelligence server 180 for further analysis. In some embodiments, a portion of the intelligent data may be generated based on sensors and/or meters that track events of the grid element (s) and/or the smart object (s) 170. The sensors may be embedded in the smart objects 170. Exemplary intelligent data may include metric data (e.g., temperature, pressure, an amount of energy consumption, an amount of energy production) , event data, log data, or the like, or any combination thereof. As used herein, the event data may describe actions performed by entities (e.g., an energy grid, a smart object 170, and a user) . Exemplary event data generated by the plurality of smart objects 170 may include starting an energy transaction, changing settings of a smart object, etc. The log data may be an automatically produced and time-stamped documentation of events related to the plurality of smart objects 170. In some embodiments, the intelligent data may be generated at a certain frequency (e.g., every 1 mins, 5 mins, 10 mins, etc. ) . In some embodiments, the intelligent data may be generated upon an operation of the grid element (s) and/or the smart object (s) 170. In some embodiments, the generated intelligent data may be stored in the smart object (s) 170 for further use. In some embodiments, the generated intelligent data may be transmitted to the blockchain network 110 for storage. In some embodiments, the generated intelligent data may be transmitted to the artificial intelligence server 180 for analysis.

The plurality of smart objects 170 may facilitate the grid elements of the energy grid to form an Internet of Things (IOT) , enabling the devices of the grid elements to connect and exchange data, and creating direct integration of physical infrastructures into IT operations. As used herein, IOT may include network-connected industrial and/or commercial devices such as sensors, machinery, or computers, or the like. The IOT may enable a relative high extent of device control, data management, and/or machine automation across distributed infrastructures. In some embodiments, the smart object (s) 170 may be set in (or connected to) the grid element (s) . In some embodiments, the smart object (s) 170 may be connected to the blockchain network 110 and/or in communication with the blockchain network 110, as illustrated by the bi-directional arrow in dotted lines linking the smart object (s) 170 and the blockchain network 110. In some embodiments, the smart object (s) 170 may be set as node (s) of the blockchain network 110, as illustrated in FIG. 2. In some embodiments, the smart object (s) 170 may be connected to and/or in communication with the artificial intelligence server 180, so that the intelligent data generated and/or collected by the smart object (s) 170 can be transmitted to the artificial intelligence server 180, and/or one or more commands (or instructions) generated by the artificial intelligence server 180 can be transmitted to the smart object (s) 170.

In some embodiments, the plurality of smart objects 170 may include intelligent energy meters (e.g., intelligent electricity meters, intelligent natural gas meters, intelligent water meters, intelligent gas meters) . The intelligent energy meter (s) may be different from conventional meters that simply track energy (e.g., electricity) consumption in real time or over a certain time horizon. In some embodiments, the intelligent energy meter (s) may be equipped with a digital data transmission facility, thereby facilitating remote management of electricity consumption, electricity production, electricity transaction, and/or an operating state of the intelligent energy meter (s) based on a two-way communication between the intelligent energy meter (s) and the artificial intelligence server 180.

Further, in some embodiments, the intelligent energy meter (s) may be embedded with self-enforcing smart contracts. The self-enforcing smart contracts may be defined to implement the intelligent energy meter (s) in a programmatic manner. The self-enforcing smart contracts may instruct the intelligent energy meter (s) to act in a predefined way according to a trigger condition written in the self-enforcing smart contracts. Using a smart contract, the intelligent energy meter (s) may have better control over the corresponding grid element (s) . For example, the intelligent energy meter (s) may define different tariffs for different hours, connect and/or disconnect energy remotely, buy and/or sell energy according to energy consumption and/or production automatically, receive information about energy usage instantly, or the like, or any combination thereof.

The intelligent energy meter (s) with a smart contract may be implemented on the blockchain network 110. The blockchain network 110 may render the intelligent energy meter (s) more secure because the blockchain prevents security gaps by acting as a decentralized transaction log. For example, the main feature of a blockchain, “private key” and “public key” , may help verify whether a message send to an intelligent energy meter is sent from an authorized entity or forged by a hacker. As another example, data acquired from intelligent energy meter (s) may be stored in blocks as transactions and replicated for validation to peer nodes in a tamper proof manner. In some embodiments, the intelligent energy meter (s) with a smart contract may be set as a node of the blockchain network 110.

The artificial intelligence server 180 may be configured to monitor and/or manage the operation of the energy grid management system 100. The artificial intelligence server 180 may detect and/or process one or more anomalies occurred in the energy grid management system 100. The anomalies may be associated with a working condition of the plurality of smart objects 170, a working condition of the blockchain network 110 (or a working condition of a plurality of nodes of the blockchain network 110) , and/or a transaction condition occurred within the blockchain network 110.

The artificial intelligence server 180 may utilize artificial intelligence for IT operations (AIOps) to monitor the operation of the energy grid management system 100 based on data transmitted from the plurality of smart objects 170 and/or the blockchain network 110. As used herein, AIOps may refer to using big data analytics, machine learning and/or other artificial intelligence technologies to automate the identification (or detection) and/or resolution of anomalies in IT issues and physical infrastructures. More descriptions regarding the AIOps may be found elsewhere in the present disclosure (e.g., FIG. 3 and the relevant descriptions thereof) .

The artificial intelligence server 180 may determine whether an anomaly exists according to the AIOps. The anomaly may be associated with the plurality of smart objects 170, the plurality of nodes 210, and/or the energy transactions. Exemplary anomalies associated with the plurality of smart objects 170 may include an abnormal data stream, and/or a physical failure. Exemplary anomalies associated with the plurality of nodes 210 may include insufficient capacity, Crash Failure, Crash-Recovery Failure, and/or Byzantine Failure. Exemplary anomalies associated with the energy transactions may include an unauthorized operation, a payment failure, and/or a transaction dispute.

In some embodiments, the artificial intelligence server 180 may be in communication with the blockchain network 110, the plurality of smart objects 170, and/or the energy grid via a network. In some embodiments, the network may be any type of wired or wireless network, or a combination thereof. Merely by way of example, the network may include a cable network, a wireline network, an optical fiber network, a tele communications network, an intranet, an Internet, a local area network (LAN) , a wide area network (WAN) , a wireless local area network (WLAN) , a metropolitan area network (MAN) , a public telephone switched network (PSTN) , a Bluetooth network, a ZigBee network, a near field communication (NFC) network, or the like, or a combination thereof. In some embodiments, the artificial intelligence server 180 may be part of the blockchain network 110. In some embodiments, the artificial intelligence server 180 may be connected to the blockchain network 110. In some embodiments, the artificial intelligence server 180 may be a single server, or a server group. The server group may be centralized, or distributed (e.g., the artificial intelligence server 180 may be a distributed system) . In some embodiments, the artificial intelligence server 180 may be implemented on a cloud platform. Merely by way of example, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, or the like, or any combination thereof. In some embodiments, the artificial intelligence server 180 may be implemented on a computing device 1000 having one or more components illustrated in FIG. 10 in the present disclosure.

It should be noted that the above description of the energy grid management system 100 is merely provided for the purposes of illustration, and not intended to limit the scope of the present disclosure. For persons having ordinary skills in the art, multiple variations and modifications may be made under the teachings of the present disclosure. However, those variations and modifications do not depart from the scope of the present disclosure. In some embodiments, one or more optionally components may be added in the energy grid management system 100. In some embodiments, one or more components of the energy grid management system 100 mentioned above may be omitted. For example, the electric car 160 may be omitted. In some embodiments, the energy grid may exchange energy with an external energy source (e.g., a state grid, another energy grid) .

FIG. 2 is a schematic diagram illustrating an exemplary blockchain network 110 according to some embodiments of the present disclosure. As described in connection with FIG. 1, the blockchain network 110 may be configured to process and record an energy transaction occurred in the energy grid management system 100.

As shown in FIG. 2, the blockchain network 110 may be a decentralized network of a plurality of nodes 210. The nodes 210 may be connected to each other via a network 220 instead of connected to a central server. As used herein, a node 210 may refer to a computing unit that is capable of executing one or more functions of the node 210 disclosed in the present disclosure. The node 210 may be implemented on any type of computing device. For example, a node 210 may be implemented on a computing device, such as a personal computer, a tablet computer, a laptop computer, a mobile device, or the like, or a portion of the computing device. As another example, a node 210 may be implemented on a computing system including a plurality of computing devices. In some embodiments, a node 210 may be implemented on one or more components of a computing device 1000 as shown in FIG. 10. In some embodiments, a node 210 may be implemented on one or more components of a mobile device 1100 as shown in FIG. 11. In some embodiments, a node 210 may be implemented on as a Docker. In some embodiments, a node 210 may be implemented on a cloud platform. Merely by way of example, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, or the like, or any combination thereof.

In some embodiments, the plurality of nodes 210 may have the same or different functions in the blockchain network 110. Merely by way of example, the nodes 210 may include a peer, an orderer, and/or a certificate authority. The peer may refer to a node 210 that maintain a distributed ledger and/or run a smart contract (also be referred to as chaincode) in order to perform read/write operations to the distributed ledger. The distributed ledger may be a consensus of shared digital data geographically spread across one or more nodes 210. The distributed ledger may be used store to a blockchain and optionally other information related to the energy grid management system 100 (e.g., world state information) . The smart contract may refer to a self-executing contract encoding rules for energy transaction.

The peer may include an endorser and a committer. The endorser may refer to a node 210 that is configured to endorse a transaction proposal received from the user terminal 240 to generate an endorsement result. The committer may refer to a node 210 that is configured to validate a transaction and/or an endorsement result. The orderer may refer to a node 210 that is configured to order one or more transactions into a block. The certificate authority may refer to a node 210 that is configured to manage membership in the energy grid management system 100. In some embodiments, a node 210 may function as a single type of node 210. Alternatively, a node 210 may function as a plurality of types of nodes. Merely by way of example, a node 210 may function as both an endorser and a committer.

In some embodiments, one or more nodes 210 of the blockchain network 110 may be configured to analyze and/or manage information related to the energy grid management system 100 to provide a plurality of services, such as contract management, transaction settlement, energy demand forecasting, energy efficiency analyzing, energy distribution, user management, information publishing, transaction monitoring, marketing analysis, or the like, or any combination thereof. For example, the node 210 may provide a user management service, such as user registration, user authentication, user information update, user account monitoring, user account suspension, or the like, or any combination thereof. As another example, the node 210 may provide a contract management service, such as contract creation, contract execution, contract inquiry, contract confirmation, contract cancellation, or the like, or any combination thereof. In some embodiments, a user associated with a grid element may send a request for a certain service to a node 210 via the user terminal 240. In response to the request, the node 210 may execute the request and transmit the execution result to the user terminal 240, so as to provide the requested service to the user.

In some embodiments, a node 210 of the blockchain network 110 may be owned and maintained by an entity (e.g., an organization, a person) that maintains the energy grid management system 100. Alternatively, the node 210 may be owned and maintained by a user associated with a grid element of the energy grid.

In some embodiments, the blockchain network 110 may further include one or more smart object (s) 250. On the one hand, a smart object 250 may act as a node 210 of the blockchain network 110. On the other hand, a smart object 250 may act as a smart object 170 as illustrated in FIG. 1 and the descriptions are not repeated here.

The network 220 may facilitate exchange of information and/or data. For example, the plurality of nodes 210 of the blockchain network 110 may be connected to and/or communicate with each other via the network 220. As another example, one or more nodes 210 of the blockchain network 110 may be connected to and/or communicate with the user terminal 240 via the network 220. In some embodiments, the network 220 may be any type of wired or wireless network, or combination thereof. Merely by way of example, the network 220 may include a cable network, a wireline network, an optical fiber network, a tele communications network, an intranet, an Internet, a local area network (LAN) , a wide area network (WAN) , a wireless local area network (WLAN) , a metropolitan area network (MAN) , a public telephone switched network (PSTN) , a Bluetooth network, a ZigBee network, a near field communication (NFC) network, or the like, or a combination thereof. In some embodiments, the network 220 may include one or more network access points. For example, the network 220 may include wired or wireless network access points such as base stations and/or internet exchange points 220-1, 220-2, …, through which one or more components of the energy grid management system 100 may be connected to the network 220 to exchange data and/or information.

As shown in FIG. 2, the blockchain network 110 may be connected to and/or communicated with a storage device 230, a user terminal 240 and/or an artificial intelligence server 180. The storage device 230 may be configured to store data and/or instructions. In some embodiments, the storage device 230 may store data obtained from one or more node (s) 210 and/or the user terminal 240. For example, the storage device 230 may store information related to the energy grid management system 100, such as user information, raw transaction information, processed transaction data received from the blockchain network 110, policy information, news information, intelligent data generated and/or collected by the smart object (s) 170, working condition of the node (s) 210, or the like, or any combination thereof. As another example, the storage device 230 may store a block index and a historical index of a key. In some embodiments, the storage device 230 may store data and/or instructions that the blockchain network 110 may execute or use to perform exemplary methods described in the present disclosure. In some embodiments, the storage device 230 may include a mass storage, removable storage, a volatile read-and-write memory, a read-only memory (ROM) , or the like, or a combination thereof. Exemplary mass storage may include a magnetic disk, an optical disk, a solid-state drive, etc. Exemplary removable storage may include a flash drive, a floppy disk, an optical disk, a memory card, a zip disk, a magnetic tape, etc. Exemplary volatile read-and-write memory may include a random access memory (RAM) . Exemplary RAM may include a dynamic RAM (DRAM) , a double date rate synchronous dynamic RAM (DDR SDRAM) , a static RAM (SRAM) , a thyristor RAM (T-RAM) , and a zero-capacitor RAM (Z-RAM) , etc. Exemplary ROM may include a mask ROM (MROM) , a programmable ROM (PROM) , an erasable programmable ROM (EPROM) , an electrically erasable programmable ROM (EEPROM) , a compact disk ROM (CD-ROM) , and a digital versatile disk ROM, etc. In some embodiments, the storage device 230 may be implemented on a cloud platform. Merely by way of example, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, or the like, or a combination thereof.

In some embodiments, the storage device 230 may be connected to the network 220 to communicate with the user terminal 240, the artificial intelligence server 180, and/or one or more nodes 210 of the blockchain network 110. Additionally or alternatively, the storage device 230 may be directly connected to or communicate with the user terminal 240, the artificial intelligence server 180, and/or one or more nodes 210 of the blockchain network 110. In some embodiments, the storage device 230 may include distributed storages. For example, the storage device 230 (or a portion thereof) may be part of a node 210. As another example, the storage device 230 (or a portion thereof) may be part of the artificial server 180.

In some embodiments, one or more components of the energy grid management system 100 (e.g., the nodes 210, the user terminal 240, the artificial intelligence server 180, or the like) may access the storage device 230. In some embodiments, one or more components of the energy grid management system 100 may read and/or write information relating to one or more transactions and/or a working condition of one or more components of the energy grid management system 100 (e.g., the smart object (s) 170, the smart object (s) 250, the node (s) 210, etc. ) when one or more conditions are met. For example, a node 210 may read and/or modify information relating to one or more transactions stored in the storage device 230. As another example, the user terminal 240 may access information stored in the storage device 230 but have no permission to modify the information stored in the storage device 230. As a further example, the artificial intelligence server 180 may access information stored in the storage device 230 to monitor the working conditions of the smart object (s) 170, the node (s) 210, etc.

The user terminal 240 may be associated with a grid element of the energy grid, and configured to enable a user interaction between a user associated with the grid element and the blockchain network 110. For example, the user terminal 240 may be associated with the thermal power plant 140. An administrator or an employee of the thermal power plant 140 may transmit a transaction proposal to the blockchain network 110 via the user terminal 240 to sell surplus energy. As another example, the user terminal 240 may be associated with the building 120. A resident of the building 120 may transmit a transaction proposal to the blockchain network 110 via the user terminal 240 to buy energy. Additionally or alternatively, the resident may submit a request to the blockchain network 110 via the user terminal 240 to predict his/her energy demand in the next month. In some embodiments, the user terminal 240 may include a software development kit (SDK) . The SDK may provide an application programming interface (API) to connect to the blockchain network 110, and enable the user terminal 240 to interact with the blockchain network 110. For example, the SDK may package a transaction proposal inputted by a user into a properly architected format and/or produce a unique signature (e.g., a digital signature) for this transaction proposal. In some embodiments, the user terminal 240 may be installed with a client application. The client application may be designed to enable a user of the user terminal 240 to transact and/or manage energy based on the blockchain network 110. For example, the user may transmit a transaction proposal for energy to the blockchain network 110 via client application. As another example, the user may view information (e.g., a predicted energy demand, a settlement result regarding historical energy consumption, an analyzing result of energy efficiency, a warning) on the client application. The client application may be a mobile application, a web application, a cloud application, a website, or any other software for energy transaction.

In some embodiments, the user terminal 240 may be connected to or communicated with one or more components of the blockchain network 110 (e.g., one or more nodes 210) via the network 220. Additionally or alternatively, the user terminal 240 may be connected to one or more components of the blockchain network 110 directly. In some embodiments, different users of the user terminal (s) 240 may have different user permissions depending on the type of the users (e.g., a registered user, a VIP, a visitor) . For example, a registered user may have a permission to transact energy on the blockchain network 110 and read transaction information related to the blockchain network 110. A visitor may only have a permission to read transaction information related to the blockchain network 110.

In some embodiments, the user terminal 240 may be configured to encrypt and decrypt information. For example, the user terminal 240 may hold a private key and a public key. The public key may be public and available for any component in the energy grid management system 100. The private key may be hold privately by a certain component in the energy grid management system 100. When transmitting a message to another component of the energy grid management system 100, the user terminal 240 may encrypt the message using its private key and digitally signs the message. When receiving a message from another component of the energy grid management system 100, the user terminal 240 may decrypt the message using a public key of the another component and/or validate the message.

In some embodiments, the user terminal 240 may be associated with a grid element of the energy grid, and configured to enable a user interaction between a user associated with the grid element and the artificial intelligence server 180. For example, the user terminal 240 may be associated with the thermal power plant 140. In some embodiments, the artificial intelligence server 180 may transmit a notification to an administrator or an employee of the thermal power plant 140 via the user terminal 240 if an anomaly exists (e.g., a certain smart object 170 associated with the thermal power plant 140 has a physical failure) and/or if the anomaly is disposed (e.g., the certain smart object 170 is repaired) . As another example, the user terminal 240 may be associated with the building 120. The artificial intelligence server 180 may transmit a transaction notification to a resident of the building 120 via the user terminal 240 to notify the resident that the energy remained is insufficient and a transaction to buy energy has been completed. Additionally or alternatively, the resident may submit a request to the artificial intelligence server 180 via the user terminal 240 to predict his/her energy demand in the next month.

In some embodiments, the user terminal 240 may be associated with an administrator (or an employee) of the blockchain network 110, and/or enable a user interaction between the administrator (or the employee) of the blockchain network 110 and the artificial intelligence server 180. The administrator of the blockchain network 110 may maintain a normal operation of the blockchain network 110 (e.g., normal operations of the plurality of nodes 210) . The user terminal 240 associated with the administrator of the blockchain network 110 may also be referred to as an administrator terminal. For example, the artificial intelligence server 180 may transmit a notification to notify the administrator of the blockchain network 110 via the administrator terminal if an anomaly exists (e.g., a certain node 210 of the blockchain network 110 has an insufficient capacity) and/or if the anomaly is disposed (e.g., a node is added to alleviate the burden of the certain node 210) .

Similarly, in some embodiments, the user terminal 240 may be associated with an administrator (or an employee) of the energy grid, and/or enable a user interaction between the administrator (or the employee) of the energy grid and the artificial intelligence server 180. The administrator of the energy grid may maintain a normal operation of the energy grid (e.g., normal operations of the plurality of grid elements) . The user terminal 240 associated with the administrator of the energy grid may also be referred to as an administrator terminal. For example, the artificial intelligence server 180 may transmit a notification to notify the administrator of the energy grid via the administrator terminal if an anomaly exists (e.g., a certain device of a grid element has a physical failure) and/or if the anomaly is disposed (e.g., the certain device is repaired or replaced) .

In some embodiments, the user terminal 240 may include a mobile device 240-1, a tablet computer 240-2, a laptop computer 240-3, a built-in device 240-4, or the like, or a combination thereof. In some embodiments, the mobile device 240-1 may include a smart home device, a wearable device, a smart mobile device, a virtual reality device, an augmented reality device, or the like, or a combination thereof. In some embodiments, the smart home device may include a smart lighting device, a control device of an intelligent electrical apparatus, a smart monitoring device, a smart television, a smart video camera, an interphone, or the like, or a combination thereof. In some embodiments, the wearable device may include a smart bracelet, a smart footgear, a smart glass, a smart helmet, a smartwatch, a smart clothing, a smart backpack, a smart accessory, or the like, or a combination thereof. In some embodiments, the smart mobile device may include a smartphone, a personal digital assistant (PDA) , a gaming device, a navigation device, a point of sale (POS) device, or the like, or a combination thereof. In some embodiments, the virtual reality device and/or the augmented reality device may include a virtual reality helmet, a virtual reality glass, a virtual reality patch, an augmented reality helmet, an augmented reality glass, an augmented reality patch, or the like, or a combination thereof. For example, the virtual reality device and/or the augmented reality device may include a Google Glass ^TM, a RiftCon ^TM, a Fragments ^TM, a Gear VR ^TM, etc.

It should be noted that the example illustrated in FIG. 2 and the description thereof are merely provided for the purposes of illustration, and not intended to limit the scope of the present disclosure. For persons having ordinary skills in the art, multiple variations and modifications may be made under the teachings of the present disclosure. However, those variations and modifications do not depart from the scope of the present disclosure. In some embodiments, the blockchain network 110 may include any number of component nodes 210. A node 210 may be assigned with any function. In some embodiments, the storage device 230 may be omitted.

FIG. 3 is a schematic diagram illustrating an exemplary artificial intelligence server with AIOps according to some embodiments of the present disclosure. The artificial intelligence server with AIOps 300 may be an example of the artificial intelligence server 180 as described elsewhere in this disclosure. The artificial intelligence server with AIOps 300 may include a data acquisition module 310, a data management module 320, a data analysis module 330 and an operating module 340.

The data acquisition module 310 may be configured to acquire maintenance data from a plurality of data sources. The maintenance data may include intelligent data, node data, and/or reference data. The intelligent data may be obtained from the plurality of smart objects 170. The intelligent data may include event data, log data and/or metric data. The node data may be obtained from the blockchain network 110. The node data may include node information and/or transaction information. The reference data may be obtained from one or more databases. The one or more databases may be part of the blockchain network 110, the storage 230, and/or the artificial intelligence server 180. In some embodiments, the reference data may include information related to historical anomalies processing. In some embodiments, the reference data may include alarm data, management/maintenance process data (i.e., data generated in management/maintenance process (es) ) . The alarm data may refer to information about alarms generated according to anomalies. The management/maintenance process data may refer to information related to the disposition of the anomalies. The maintenance data may include historical maintenance data and/or current (or real-time) maintenance data. The current maintenance data may be denoted by stream data.

In some embodiments, the maintenance data may include a description of an event produced in the energy grid management system 100. The event may refer to information generated under any working condition (including normal working condition and/or abnormal working condition) of the grid element (s) , the smart object (s) 170, and/or the node (s) 210 of the energy grid management system 100. In some embodiments, the event may include a change happens within the energy grid management system 100, such as a change in climate, a change in one of the plurality of smart objects, a change in one of the plurality of nodes 210, a change in a transaction, etc. In some embodiments, the event may relate to the state (s) (and/or a change of the state (s) ) of one or more devices of the grid element (s) . The devices of the grid element (s) may include smart object (s) and/or unintelligent device (s) (e.g., electrical equipment) . In some embodiments, the smart object (s) may monitor the event (s) of the unintelligent device (s) . The state (s) of the device (s) of a grid element may refer to and/or include a normal state and/or an abnormal state. The state (s) of the device (s) may also describe the device (s) in a more specific manner such as excellent, good, average, and poor based on a certain criteria or parameter. In some embodiments, the event may relate to the state (s) (and/or a change of the state (s) ) of a grid element (e.g., over heat) . The state (s) of the grid element (s) may refer to and/or include a normal state and/or an abnormal state. The state (s) of the grid element (s) may also describe the grid element (s) in a more specific manner such as excellent, good, average, and poor based on a certain criteria or parameter. In some embodiments, the event may relate to the state (s) (and/or a change of the state (s) ) of the node (s) 210 of the blockchain network 110. The state (s) of the node (s) 210 may refer to and/or include a normal state and/or an abnormal state. The state (s) of the node (s) may also describe the node (s) in a more specific manner such as excellent, good, average, and poor based on a certain criteria or parameter. In some embodiments, the event may also refer to information associated with energy transaction (s) in the blockchain network 110. The event may relate to the state (s) (and/or a change of the state (s) ) of energy transaction (s) of the blockchain network 110. The state (s) of the energy transaction (s) may refer to and/or include a normal state and/or an abnormal state. In some embodiments, the state (s) of a component (e.g., a grid element, a smart object, a node, etc. ) of the energy grid management system 100 may indicate an action or event that the component is conducting, for example, the component is receiving information, the component is transmitting information, the component is executing an instruction of the artificial intelligence server 180, the component is idle, the component is suffering from a physical failure, etc.

In some embodiments, the data acquisition module 310 may acquire the current maintenance data from the plurality of smart objects 170, the plurality of nodes 210, the user terminal 240, or the like, or any combination thereof. In some embodiments, the data acquisition module 310 may acquire the historical maintenance data from a storage device (e.g., the storage device 230, a storage of the smart object (s) 170, a storage of the node (s) 210, a storage of the user terminal 240) . In some embodiments, the data acquisition module 310 may acquire the maintenance data without using an agent. For example, the data acquisition module 310 may acquire the maintenance data using a server supporting Simple Network Management Protocol (SNMP) , Java Database Connectivity (JDBC) , Transmission Control Protocol (TCP) , User Datagram Protocol (UDP) , Web Service, syslog protocol, message queue, or the like, or any combination thereof. In some embodiments, the data acquisition module 310 may acquire the maintenance data using an agent. For example, the data acquisition module 310 may acquire the maintenance data from local files, container orchestration, scripts, or the like, or any combination thereof.

The data management module 320 may be configured to manage and/or store the maintenance data. The management of the maintenance data may include data field extraction, data format normalization, data field content process, time normalization, pre-aggregation calculation, or the like, or any combination thereof. The data management module 320 may extract the data field via regular parsing, (Key-Value) KV parsing, delimiter parsing, or the like, or any combination thereof. The data management module 320 may normalize the data format by refining a field value type, converting the format of the field value type, etc. The data management module 320 may process contents of a data field by desensitizing personal data, replacing invalid and/or missing data, etc.

In some embodiments, before managing the maintenance data, the data acquisition module 310 may preprocess the maintenance data. The preprocessing of the maintenance data may include removing redundant data in the maintenance data. In some embodiments, the data acquisition module 310 may perform the preprocess (es) upon receiving the maintenance data in order to save time and cost caused by applying algorithms to redundant data and the storage of junk data.

The data analysis module 330 may be configured to analyze the maintenance data. In some embodiments, the data analysis module 330 may analyze the maintenance data based on time stamps of the maintenance data, properties of maintenance data, historicity of the maintenance data and/or seasonality of the maintenance data. At least partial of the maintenance data (e.g., event data, log data, metric data) may have time signatures. In some embodiments, the data analysis module 330 may use the time signature (s) to bring the at least partial of the maintenance data around a point in time or a time window together. In some embodiments, the data analysis module 330 may use the time signature (s) as time stamp (s) to correlate events with each other and/or with other time-series data for causal analysis. As used herein, the time-series data may refer to series of data (e.g., event data, log data, metric data indexed (or listed or graphed) in time order) . The properties of the maintenance data may refer to the key-value pairs information associated with the maintenance data (e.g., ‘status’ , ‘source’ , ‘submitter’ , etc. ) . In some embodiments, the data analysis module 330 may create relationship models between data from different sources or of different types based on the properties. The relationship models may be configured to correlate the data according to the properties. The historicity of the maintenance data may refer to past performance of maintenance data with time-stamps. In some embodiments, the data analysis module 330 may use the historicity of the maintenance data to forecast future performance or determine normal range for parameters associated with one or more components of the energy grid management system 100 (e.g., the plurality of smart objects 170, the plurality of nodes 210. The parameters may be used to evaluate the state of one or more components of the energy grid management system 100. Exemplary parameters may include processing rate of a node 210, operating temperature of a smart object 170, a number count of error logs related to an energy transaction, etc. The seasonality of the maintenance data may refer to the regularity of the time-series data (e.g., event data, log data, metric data) over a day, week, month, etc. In some embodiments, the data analysis module 330 may use the seasonality of the maintenance data to correlate data from different sources or of different types or anticipate resource requirements for scalability (e.g., capacity of a node, energy consumption of an energy grid) . For example, the data analysis module 330 may use the maintenance data of the last year to predict an amount of energy to be consumed in next June.

In some embodiments, the data analysis module 330 may build one or more analytic models based on the maintenance data and/or one or more machine learning algorithms. The analytic model (s) may be used to analyze historical events, and/or current events and/or predict future events. The analytic model (s) may analyze events associated with the plurality of smart objects 170, the plurality of nodes 210 and/or energy transactions. The analytic model (s) may be trained using a machine learning algorithm based on historical operation data. The historical operation data including a cause, a disposition and an event result, and/or log files of the events. For example, if the analytic model (s) are configured to analyze events associated with the plurality of smart objects, the analytic model (s) may be trained using a machine learning algorithm based on historical intelligent data of the plurality of smart objects 170. As another example, if the analytic model (s) are configured to analyze events associated with the plurality of nodes 210, the analytic model (s) may be trained using a machine learning algorithm based on historical node information relating to the plurality of nodes 210 of the blockchain network 110. As still another example, if the analytic model (s) are configured to analyze events associated with the energy transactions, the analytic model (s) may be trained using a machine learning algorithm based on historical transaction information.

In some embodiments, the data analysis module 330 may analyze the historical events and/or predict the future events using off-line computation. In some embodiments, the operating module 340 may analyze the current events using on-line computation.

In some embodiments, the data analysis module 330 may use the analytic model (s) to reproduce and/or diagnose the historical events. The analysis of the historical events may include a bottleneck analysis, a hotspot analysis, a Key Performance Indicator (KPI) -clustering, a KPI association mining, an anomaly association mining, an anomaly propagation diagram construction, or the like, or a combination thereof. The bottleneck analysis may refer to discoveries of hardware and/or software bottleneck (s) that restrict the performance of Internet services provided by the plurality of smart objects 170 and/or the blockchain network 110. The hotspot analysis may refer to the detection of an entity (e.g., the plurality of smart objects 170, the blockchain network 110, energy transactions) with parameters (e.g., operating temperature of a smart object 170, error logs of a node 210, processing rate of the energy transaction (s) ) significantly larger than that in a counterpart. The KPI-clustering may refer to a cluster of KPI curves of similar shape. The KPI association mining may refer to the data mining of relationships between KPI curves. The anomaly association mining may refer to the data mining of relationships between anomalies. The anomaly propagation diagram construction may be a combination of the KPI-clustering, the KPI association mining, the anomaly association mining, and/or the call chain analysis. The anomaly propagation diagram construction may be performed to infer the anomaly propagation relationship between one or more anomalies.

As used herein, KPI of an entity may be a set of metrics used to evaluate factors that are crucial to the success of the entity. For example, KPI of the plurality of smart objects 170 may include network connectivity, CPU usage, temperature, or the like, or any combination thereof. As another example, KPI of the plurality of nodes 210 may include memory usage, request response time, computing resource, or the like, or any combination thereof. As still another example, KPI of the plurality of the energy transactions may include price of the energy, tokens, an amount of the energy, or the like, or any combination thereof. In some embodiments, with KPI, the data analysis module 330 may convert the detection of an anomaly into a dichotomy in multidimensional attribute space, wherein each KPI may be an attribute and with a threshold dividing the KPI into a normal one and/or an abnormal one.

In some embodiments, the data analysis module 330 may detect anomalies based on the KPI curve (s) . For example, the data analysis module 330 may determine that a possible anomaly may exist in an entity when a KPI of the entity experiences a sudden change (e.g., a sudden rise, a sudden fall, a jitter) .

In some embodiments, the data analysis module 330 may use the analytic model (s) to predict one or more anomalies in the future events of the energy grid management system 100. The prediction of the future events may include a fault prediction, a capacity prediction, and/or a trend prediction. For example, the fault prediction may include predicting a physical failure of a smart object 170 based on the intelligent data of the smart object 170 and/or an extreme weather. As another example, the capacity prediction may include predicting an insufficient capacity associated with a node based on the node data. As still another example, the trend prediction may include an energy consumption prediction, an energy price prediction, an energy production prediction, or the like, or any combination thereof.

The operating module 340 may be configured to detect one or more anomalies in the current events and/or predict one or more anomalies in the future events based on the maintenance data. In some embodiments, the operating module 340 may detect the one or more anomalies in the current events and/or predict the one or more anomalies in the future events using the analytic model (s) . The detection of the current events may include a KPI anomaly detection, an anomaly positioning, a fast stop-loss, and a root cause analysis. The KPI anomaly detection may refer to the analysis of KPI curves to discover an anomaly in the hardware and/or software of Internet services provided by the plurality of smart objects 170 and/or the blockchain network 110, such as an increased access delay of a node 210, a network failure of a smart object 170, and/or a sharp decrease in user accesses of a transaction platform constructed based on the blockchain network 110. In some embodiments, the anomaly positioning may be triggered after the anomaly is detected. The anomaly positioning may be performed to quickly locate one or more possible causes that contribute to the anomaly. For example, if an energy transaction is unsuccessful, the anomaly positioning may be configured to locate possible causes for the unsuccessful energy transaction. As another example, if a smart object is damaged, the anomaly positioning may be configured to locate possible parts that may cause the damage. The fast stop-loss may include a collection of abnormal alarms caused by common anomalies in the past, which may be used to quickly compare maintenance data associated with new anomalies with the collection to determine a possible resolution for the new anomalies. With respect to a new anomaly, the fast stop-loss may be configured to search historical solutions of similar anomalies and/or determine a solution for the new anomaly based on the historical solutions. For example, the fast stop-loss may discover a common solution for a node with insufficient capacity is adding a new node. The fast stop-loss may recommend adding a new node when a new anomaly associated with a node with insufficient capacity is detected. The root cause analysis may refer to the determination of a root cause of an anomaly. The root cause analysis may be performed to determine the root cause based on an anomaly propagation diagram. The anomaly propagation relationship between anomalies may be constantly changing, and thus it may be difficult to determine the anomaly propagation relationship based on static setting of prior knowledge. However, the anomaly propagation diagram may provide a basis of the anomaly root cause analysis. In some embodiments, the root cause analysis may be configured to process alarms produced by a plurality of anomalies efficiently. For example, when receiving a plurality of alarms associated with the blockchain network 110, the data analysis module 330 may identify multiple alarms associated with the same root cause (e.g., a certain node with insufficient capacity causing multiple nodes related to the certain node to generate multiple alarms) from the plurality of alarms using root cause analysis. The data analysis module 330 may process the multiple alarms by disposing the certain node (e.g., adding a new node to alleviate the burden of the certain node) . By doing so, the screen and recovery time for anomalies may be shortened.

It should be noted that the artificial intelligence server with AIOps 300 and the description thereof are merely provided for the purposes of illustration, and not intended to limit the scope of the present disclosure. For persons having ordinary skills in the art, multiple variations and modifications may be made under the teachings of the present disclosure. However, those variations and modifications do not depart from the scope of the present disclosure. The modules in the artificial intelligence server with AIOps 300 may be connected to or communicate with each other via a wired connection or a wireless connection. The wired connection may include a metal cable, an optical cable, a hybrid cable, or the like, or a combination thereof. The wireless connection may include a Local Area Network (LAN) , a Wide Area Network (WAN) , a Bluetooth, a ZigBee, a Near Field Communication (NFC) , or the like, or a combination thereof. Two or more of the modules may be combined into a single module, and any one of the modules may be divided into two or more units.

FIG. 4 is a flowchart illustrating an exemplary process for monitoring an energy grid according to some embodiments of the present disclosure. In some embodiments, one or more operations of process 400 illustrated in FIG. 4 may be implemented in the energy grid management system 100. For example, the process 400 may be implemented as a set of instructions (e.g., an application) stored in a storage device (e.g., a storage device of a node 210, the storage device 230) . As another example, one or more operations of the process 400 may be invoked and/or executed by the artificial intelligence server 180 (implemented in, for example, the processor 1020 of the computing device 1000 as illustrated in FIG. 10) . One or more components of the energy grid management system 100 may execute the set of instructions, and when executing the instructions, the one or more components of the energy grid management system 100 may be configured to perform the process 400. The operations of the illustrated process presented below are intended to be illustrative. In some embodiments, the process 400 may be accomplished with one or more additional operations not described and/or without one or more of the operations discussed. Additionally, the order in which the operations of the process as illustrated in FIG. 4 and described below is not intended to be limiting.

In 402, each of a plurality of smart objects (e.g., the smart object (s) 170) may generate intelligent data. In some embodiments, the smart object (s) 170 may generate the intelligent data based on output of at least one sensor in the each of the smart object (s) 170. As described in connection with FIG. 1, each of the plurality of smart objects 170 may correspond to one of a plurality of grid elements (e.g., the power convert system 130, the thermal power plant 140, the PV power device 150) . The plurality of smart objects 170 may collect information of the plurality of grid elements. In some embodiments, at least partial of the plurality of smart objects 170 may be intelligent energy meters configured to automatically execute a smart contract, settle an energy consumption, and/or act according to one or more commands of the artificial intelligence server 180. In some embodiments, for each of the plurality of smart objects 170, the intelligent data may be generated according to the execution of a smart contract embedded in the smart object 170. More descriptions regarding the smart contract may be found elsewhere in the present disclosure (e.g., FIG. 9, and the descriptions thereof) .

Exemplary intelligent data may include metric data, event data, log data, or the like, or any combination thereof. The metric data may be associated with values of parameters of the grid element (s) and/or the corresponding smart device (s) (e.g., electricity meters, natural gas meters) thereof. For example, the metric data may include a transinformation rate of a smart device, a temperature of a smart device, an energy consumption of a grid element, an amount of energy produced by a grid element, an environmental temperature of a grid element, or the like, or any combination thereof. In some embodiments, the metric data may have a time stamp (e.g., a time point, a time period) . For example, the metric data may specify that the environmental temperature is 20 ℃ at 8: 00 am and 25 ℃ at 11: 00 am. The event data may include actions performed by entities (e.g., an energy grid, a smart object 170, a user) . For example, the event data may include an operation of a user, a transmission of a message of a smart object 170, a stop of the PV power device 150. In some embodiments, the event data may have a time stamp (e.g., a time point, a time period) . For example, the event data may specify that a smart object (e.g., an intelligent energy meter) has purchased 100 kwh electricity on June 19. The log data may be an automatically produced and time-stamped documentation of events associated with the plurality of smart objects 170. In some embodiments, the log data may have a time stamp (e.g., a time point, a time period) . For example, the log data may specify that a certain smart object stopped working at 8:00 am and started working again at 11: 00 am. In some embodiments, the events may be associated with the state (s) of the smart object (s) 170.

In some embodiments, the plurality of smart objects 170 may generate and/or transmit the intelligent data at a certain frequency (e.g., every 5 seconds, every hour, every day, every month, etc. ) . For example, the plurality of smart objects 170 may generate and/or transmit an amount of energy consumption every month to the artificial intelligence server 180. In some embodiments, the plurality of smart objects 170 may store the intelligent data and transmit certain intelligent data when required. For example, a temperature sensor of a smart object 170 may generate a temperature every hour and store the temperature (s) in a storage of the smart object 170. The smart object 170 may transmit the temperature to the artificial intelligence server 180 if the smart object 170 is in an abnormal sate. In some embodiments, the plurality of smart objects 170 may determine the priority of the intelligent data to be transmitted. For example, a temperature sensor of a smart object 170 may generate a temperature higher than the operating temperature of the smart object 170. The smart object 170 may transmit the temperature immediately after the temperature is sensed, to the artificial intelligence server 180 to indicate that an over heat may occur and may cause damage to the smart object 170.

In 404, each of a plurality of nodes 210 may generate node data related to a blockchain network (e.g., the blockchain network 110) . The node data may refer to data and/or information generated by and/or relating to the node (s) 210 of the blockchain network 110. In some embodiments, the node data may be associated with anomalies. The anomalies may be associated with the plurality of nodes 210 and/or the energy transactions. The anomalies associated with the plurality of nodes 210 may include insufficient capacity, Crash Failure, Crash-Recovery Failure, and/or Byzantine Failure. The anomalies associated with the energy transactions may include an unauthorized operation, a payment failure, and/or a transaction dispute. In some embodiments, the node data may include transaction information and/or node information. The transaction information may refer to information of a transaction started within the blockchain network 110. Exemplary transaction information may include a smart contract, a key-value pair, an endorsement result, a ledger, or the like, or any combination thereof. The node information may indicate the state (s) of the node (s) 210. Exemplary node information may include the capacity of a node, the processing rate of a node, the load of a node, the functionality of a node, topological relations of the plurality of nodes 210, or the like, or any combination thereof.

In some embodiments, the plurality of nodes 210 may generate and/or transmit the node data at a certain frequency (e.g., every 5 seconds, every hour, every day, every month) . For example, a node 210 may generate and/or transmit a processing rate of the node 210 in every five seconds to the artificial intelligence server 180. In some embodiments, the plurality of smart nodes 210 may store the node data and/or transmit certain node data when required. For example, a node 210 may generate a remaining capacity of the node 210 every half hour and store the remaining capacity (s) in a storage of the node 210. The node 210 may transmit the remaining capacity (s) to the artificial intelligence server 180 if the node 210 is in an abnormal state. In some embodiments, the plurality of nodes 210 may determine the priority of the node data to be transmitted. For example, a node 210 may generate a remaining capacity lower than a threshold for remaining capacity. The node 210 may transmit the remaining capacity immediately after the remaining capacity is calculated, to the artificial intelligence server 180 to indicate that an insufficient capacity may occur and may cause damage to the node 210.

In 406, the artificial intelligence server 180 may obtain the intelligent data and/or the node data. In some embodiments, the artificial intelligence server 180 may acquire the intelligent data from the smart object (s) 170. In some embodiments, the artificial intelligence server 180 may acquire the node data from the node (s) 210. In some embodiments, the artificial intelligence server 180 may receive the intelligent data and/or the node data from the smart object (s) 170 and/or the node (s) 210.

In 407, the artificial intelligence server 180 may generate an analysis result based on the intelligent data, the node data and/or one or more analytic models. In some embodiments, the artificial intelligence server 180 may determine an event type based on the intelligent data and/or the node data. The event type may include a working condition of the plurality of smart objects 170, a working condition of the plurality of nodes 210, and/or a transaction condition. The artificial intelligence server 180 may then select one or more analytic models out of a plurality of analytic models based on the intelligent data, the node data and/or the event type.

In some embodiments, the analytic model (s) may be trained using one or more preliminary models based on historical operation data associated with historical events of the determined event type. In some embodiments, the preliminary model (s) may be constructed based on a machine learning algorithm. Exemplary machine learning algorithm may include Holt-Winters, Auto-Regressive and Moving Average (ARTMA) algorithm, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, K-medoids algorithm, Clustering Algorithm based on Randomized Search (CLARANS) , Pearson correlation-based algorithm, Spearman correlation-based algorithm, Kendal correlation-based algorithm, Frequent Pattern Growth (FP-Growth) algorithm, Random Forest algorithm, or the like, or any combination thereof. In some embodiments, the preliminary model (s) may be a deep learning model. In some embodiments, the preliminary model (s) may include a convolution neural network. Exemplary preliminary model may include one or more deep neural networks (DNN) , one or more deep Boltzmann machines (DBM) , one or more stacked auto encoders, one or more deep stacking networks (DSN) , etc. A DNN may include a convolution neural network (CNN) , a recurrent neural network (RNN) , a deep belief network (DBN) , etc. In some embodiments, a DNN may include a multi-layer structure. The historical operation data may include information of one or more historical events (associated with the smart object (s) 170 and/or the node (s) 210) , analysis result (s) of the historical event (s) , and/or operation (s) of the historical event (s) . For example, the historical operation data may include description (s) , cause (s) , disposition (s) and event result (s) , and/or log files of the events. The artificial intelligence server 180 may determine the disposition (s) and the event result (s) based on the alarm data, the management/maintenance process data disclosed in FIG. 3.

In some embodiments, historical operation data may include historical intelligent data (see, e.g., FIG. 5 and the description thereof) , historical node information (see, e.g., FIG. 6 and the description thereof) , and historical transaction data (see, e.g., FIG. 7 and the description thereof) .

In some embodiments, the analytic model (s) may be further trained and/or updated based on the alarm data, the management/maintenance process data.

In some embodiments, instead of building an analytic model from scratch, a learnware may be used to accelerate the generation of the analytic model. A learnware may refer to a well-performed pre-trained machine learning model with a specification explaining the purpose and/or specialty of the model. The specification may be logic-based descriptions, and/or statistics that reveal the target to which the model aimed. The specification may further include a few simplified training samples that disclose the scenario for which the model was trained. When trying to identify a kind of anomaly using a learnware, requirements of the learnware may need to be first figured out in order to search a learnware whose specification matches the requirement. In some embodiments, the learnware may be used directly. In some embodiments, the learnware may be adapted using the historical operation data before using.

In some embodiments, the artificial intelligence server 180 may input the intelligent data and/or the node data into the analytic model (s) , and the analytic model (s) may output the analysis result. As used herein, the analysis result may include an event type, a potential cause, a location (e.g., a node associated with the event, a component of a smart object associated with the event) , a time, and a recommended disposition of an event. In some embodiments, the analysis result may include a state of the plurality of smart objects 170, an operating state of the blockchain network 110 and/or a state of the transactions started in the blockchain network 110 as disclosed in FIGs. 5-7.

In 408, the artificial intelligence server 180 may determine whether an anomaly exists based on the analysis result. The anomaly may be associated with the plurality of smart objects 170, the plurality of nodes 210, and/or the transactions started in the blockchain network 110. Exemplary anomalies associated with the plurality of smart objects 170 may include an abnormal data stream relating to an event of at least one of the plurality of smart object (s) 170, and/or a physical failure of at least one of the plurality of smart objects 170 (see, e.g., FIG. 5 and the description thereof) . Exemplary anomalies associated with the plurality of nodes 210 may include insufficient capacity, Crash Failure, Crash-Recovery Failure, and/or Byzantine Failure (see, e.g., FIG. 6 and the description thereof) . Exemplary anomalies associated with the transactions may include an unauthorized operation, a payment failure, and/or a transaction dispute (see, e.g., FIG. 7 and the description thereof) .

In some embodiments, the artificial intelligence server 180 may identify and/or facilitate the remediation of one or more anomalies using a plurality of analytic models. In some embodiments, partial of the plurality of analytic models may be configured to identify the anomalies. The identification of an anomaly may include an anomaly detection, an anomaly positioning, a root cause identification, and/or an anomaly prediction. The anomaly prediction may include performance bottleneck analysis, capacity forecasting, and/or fault prediction. In some embodiments, partial of the plurality of analytic models may be configured to determine a disposition of the event (s) associated with an anomaly in order to command one or more components of the energy grid management system 100 (e.g., the blockchain network 110, the plurality of smart objects 170) to automatically remediate the anomaly. For example, the artificial intelligence server 180 may employ a first analytic model to detect an anomaly based on the intelligent data and/or the node data. If the anomaly is detected, the artificial intelligence server 180 may employ a second analytic model to position the anomaly. Further, the artificial intelligence server 180 may employ a third analytic model to determine a remediation for the anomaly.

In 410, the artificial intelligence server 180 may send a command to at least one of the plurality of smart objects 170, and/or at least one of the plurality of nodes 210 to perform an automated remediation in response to a determination that the anomaly exists.

In some embodiments, in response to a determination that the anomaly exists in the plurality of smart objects 170, the artificial intelligence server 180 may send a command including a disposition of the anomaly to one or more target smart objects (see, e.g., FIG. 5 and the description thereof) . In some embodiments, in response to a determination that the anomaly exists in the plurality of nodes 210, the artificial intelligence server 180 may send a command including a disposition of the anomaly to at least one of the plurality of nodes 210 (see, e.g., FIG. 6 and the description thereof) . In some embodiments, in response to a determination that the anomaly exists in the transactions, the artificial intelligence server 180 may send a command including a disposition of the transaction (s) associated with the anomaly to the blockchain network 110 (see, e.g., FIG. 7 and the description thereof) .

In some embodiments, one or more components of the energy grid management system 100 receiving the command may take an action to remediate the anomaly according to the command. More descriptions regarding the action may be found elsewhere in the present disclosure (e.g., FIGs. 5-7, and the descriptions thereof) . In response to a determination that no anomaly exists in the energy grid management system 100, the process 400 may proceed to 406, and the artificial intelligence server 180 may continue monitoring the energy grid.

It should be noted that the above description is merely provided for the purposes of illustration, and not intended to limit the scope of the present disclosure. For persons having ordinary skills in the art, multiple variations and modifications may be made under the teachings of the present disclosure. However, those variations and modifications do not depart from the scope of the present disclosure. For example, one or more other optional operations (e.g., a storing operation) may be added elsewhere in the exemplary process 400. In the storing operation, the artificial intelligence server 180 may store at least one of the analysis result, the command, and an outcome of the action in any storage device (e.g., the storage device 230, the plurality of nodes 210) disclosed elsewhere in the present disclosure. In some embodiments, the artificial intelligence server 180 may further send the analysis result and/or the outcome of the action to a user terminal in communication with one or more components of the energy grid management system 100 (e.g., the artificial intelligence server 180, the plurality of nodes 210, or the plurality of smart objects 170) . In some embodiments,

operations

402, 404 and/or 410 may be omitted.

FIG. 5 is a flowchart illustrating an exemplary process for monitoring smart objects according to some embodiments of the present disclosure. In some embodiments, one or more operations of process 500 illustrated in FIG. 5 may be implemented in the energy grid management system 100. For example, the process 500 may be implemented as a set of instructions (e.g., an application) stored in a storage device (e.g., a storage device of a node 210, the storage device 230) . As another example, one or more operations of the process 500 may be invoked and/or executed by the artificial intelligence server 180 (implemented in, for example, the processor 1020 of the computing device 1000 as illustrated in FIG. 10) . One or more components of the energy grid management system 100 may execute the set of instructions, and when executing the instructions, the one or more components of the energy grid management system 100 may be configured to perform the process 500. The operations of the illustrated process presented below are intended to be illustrative. In some embodiments, the process 500 may be accomplished with one or more additional operations not described and/or without one or more of the operations discussed. Additionally, the order in which the operations of the process as illustrated in FIG. 5 and described below is not intended to be limiting.

In 502, each of the plurality of smart objects 170 may generate a set of intelligent data. In some embodiments, the smart object (s) 170 may generate the intelligent data based on output of at least one sensor in the each of the plurality of smart objects 170. The set of intelligent data may be associated with at least one of an energy production, an energy consumption, and/or an energy transaction. In some embodiments, for each of the plurality of smart objects 170, the set of intelligent data may be generated according to the execution of a smart contract embedded in the smart object 170. In some embodiments, the plurality of smart objects 170 may generate and/or transmit the intelligent data at a certain frequency (e.g., every 5 seconds, every hour, every day, every month) . In some embodiments, the plurality of smart objects 170 may store the intelligent data and/or transmit certain intelligent data when required. In some embodiments, the plurality of smart objects 170 may determine the priority of the intelligent data to be transmitted. More descriptions of the intelligent data generated by the smart object (s) 170 may be found elsewhere in the present disclosure (e.g., FIGs. 3 and 4, and the descriptions thereof) .

In 504, the artificial intelligence server 180 may obtain the sets of intelligent data. In some embodiments, the artificial intelligence server 180 may acquire or receive the sets of intelligent data from the smart object (s) 170.

In 505, the artificial intelligence server 180 may generate an analysis result based on the sets of intelligent data and/or one or more analytic models. The analysis result may specify a state of the plurality of smart objects 170. In some embodiments, when a smart object is in an abnormal state, the analysis result may further include information related to possible anomalies (e.g., parameters with values out of corresponding normal ranges) . For example, if the normal interval between two transmissions is 4 hours, a smart object from which no data has been received during the last 5 hours may be determined using the analytic model (s) as abnormal. The abnormal state of the smart object may specify that the smart object is disconnected.

In some embodiments, the artificial intelligence server 180 may input the sets of intelligent data into the analytic model (s) , and the analytic model (s) may output the analysis result. In some embodiments, the analytic model (s) may be trained using one or more preliminary models constructed based on a machine learning algorithm, or may be adapted based on a learnware. In some embodiments, the analytic model (s) may be trained and/or adapted based on historical intelligent data. The historical intelligent data may include a cause, a disposition, an event result, and/or one or more log files of a plurality of events of the plurality of smart objects.

In 506, the artificial intelligence server 180 may determine whether an anomaly exists in the plurality of smart objects 170 based on the analysis result. In some embodiments, if it is determined that an anomaly exists in the plurality of smart objects 170, the artificial intelligence server 180 may identify one or more target smart objects associated with the anomaly. The anomaly may include an abnormal data stream relating to at least one of the plurality of smart objects 170, and/or a physical failure of at least one of the plurality of smart objects 170. For example, if the analysis result specifies that a certain smart object is disconnected, the artificial intelligence server 180 may perform an anomaly detection to determine what anomaly (e.g., a network disconnection, a physical failure of the smart object) causes the disconnection. Further, if there is a physical failure in a smart object, the artificial intelligence server 180 may perform an anomaly positioning to determine which part of the smart object is broken. Still further, the artificial intelligence server 180 may determine a remediation of the anomaly for the smart object. In some embodiments, the artificial intelligence server 180 may employ different analytic models to implement the above functions.

In 508, the artificial intelligence server 180 may send a command to at least one of the plurality of smart objects 170, in response to a determination that the anomaly exists in the plurality of smart objects 170. In some embodiments, the artificial intelligence server 180 may send the command to one or more target smart objects associated with the anomaly. In some embodiments, the artificial intelligence server 180 may further send the command to a back-up smart object configured to replace a target smart object. The command may include a disposition of the anomaly. The disposition may include resetting a smart object, repairing a smart object, replacing a smart object, activating a smart object, and/or turning off a smart object. In some embodiments, the command (s) sent to different smart objects may be the same or different. For example, if the disposition of the anomaly is replacing smart object A with smart object B, the command sent to smart object A may be turning off and the command send to smart object B may be activating. In some embodiments, the command may be ciphered using an encryption algorithm. The encryption algorithm may include a key. The key may be used to encrypt the command. Either the key or a complementary key may be used to decrypt the command. Exemplary encryption algorithm may include Data Encryption Standard (DES) algorithm, Triple Data Encryption Standard (DES) algorithm, Rivest–Shamir–Adleman (RSA) algorithm, Blowfish algorithm, Twofish algorithm, Advanced Encryption Standard (AES) , or the like, or any combination thereof. In response to a determination that no anomaly exists in the plurality of smart objects 170, the process 500 may proceed to 504, and the artificial intelligence server 180 may continue monitoring the smart object (s) 170 in the energy grid management system 100.

In 510, the at least one of the plurality of smart objects 170 (also referred to as the target smart object (s) associated with the anomaly) may dispose the anomaly according to the command. In some embodiments, if the command is ciphered, the at least one of the plurality of smart objects 170 may first decipher the command using the key or the complementary key before disposing the anomaly. In some embodiments, using the blockchain network 110, only smart objects with the right private key (s) may decipher the command.

In 512, the at least one of the plurality of smart objects 170 (also referred to as the target smart object (s) associated with the anomaly) may send a result of the disposition to the artificial intelligence server 180. The at least one of the plurality of smart objects 170 may generate a result of the disposition after performing an automated disposition according to the command. The result of the disposition may include a successful remediation, or a failure. In some embodiments, if the at least one of the plurality of smart objects 170 fails to remedy the anomaly, the result of the disposition may include one or more factors that cause (s) the failure of the remediation.

In some embodiments, the artificial intelligence server 180 may transmit a notification to at least one user terminal associated with the one or more target smart objects. The notification may include the description and/or the disposition of the anomaly and/or the result of the disposition. For example, the at least one user terminal may be associated with one or more target smart objects of thermal power plant 140. The artificial intelligence server 180 may transmit a notification to an administrator or an employee of the thermal power plant 140 via the user terminal 240 to notify that a physical failure had happened to the one or more target smart objects, the one or more target smart objects have been repaired, and/or how the target smart object (s) are repaired. In some embodiments, information relating to the anomaly, the disposition of the anomaly, and/or the result of the disposition may be stored in the storage device 230.

It should be noted that the above description is merely provided for the purposes of illustration, and not intended to limit the scope of the present disclosure. For persons having ordinary skills in the art, multiple variations and modifications may be made under the teachings of the present disclosure. However, those variations and modifications do not depart from the scope of the present disclosure. For example, one or more other optional operations (e.g., a storing operation) may be added elsewhere in the exemplary process 500. In the storing operation, the artificial intelligence server 180 may store information relating to the anomaly, the disposition of the anomaly, and/or the result of the disposition in any storage device (e.g., the storage device 230) disclosed elsewhere in the present disclosure. As another example, if the result of the disposition indicates a failure, the artificial intelligence server 180 may send a notification to an administrator or an employee of the energy grid management system 100 requesting assistance from maintenance staff. In some embodiments, operations 502 and/or 512 may be omitted.

FIG. 6 is a flowchart illustrating an exemplary process for monitoring a blockchain network according to some embodiments of the present disclosure. In some embodiments, one or more operations of process 600 illustrated in FIG. 6 may be implemented in the energy grid management system 100. For example, the process 600 may be implemented as a set of instructions (e.g., an application) stored in a storage device (e.g., a storage device of a node 210, the storage device 230) . As another example, one or more operations of the process 600 may be invoked and/or executed by the artificial intelligence server 180 (implemented in, for example, the processor 1020 of the computing device 1000 as illustrated in FIG. 10) . One or more components of the energy grid management system 100 may execute the set of instructions, and when executing the instructions, the one or more components of the energy grid management system 100 may be configured to perform the process 600. The operations of the illustrated process presented below are intended to be illustrative. In some embodiments, the process 600 may be accomplished with one or more additional operations not described and/or without one or more of the operations discussed. Additionally, the order in which the operations of the process as illustrated in FIG. 6 and described below is not intended to be limiting.

In 602, each of the plurality of nodes 210 may generate node information related to a blockchain network (e.g., the blockchain network 110) . Exemplary node information may include the capacity of a node, the processing rate of a node, the load of a node, the functionality of a node, topological relations of the plurality of nodes 210, or the like, or any combination thereof.

In 604, the artificial intelligence server 180 may obtain the node information from the plurality of nodes 210. In some embodiments, the artificial intelligence server 180 may acquire or receive the node information from the node (s) 210.

In 605, the artificial intelligence server 180 may detect an operating state of the blockchain network 110 based on the node information and/or one or more analytic models. The operating state of the blockchain network 110 may refer to a combination of current states of all the nodes 210 in the blockchain network 110. The operating state of the blockchain network 110 may specify a current state of each of the plurality of nodes 210. If a node is in an abnormal state, the analysis result may further include data related to possible anomalies (e.g., parameters with values out of corresponding normal ranges) . For example, a node of which more than a percentage threshold (e.g., 80%, 90%, 95%) of capacity is occupied during a time period (e.g., a week, a month) may be determined using the analytic model (s) as abnormal. The abnormal state of the node may specify that the capacity of the node is insufficient.

In some embodiments, the artificial intelligence server 180 may input the node information into the analytic model (s) , and the analytic model (s) may output the operating state of the blockchain network 110. In some embodiments, the analytic model (s) may be trained using one or more preliminary models constructed based on a machine learning algorithm, or may be adapted based on a learnware. In some embodiments, the analytic model (s) may be trained and/or adapted based on historical node information. The historical node information may include functionality, capacity, topological relations of the plurality of nodes 210, or the like, or any combination thereof.

In 606, the artificial intelligence server 180 may determine whether an anomaly exists in the plurality of nodes 210 based on the operating state of the blockchain network 110. In some embodiments, if it is determined that an anomaly exists in the plurality of nodes 210, the artificial intelligence server 180 may identify one or more target nodes associated with the anomaly. The anomaly may include insufficient capacity, Crash Failure, Crash-Recovery Failure, and/or Byzantine Failure. For example, if the state of a target node specifies that the target node has insufficient capacity, the artificial intelligence server 180 may perform an anomaly prediction to determine whether an anomaly will happen to the target node. Further, if the artificial intelligence server 180 determine that an anomaly would happen to the target node (e.g., with a probability higher than 70%) , the artificial intelligence server 180 may determine that another node (e.g., a new node) is to be added to the target node to alleviate the burden of the target node. In some embodiments, the artificial intelligence server 180 may employ different analytic models to implement the above functions.

In 608, the artificial intelligence server 180 may determine a command of an automated remediation for at least one of the plurality of nodes 210 (also referred to as the target node (s) associated with the anomaly) in response to a determination that the anomaly exists in the plurality of nodes 210. The artificial intelligence server 180 may send the command to the target node (s) . In some embodiments, the artificial intelligence server 180 may further send the command to a back-up node if a new node is to be added. The command may include an automated remediation of the anomaly. The automated remediation may include resetting a node, repairing a node, replacing a node, deleting a node, and/or adding a node. In some embodiments, the command may be ciphered using an encryption algorithm. The encryption algorithm may include a key. The key may be used to encrypt the command. Either the key or a complementary key may be used to decrypt the command. Exemplary encryption algorithm may include Data Encryption Standard (DES) algorithm, Triple Data Encryption Standard (DES) algorithm, Rivest–Shamir–Adleman (RSA) algorithm, Blowfish algorithm, Twofish algorithm, Advanced Encryption Standard (AES) , or the like, or any combination thereof. In response to a determination that no anomaly exists in the plurality of nodes 210, the process 600 may proceed to 604, and the artificial intelligence server 180 may continue monitoring the blockchain network 110 in the energy grid management system 100.

In 610, the one or more target nodes may remediate the anomaly automatically according to the command. In some embodiments, if the command is ciphered, the at least one of the nodes 210 may first decipher the command using the key or the complementary key before disposing the anomaly. In some embodiments, using the blockchain network 110, only nodes with the right private key (s) may decipher the command.

In 612, the one or more target nodes may send a result of the automated remediation to the artificial intelligence server 180. The one or more target nodes may generate a result of the disposition after performing an automated remediation according to the command. The result of the automated remediation may include a successful remediation, or a failure. In some embodiments, if the target node (s) fail to remedy the anomaly, the result of the remediation may include one or more factors that cause (s) the failure of the remediation.

In some embodiments, the artificial intelligence server 180 may transmit a notification to an administrator terminal associated with an administrator of the blockchain network 110. The notification may include the description and/or the remediation of the anomaly, the one or more target nodes associated with the anomaly, how the anomaly is remediated, and/or the result of the remediation.

It should be noted that the above description is merely provided for the purposes of illustration, and not intended to limit the scope of the present disclosure. For persons having ordinary skills in the art, multiple variations and modifications may be made under the teachings of the present disclosure. However, those variations and modifications do not depart from the scope of the present disclosure. For example, one or more other optional operations (e.g., a storing operation) may be added elsewhere in the exemplary process 600. In the storing operation, the artificial intelligence server 180 may store the result of the remediation in any storage device (e.g., the storage device 230) disclosed elsewhere in the present disclosure. As another example, if the automated remediation is successful, the artificial intelligence server 180 may store the remediation as a training sample for analytic model (s) (e.g., an analytic model for fast stop-loss) . In some embodiments, operations 602 and/or 612 may be omitted.

FIG. 7 is a flowchart illustrating an exemplary process for monitoring energy transactions in an energy grid according to some embodiments of the present disclosure. In some embodiments, one or more operations of process 700 may be implemented in the energy grid management system 100. For example, the process 700 may be implemented as a set of instructions (e.g., an application) stored in a storage device (e.g., a storage device of a node 210, the storage device 230) . As another example, one or more operations of the process 700 may be invoked and/or executed by the artificial intelligence server 180 (implemented in, for example, the processor 1020 of the computing device 1000 as illustrated in FIG. 10) . One or more components of the energy grid management system 100 may execute the set of instructions, and when executing the instructions, the one or more components of the energy grid management system 100 may be configured to perform the process 700. The operations of the illustrated process presented below are intended to be illustrative. In some embodiments, the process 700 may be accomplished with one or more additional operations not described and/or without one or more of the operations discussed. Additionally, the order in which the operations of the process as illustrated in FIG. 7 and described below is not intended to be limiting.

In 702, each of the plurality of nodes 210 may generate a plurality of messages based on one or more energy transaction proposals. The plurality of messages may be also referred to as transaction information. Exemplary transaction information may include a smart contract, a key-value pair, an endorsement result, a ledger, or the like, or any combination thereof.

In 704, the artificial intelligence server 180 may monitor one or more energy transactions corresponding to the transaction proposal (s) based on the plurality of messages and/or one or more analytic models. The artificial intelligence server 180 may generate an analysis result based on the analytic model (s) . The analysis result may include a state of each of the energy transaction (s) . In some embodiments, an abnormal state of an energy transaction may further include data related to possible anomalies. For example, if the normal time period for completing a transaction is less than half an hour, and a transaction that is not completed within half an hour may be determined using the analytic model (s) as abnormal. In some embodiments, the abnormal state of the transaction may specify that the transaction has not been completed.

In some embodiments, the artificial intelligence server 180 may input the plurality of messages into the analytic model (s) , and the analytic model (s) may output the analysis result. In some embodiments, the analytic model (s) may be trained using one or more preliminary models constructed based on a machine learning algorithm, or may be adapted based on a learnware. In some embodiments, the analytic model (s) may be trained and/or adapted based on historical transaction data. The historical transaction data may include a smart contract, a key-value pair, an endorsement result, a ledger, or the like, or any combination thereof.

In 706, the artificial intelligence server 180 may determine whether an anomaly exists in energy transaction (s) according to the monitoring. In some embodiments, the artificial intelligence server 180 may determine whether an anomaly exists in energy transaction (s) based on an analysis result generated in the monitoring. The anomaly may include an unauthorized operation, a payment failure, a transaction dispute, or the like, or any combination thereof.

In 708, the artificial intelligence server 180 may send a command to the blockchain network 110 in response to a determination that the anomaly exists in the energy transaction (s) . The command may include a disposition of the anomaly. The disposition may include canceling a transaction, invalidating a transaction, restarting a transaction, or the like, or any combination thereof. In some embodiments, the command may be ciphered using an encryption algorithm. The encryption algorithm may include a key. The key may be used to encrypt the command. Either the key or a complementary key may be used to decrypt the command. Exemplary encryption algorithm may include Data Encryption Standard (DES) algorithm, Triple Data Encryption Standard (DES) algorithm, Rivest–Shamir–Adleman (RSA) algorithm, Blowfish algorithm, Twofish algorithm, Advanced Encryption Standard (AES) , or the like, or any combination thereof. In response to a determination that no anomaly exists in the energy transaction (s) , the process 700 may proceed to 704, and the artificial intelligence server 180 may continue monitoring the energy transaction (s) in the blockchain network 110.

In 710, the blockchain network 110 may automatically process the energy transaction (s) to eliminate the anomaly according to the command. For example, the blockchain network 110 may cancel an energy transaction that has not completed within a certain time period. As another example, the blockchain network 110 may cancel an energy transaction that is signed by an unauthorized party. In some embodiments, if the command is ciphered, the at least one of the blockchain network 110 may first decipher the command using the key or the complementary key before disposing the anomaly.

In 712, the blockchain network 110 may send a result of the elimination to the artificial intelligence server 180. The result of the remediation may include a successful remediation, or a failure. In some embodiments, if the blockchain network 110 fail to remedy the anomaly, the result of the remediation may include one or more factors that cause (s) the failure of the remediation.

In some embodiments, the artificial intelligence server 180 may transmit a notification to one or more user terminals associated with the energy transaction (s) . The one or more user terminals may be associated with a buyer, a seller, a broker of the energy transaction, etc. The notification may include the description and/or the remediation of the anomaly, how the anomaly is remediated, and/or the result of the elimination.

It should be noted that the above description is merely provided for the purposes of illustration, and not intended to limit the scope of the present disclosure. For persons having ordinary skills in the art, multiple variations and modifications may be made under the teachings of the present disclosure. However, those variations and modifications do not depart from the scope of the present disclosure. For example, the artificial intelligence server 180 may identify an unauthorized operation and add the operator to a blacklist. As another example, operations 702 and/or 712 may be omitted.

FIG. 8 is a schematic diagram illustrating an exemplary process of an energy transaction based on a blockchain network 800 according to some embodiments of the present disclosure. The blockchain network 800 may be an example of the blockchain network 110 as described elsewhere in this disclosure.

As described in connection with FIG. 2, the blockchain network 800 may include a plurality of nodes. Each of the plurality of nodes may be configured to communicate with each of other nodes of blockchain network 800. A user terminal 240 associated with a grid element of an energy grid may be connected to and/or communicated with the blockchain network 800. For example, the user terminal 240 may be connected to and/or communicated with one or more of the plurality of nodes.

As shown in FIG. 8, the plurality of nodes may include a plurality of peers (i.e., endorsers E ₀ to E ₂ and committers C ₃ and C ₄) and a plurality of orderers O ₀ to O ₄. Each of the peers may be configured to hold a distributed ledger and/or run one or more smart contracts. The distributed ledger may include a plurality of blocks. The orderers O ₀ to O ₄ may provide an ordering service.

In 802, a user may submit a transaction proposal via the user terminal 240 to the blockchain network 800. The transaction proposal may be a transaction proposal to buy or sell energy in the energy grid management system 100. For example, the user may send the transaction proposal using a client application installed on the user terminal 240. In some embodiments, the client application may use a SDK (e.g., a Node SDK, a Java SDK, or a Python SDK) and utilize an API to generate the transaction proposal. Optionally, the client application may produce a digital signature using a cryptographic credential of the user. In some embodiments, the transaction proposal may include at least one of an ID of the user of the user terminal 240, a digital signature of the user, a time stamp, an ID of the smart contract corresponding to the transaction proposal, a type of the energy to be traded, an amount of the energy, a transaction method, and/or a transaction price of the energy, or the like, or any combination thereof.

One or more peers that need to endorse the transaction proposal may be defined by an endorsement policy. The endorsement policy may define one or more nodes that need to endorse a specific type of transaction proposal. Additionally or alternatively, the endorsement policy may define a requirement for a valid endorsement of the transaction proposal. For example, the endorsement policy may require that the transaction endorsement by the endorser (s) is valid unless the transaction proposal is endorsed by a minimum number or percentage of the endorser (s) , or by all of the endorser (s) . Merely by way of example, an exemplary endorsement policy may define that endorsers A, B, and C need to endorse a transaction proposal for electricity. Additionally or alternatively, the exemplary endorsement policy may define that the endorsement of the transaction proposal for electricity is valid if at least two of A, B, and C endorse the transaction proposal. As shown in FIG. 8, the endorsement policy may define that the peers E ₀, E ₁, and E ₂ are required to be involved in the transaction proposal endorsement. In such case, the transaction proposal is transmitted to each of the E ₀, E ₁, and E ₂, respectively.

In response to the received transaction proposal, each of the endorsers E ₀, E ₁, and E ₂ may endorse the transaction proposal by first verifying the transaction proposal. For example, each endorser may verify that the transaction proposal is well formed and/or the transaction proposal has not been submitted already in the past. Additionally or alternatively, each endorser may verify that the digital signature of the transaction proposal is valid and the submitter of the transaction proposal is properly authorized to submit the transaction proposal. After verifying the transaction proposal, each of the endorsers E ₀, E ₁, and E ₂ may independently simulate the execution of the smart contract using a transaction proposal to generate a transaction result. Each of the endorsers E ₀, E ₁, and E ₂ may transmit the transaction result, along with its digital signature back as an endorsement result to the user terminal 240. None of the endorser (s) may update the distributed ledger at this point.

The smart contract may refer to a self-executing contract encoding rules for energy transaction. For example, the smart contract may include terms of agreements regarding an energy transaction between two parties. Each of the endorser (s) may store the smart contract. In some embodiments, each endorser may endorse the transaction proposal according to a smart contract associated with the transaction proposal. Merely by way of example, the transaction proposal may define an ID of a smart contract to be executed, and the endorser (s) may perform the endorsement based on the defined smart contract. As another example, the endorser (s) may perform the endorsement based on a smart contract that is signed by a user associated with the user terminal 240 (e.g., a manager of the corresponding grid element) . In some embodiments, the smart contract may be of various types, such as a customized smart contract, a predefined smart contract, an open smart contract, a long-term smart contract, a short-term smart contract. More descriptions regarding the smart contract may be found elsewhere in the present disclosure (e.g., FIG. 9 and the relevant descriptions thereof) .

In 804, when and/or after receiving signed endorsement result (s) from “enough” peer (s) , the user terminal 240 may generate a transaction including the signed endorsement result (s) , and transmit the transaction to one or more of the orders O ₁-O ₄. As used herein, if the user terminal 240 receives endorsement result (s) from a predetermined number of endorsers, it may determine that it has received endorsement result (s) from “enough” endorser (s) . In some embodiments, the predetermined number of endorsers may be defined by a requirement of a valid endorsement in the endorsement policy as described in connection with operation 802. For example, an endorsement policy may define that as long as two of the three nodes E ₀, E ₁, and E ₂ transmit the endorsement results to user terminal 240, the endorsement of the transaction proposal is valid. In such case, the user terminal 240 may generate a transaction once it receives two endorsement results from E ₀, E ₁, and E ₂. In some embodiments, if the user terminal 240 fails to receive “enough” endorsement result (s) , the transaction proposal may be discarded and the user may need to start a new transaction proposal.

In 806, the orderer (s) that receive the transaction from the user terminal 240 may order the transaction together with other transaction (s) received from other user terminals (not shown in FIG. 8) . The orderer (s) may package the transactions received from the user terminal 240 and the other user terminal (s) into a block, and subsequently distribute the block to each of the peers connected to the orderer (s) . The orderer (s) may order the transactions according to an ordering mechanism, such as a SOLO ordering mechanism, an Apache Kafka ordering mechanism, a Simplified Byzantine Fault Tolerance (SBFT) ordering mechanism, or the like, or any combination thereof. As shown in FIG. 8, in 806, the orderer (s) may distribute a block including the transaction submitted by the user terminal 240 and the other transaction (s) to the peers E ₀, E ₁, E ₂, C ₃, and C ₄ for validation.

In 808, each of the peers that receives the block from the orderer may validate each transaction in the block, including the transaction submitted by the user terminal 240. For the transaction submitted by the user terminal 240, each peer may validate that whether the endorsement result (s) of transaction are correct and whether the transaction is compatible with current state of the distributed ledger. In response to a determination that the endorsement result (s) are correct and the transaction is compatible with the current state of the distributed ledger, each peer may determine that the transaction submitted by the user terminal 240 is valid. Upon the validation result that the transaction is valid, each peer may update its distributed ledger by writing the transaction submitted by the user terminal 240 into the distributed ledger. On the other hand, if the peer determines that the endorsement policy of the transaction has not been fulfilled or the current state of the distributed ledger is incompatible with the state of the distributed ledger when the block was generated, the peer may determine that the transaction is invalid. An invalid transaction may not be applied to the distributed ledger, but be retained for audit purpose.

In some embodiments, a notification regarding the validation result may be sent to the user terminal 240 when the transaction submitted by the user terminal 240 succeed or fail and/or when the corresponding block is added to the distributed ledger. The notification may be sent out by each peer connected to the user terminal 240. For example, each of the peers E ₀, E ₁, E ₂, C ₃, and C ₄ may send a notification to the user terminal 240 when the transaction submitted by the user terminal 240 is validated.

FIG. 9 is a schematic diagram illustrating an exemplary smart contract 900 according to some embodiments of the present disclosure. As described in connection with FIG. 8, a smart contract may be a self-executing contract encoding rules for energy transaction. For example, the smart contract may include terms of agreements between two parties, e.g., an energy buyer and an energy seller.

As illustrated in FIG. 9, the smart contract 900 may stipulate a first party and a second party that signed the smart contract 900, an amount of energy to be traded between the first party and the second party, the type of energy to be traded between the first party and the second party, a transaction price, an effective date of the smart contract 900, an expiration date of the smart contract 900, a type of the smart contract 900, a status of the smart contract 900, a contraction duration, or the like, or any combination thereof. The first party and the second party may be associated with a grid element registered in an energy gird, respectively. The type of energy to be traded may include electric energy, solar energy, wind energy, fuel energy, hydroelectric power, nuclear energy, marine energy, osmotic energy, biomass energy, geothermal energy, or the like, or any combination thereof. The type of the smart contract 900 may include, for example, a customized smart contract, a predefined smart contract, an open smart contract, a long-term smart contract, a short-term smart contract, or the like, or any combination thereof.

As used herein, the customized smart contract may refer to a smart contract that is based at least in part on data related to the smart contract inputted by a user via a user terminal 240. For example, the first party and/or the second party of the smart contract may input data via the user terminal 240 to add, remove, and/or modify one or more terms of agreements in the smart contract. In some embodiments, the customized smart contract may be written by the first party and/or the second party using a Domain Specific Language (DSL) (e.g., go, node. js) . Alternatively, the first party and/or the second party of the customized smart contract may input one or more terms of agreements in a natural language into the user terminal 240. A node 210 of the blockchain network 110 and/or the user terminal 240 may then convert the inputted term (s) into the customized smart contract.

The predefined smart contract may be selected from one of a plurality of predefined smart contracts stored in one or more nodes 210 (e.g., one or more endorsers) of the blockchain network 110. The plurality of predefined smart contracts may include one or more predetermined terms of agreements between the first and the second parities. In some embodiments, the predefined smart contracts may be generated using a machine learning algorithm based on sample data. The sample data may include, such as a plurality of customized smart contracts, common knowledge, a national policy and/or regulation regarding energy trading, or the like, or any combination thereof. For example, the predefined smart contracts may be generated based on a plurality of customized smart contracts defined by users of the energy grid management system 100 using a machine learning algorithm. Exemplary machine learning algorithm may include but not be limited to an artificial neural network algorithm, a deep learning algorithm, a decision tree algorithm, an association rule algorithm, an inductive logic programming algorithm, a support vector machines algorithm, a clustering algorithm, a Bayesian networks algorithm, a reinforcement learning algorithm, a representation learning algorithm, a similarity and metric learning algorithm, a sparse dictionary learning algorithm, a genetic algorithms, a rule-based machine learning algorithm, or the like, or any combination thereof.

The open smart contract may include a contract that is constructed by a single participant of the energy grid management system 100. The open smart contract may automatically execute itself when another participant of the energy grid management system 100 meets all the contract terms. Additionally or alternatively, an open smart contract may include a contract the term (s) of which do not describe the entire agreement between the two parties. For example, the open smart contract may be constructed without an end date, and the contract may continue as long as both parties are satisfied with the contract.

In some embodiments, the smart contract 900 may be constructed by the first party and/or the second party on a client application for energy transaction installed in a user terminal 240. For example, the first party may input terms of agreement into the client application installed in his/her user terminal 240 to construct an initial smart contract. After the initial smart contract is confirmed by the second party, it may become a formal smart contract. In some embodiments, the smart contract 900 may be managed by the first party and/or the second party on the client application. For example, the first party and/or the second party may search, view, modify, cancel, download, print, and/or confirm the smart contract 900 on the client application.

It should be noted that the example illustrated in FIG. 9 and the above description thereof are merely provided for the purposes of illustration, and not intended to limit the scope of the present disclosure. For persons having ordinary skills in the art, multiple variations and modifications may be made under the teachings of the present disclosure. However, those variations and modifications do not depart from the scope of the present disclosure. In some embodiments, the smart contract 900 may include one or more additional terms. Additionally or alternatively, one or more terms of the smart contract 900 mentioned above may be omitted.

FIG. 10 is a schematic diagram illustrating exemplary hardware and/or software components of a computing device 1000 according to some embodiments of the present disclosure.

The computing device 1000 may be used to implement any component of the energy grid management system 100 as described herein. For example, a node 210 of the blockchain network 110 and/or a user terminal 240 may be implemented on the computing device 1000, via its hardware, software program, firmware, or a combination thereof. Although only one such computing device is shown, for convenience, the computer functions relating to the energy grid management system 100 as described herein may be implemented in a distributed fashion on a number of similar platforms, to distribute the processing load.

The computing device 1000 may include a COM port 1050 connected to and from a network connected thereto to facilitate data communications. The computing device 1000 may also include a processor 1020 that is configured to execute instructions. The instructions may include, for example, routines, programs, objects, components, signals, data structures, procedures, modules, and functions, which perform particular functions described herein. In some embodiments, the processor 1020 may process information related to an energy transaction in the energy grid management system 100. For example, the processor 1020 may endorse a transaction proposal based on a smart contract. In some embodiments, the processor 1020 may include one or more hardware processors, such as a microcontroller, a microprocessor, a reduced instruction set computer (RISC) , an application specific integrated circuits (ASICs) , an application-specific instruction-set processor (ASIP) , a central processing unit (CPU) , a graphics processing unit (GPU) , a physics processing unit (PPU) , a microcontroller unit, a digital signal processor (DSP) , a field programmable gate array (FPGA) , an advanced RISC machine (ARM) , a programmable logic device (PLD) , any circuit or processor capable of executing one or more functions, or the like, or any combinations thereof.

The computing device 1000 may further include an internal communition bus 1010, differet types of program storage and data storage including, for example, a disk 1070, and a read-only memory (ROM) 1030, or a random access memory (RAM) 1040. The exemplary computing device may also include program instructions stored in the ROM 1030, RAM 1040, and/or another type of non-transitory storage medium to be executed by the processor 1020. The methods and/or processes of the present disclosure may be implemented as the program instructions. The computing device 1000 also includes an I/O component 1060, supporting input/output between the computing device 1000 and other components. The computing device 1000 may also receive programming and data via network communications.

Merely for illustration, only one processor is illustrated in FIG. 10. However, it should be noted that the computing device 1000 in the present disclosure may also include multiple processors. Thus operations and/or method operations performed by one processor as described in the present disclosure may also be jointly or separately performed by the multiple processors. For example, if in the present disclosure a processor of the computing device 1000 executes both operation A and operation B, it should be understood that operation A and operation B may also be performed by two different processors jointly or separately in the computing device 1000 (e.g., the first processor executes operation A and the second processor executes operation B, or the first and second processors jointly execute operations A and B) .

FIG. 11 is a schematic diagram illustrating exemplary hardware and/or software components of a mobile device 1100 according to some embodiments of the present disclosure. In some embodiments, a user terminal 240 may be implemented on the mobile device 1100. As illustrated in FIG. 11, the mobile device 1100 may include a communication platform 1110, a display 1120, a graphics processing unit (GPU) 1130, a central processing unit (CPU) 1140, an I/O 1150, a memory 1160, and a storage 1190. In some embodiments, any other suitable component, including but not limited to a system bus or a controller (not shown) , may also be included in the mobile device 1100.

In some embodiments, a mobile operating system 1170 (e.g., iOS ^TM, Android ^TM, Windows Phone ^TM, etc. ) and one or more applications 1180 may be loaded into the memory 1160 from the storage 1190 in order to be executed by the CPU 1140. The applications 1180 may include a browser or any other suitable mobile apps for receiving and rendering information relating to the energy grid management system 100. In some embodiments, the applications 1180 may include an application designed for energy transaction as described elsewhere in this disclosure (e.g., FIG. 2 and the relevant descriptions) . User interactions with the information stream may be achieved via the I/O 1150 and provided to the blockchain network 110 and/or other components of the energy grid management system 100 via a network.

To implement various modules, units, and their functionalities described in the present disclosure, computer hardware platforms may be used as the hardware platform (s) for one or more of the elements described herein. A computer with user interface elements may be used to implement a personal computer (PC) or any other type of work station or terminal device. A computer may also act as a server if appropriately programmed.

It should be noted that the above description is merely provided for the purposes of illustration, and not intended to limit the scope of the present disclosure. For persons having ordinary skills in the art, multiple variations and modifications may be made under the teachings of the present disclosure. However, those variations and modifications do not depart from the scope of the present disclosure.

Having thus described the basic concepts, it may be rather apparent to those skilled in the art after reading this detailed disclosure that the foregoing detailed disclosure is intended to be presented by way of example only and is not limiting. Various alterations, improvements, and modifications may occur and are intended to those skilled in the art, though not expressly stated herein. These alterations, improvements, and modifications are intended to be suggested by this disclosure and are within the spirit and scope of the exemplary embodiments of this disclosure.

Moreover, certain terminology has been used to describe embodiments of the present disclosure. For example, the terms “one embodiment, ” “some embodiments, ” and/or “some embodiments” mean that a particular feature, structure or characteristic described in connection with some embodiments is included in at least one embodiment of the present disclosure. Therefore, it is emphasized and should be appreciated that two or more references to “some embodiments, ” “one embodiment, ” or “an alternative embodiment” in various portions of this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures or characteristics may be combined as suitable in one or more embodiments of the present disclosure.

Further, it will be appreciated by one skilled in the art, aspects of the present disclosure may be illustrated and described herein in any of a number of patentable classes or context including any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof. Accordingly, aspects of the present disclosure may be implemented entirely hardware, entirely software (including firmware, resident software, micro-code, etc. ) or combining software and hardware implementation that may all generally be referred to herein as a "block, " “module, ” “engine, ” “unit, ” “component, ” or “system. ” Furthermore, aspects of the present disclosure may take the form of a computer program product embodied in one or more computer-readable media having computer readable program code embodied thereon.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including electromagnetic, optical, or the like, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that may communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable signal medium may be transmitted using any appropriate medium, including wireless, wireline, optical fiber cable, RF, or the like, or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present disclosure may be written in a combination of one or more programming languages, including an object-oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB. NET, Python or the like, conventional procedural programming languages, such as the “C” programming language, Visual Basic, Fortran 1703, Perl, COBOL 1702, PHP, ABAP, dynamic programming languages such as Python, Ruby, and Groovy, or other programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN) , or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider) or in a cloud computing environment or offered as a service such as a software as a service (SaaS) .

Furthermore, the recited order of processing elements or sequences, or the use of numbers, letters, or other designations, therefore, is not intended to limit the claimed processes and methods to any order except as may be specified in the claims. Although the above disclosure discusses through various examples what is currently considered to be a variety of useful embodiments of the disclosure, it is to be understood that such detail is solely for that purpose, and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover modifications and equivalent arrangements that are within the spirit and scope of the disclosed embodiments. For example, although the implementation of various components described above may be embodied in a hardware device, it may also be implemented as a software-only solution-e.g., an installation on an existing server or mobile device.

Similarly, it should be appreciated that in the foregoing description of embodiments of the present disclosure, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the various embodiments. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed subject matter requires more features than are expressly recited in each claim. Rather, claimed subject matter may lie in less than all features of a single foregoing disclosed embodiment.

Claims

A system for monitoring smart objects, comprising:

a plurality of smart objects, each of the plurality of smart objects being associated with one of a plurality of grid elements, each of the plurality of smart objects being capable of generating a set of intelligent data; and

an artificial intelligence server in communication with the plurality of smart objects via a network, the artificial intelligence server being configured to:

obtain the sets of intelligent data from the plurality of smart objects;

generate an analysis result based on the sets of intelligent data using one or more analytic models associated with the sets of intelligent data; and

determine whether an anomaly exists in the plurality of smart objects based on the analysis result.
The system of claim 1, wherein the one or more analytic models are trained using a machine learning algorithm based on historical intelligent data of the plurality of smart objects.
The system of claim 2, wherein the historical intelligent data includes a cause, a disposition, an event result, and/or one or more log files of a plurality of events of the plurality of smart objects.
The system of claim 1, wherein the analysis result specifies a state of the plurality of smart objects.
The system of claim 1, wherein the anomaly includes an abnormal data stream relating to at least one of the plurality of smart objects, and/or a physical failure of the at least one of the plurality of smart objects.
The system of claim 1, wherein the set of intelligent data is associated with at least one of an energy production, an energy consumption, and an energy transaction.
The system of claim 1, wherein the plurality of smart objects include intelligent energy meters.
The system of claim 1, further comprising:

a plurality of user terminals in communication with the artificial intelligence server, each of the plurality of user terminals being associated with at least one of the plurality of grid elements.
The system of claim 8, wherein the artificial intelligence server is further configured to:

in response to a determination that the anomaly exists in the plurality of smart objects,

identify one or more target smart objects associated with the anomaly; and

send a command including a disposition of the anomaly to the one or more target smart objects.
The system of claim 9, wherein the artificial intelligence server is further configured to:

transmit a notification to at least one user terminal associated with the one or more target smart objects.
The system of claim 9, wherein the one or more target smart objects are configured to perform an automated remediation according to the command, the automated remediation including resetting a smart object, repairing a smart object, replacing a smart object, activating a smart object, and/or turning off a smart object.
The system of claim 11, wherein the one or more target smart objects are further configured to send a result of the disposition to the artificial intelligence server.
The system of claim 12, further comprising a storage configured to store information relating to the anomaly, the disposition of the anomaly, and/or the result of the disposition.
The system of claim 8, wherein at least one of the plurality of smart objects is connected to a blockchain network or set as a node of the blockchain network.
The system of claim 14, wherein:

each of the plurality of user terminals is in communication with the blockchain network.
The system of claim 14, wherein the artificial intelligence server is connected to the blockchain network.
The system of claim 1, wherein the network is a blockchain network.
A system for monitoring a blockchain network, comprising:

an artificial intelligence server in communication with the blockchain network, the artificial intelligence server being configured to

obtain node information relating to a plurality of nodes of the blockchain network; and

detect an operating state of the blockchain network based on the node information and one or more analytic models;

wherein

the blockchain network is configured to facilitate an energy transaction; and

each of the plurality of nodes of the blockchain network is configured to endorse, order, or validate data related to the energy transaction.
The system of claim 18, wherein the one or more analytic models are trained using a machine learning algorithm based on historical node information relating to the plurality of nodes of the blockchain network.
The system of claim 19, wherein the historical node information includes functionality, capacity, and/or topological relation of the plurality of nodes.
The system of claim 18, wherein the operating state of the blockchain network specifies a state of each of the plurality of nodes.
The system of claim 18, wherein the artificial intelligence server is further configured to determine whether an anomaly exists in the plurality of nodes based on the operating state of the blockchain network, the anomaly including insufficient capacity, Crash Failure, Crash-Recovery Failure, and/or Byzantine Failure.
The system of claim 18, wherein the artificial intelligence server is further configured to:

in response to a determination that the anomaly exists in the plurality of nodes,

send a command including an automated remediation of at least one of the plurality of nodes to the blockchain network, the automated remediation including resetting a node, repairing a node, replacing a node, deleting a node, and/or adding a node of the plurality of nodes.
The system of claim 23, further comprising:

an administrator terminal in communication with the artificial intelligence server, the administrator terminal being associated with an administrator of the blockchain network.
The system of claim 24, wherein the artificial intelligence server is further configured to transmit a notification associated with the automated remediation to the administrator terminal.
A system for monitoring energy transactions in an energy grid, comprising:

a plurality of grid elements in communication with each other via a blockchain network, wherein each of the plurality of grid elements is registered in the energy grid; and

an artificial intelligence server configured to monitor energy transactions between the plurality of grid elements based on one or more analytic models.
The system of claim 26, further comprising:

a plurality of user terminals in communication with the artificial intelligence server, each of the plurality of user terminals being associated with one of the plurality of grid elements, each of the plurality of user terminals being configured to generate a transaction proposal associated with an energy transaction.
The system of claim 27, wherein the blockchain network is configured to generate a plurality of messages based on the transaction proposal.
The system of claim 28, wherein the artificial intelligence server is further configured to monitor the energy transactions based on the plurality of messages and the one or more analytic models.
The system of claim 26, wherein the one or more analytic models are trained using a machine learning algorithm based on historical transaction data.
The system of claim 26, wherein the artificial intelligence server is further configured to

generate an analysis result based on the energy transactions between the plurality of grid elements using the one or more analytic models; and

determine whether an anomaly exists in the energy transactions based on the analysis result, the anomaly including an unauthorized operation, a payment failure, and/or a transaction dispute.
The system of claim 31, wherein the artificial intelligence server is further configured to

in response to a determination that the anomaly exists in the energy transactions,

send a command including a disposition of the energy transactions to the blockchain network.
The system of claim 32, wherein the blockchain network is configured to automatically process the energy transactions to eliminate the anomaly according to the command.
A system for monitoring an energy grid, comprising:

a plurality of nodes connected with the energy grid configured to form a blockchain network, each of the plurality of nodes being in communication with each of other nodes of the plurality of nodes, and being capable of generating node data related to the blockchain network;

a plurality of smart objects connected with the energy grid, each of the plurality of smart objects being associated with one of a plurality of grid elements in the energy grid, and being capable of generating intelligent data based on output of at least one sensor in the each of the plurality of smart objects; and

an artificial intelligence server in communication with the energy grid, the plurality of nodes, and the plurality of smart objects, the artificial intelligence server being configured to

obtain the intelligent data from the each of the plurality of smart objects, the intelligent data including a description of an event;

obtain the node data from the each of the plurality of nodes, the node data including node information and transaction information;

determine an event type based on the intelligent data and the node data, the event type including a working condition of the plurality of smart objects, a working condition of the plurality of nodes in the system, and/or a transaction condition;

generate an analysis result based on the intelligent data, the node data and one or more analytic models associated with the event type;

determine whether an anomaly exists in the system and the energy grid based on the analysis result; and

in response to a determination that the anomaly exists in the system and the energy grid, send a command to at least one of the plurality of smart objects, and/or at least one of the plurality of nodes to perform an automated remediation.
The system of claim 34, wherein at least partial of the plurality of smart objects are intelligent energy meters configured to automatically execute a smart contract, settle an energy consumption, and/or act according to the command of the artificial intelligence server.
The system of claim 34, wherein, for each of the plurality of smart objects, the intelligent data is generated according to a smart contract embedded in the smart object, the smart contract including at least one of a time stamp, an ID of the smart contract, a type of the energy to be traded, an amount of the energy, a transaction method, or a transaction price of the energy.
The system of claim 34, wherein the one or more analytic models are associated with at least one of an anomaly detection, an anomaly positioning, a root cause identification, and an anomaly prediction.
The system of claim 37, wherein the anomaly prediction includes performance bottleneck analysis, capacity forecasting, and/or fault prediction.
The system of claim 34, wherein the analysis result includes an event type, a potential cause, a location, a time, and a recommended disposition of the event.
The system of claim 34, further comprising at least one storage device configured to store at least one of the analysis result, the command, and an outcome of an action.
The system of claim 40, wherein the artificial intelligence server is configured to send the analysis result and/or the outcome of the action to a user terminal in communication with the artificial intelligence server, the plurality of nodes, or the plurality of smart objects.
The system of claim 34, wherein the one or more analytic models are trained using a machine learning algorithm based on historical operation data associated with events of the determined event type, the historical operation data including a cause, a disposition and an event result, and/or log files of the events.