CN113537625A - Data sharing method considering energy consumption efficiency in power internet of things based on block chain - Google Patents
Data sharing method considering energy consumption efficiency in power internet of things based on block chain Download PDFInfo
- Publication number
- CN113537625A CN113537625A CN202110873613.6A CN202110873613A CN113537625A CN 113537625 A CN113537625 A CN 113537625A CN 202110873613 A CN202110873613 A CN 202110873613A CN 113537625 A CN113537625 A CN 113537625A
- Authority
- CN
- China
- Prior art keywords
- data
- preset
- current
- block chain
- network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000005265 energy consumption Methods 0.000 title abstract description 16
- 238000007689 inspection Methods 0.000 claims abstract description 60
- 238000012549 training Methods 0.000 claims abstract description 44
- 230000009471 action Effects 0.000 claims description 49
- 238000005457 optimization Methods 0.000 claims description 33
- 238000012795 verification Methods 0.000 claims description 32
- 238000003860 storage Methods 0.000 claims description 25
- 230000008447 perception Effects 0.000 claims description 16
- 230000007613 environmental effect Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000006855 networking Effects 0.000 claims 1
- 230000005540 biological transmission Effects 0.000 abstract description 8
- 230000008569 process Effects 0.000 description 24
- 229920000314 poly p-methyl styrene Polymers 0.000 description 16
- 238000013135 deep learning Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 13
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 230000000875 corresponding effect Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000013500 data storage Methods 0.000 description 6
- 230000033001 locomotion Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 239000000126 substance Substances 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002787 reinforcement Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000001351 cycling effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/64—Protecting data integrity, e.g. using checksums, certificates or signatures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/35—Utilities, e.g. electricity, gas or water
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
- G16Y20/40—Information sensed or collected by the things relating to personal data, e.g. biometric data, records or preferences
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/50—Safety; Security of things, users, data or systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Human Resources & Organizations (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Bioethics (AREA)
- Computer Hardware Design (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Accounting & Taxation (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a data sharing method considering energy consumption efficiency in an electric power Internet of things based on a block chain, which is used for solving the technical problems of low data transmission safety and integrity, low data sharing rate and high energy consumption of the existing data sharing method. Wherein, the invention includes: training an optimal routing inspection path at a routing inspection site of the power system; patrolling the power system based on the optimal patrolling path to obtain sensing data; and uploading the sensing data to a preset block chain.
Description
Technical Field
The invention relates to the technical field of data sharing, in particular to a data sharing method considering energy consumption efficiency in an electric power Internet of things based on a block chain.
Background
With the deep fusion of the internet of things technology and a smart grid, the intelligent mining of mass user side data, the safe sharing of energy data, the real-time processing of routing inspection data and the wide interconnection of edge data of a power system, the ubiquitous power internet of things with comprehensive sensing of the construction state and ubiquitous data connection becomes a current research hotspot, and the mass data sensing and the safe sharing in the power internet of things become key problems to be solved urgently.
The large-scale power system is easy to generate high-frequency abnormal conditions of power transmission (distribution) equipment in the long-term operation process in the field (or indoor) severe environment, the traditional manual regular inspection operation mode is relied on, the workload is large, the efficiency is low, the investment cost is high, the life safety of operators can be threatened by long-period power inspection operation in the complex environment, and therefore, the intelligent robot inspection becomes a safe and efficient alternative mode.
However, how to collect high-quality data on the site of a power system by using a mobile intelligent device (such as a mobile intelligent device, an unmanned aerial vehicle, etc.) and realize safe and real-time data sharing is a problem to be solved urgently. On one hand, in the case that the endurance and sensing range of a Mobile Smart Terminal (MST) are limited, how to obtain more high-quality data perception is very important. On the other hand, how to share the sensed data to other MSTs and promote mutual understanding and cooperation among devices so as to complete the allocation task better is one of the key problems to be solved urgently.
The traditional centralized power internet of things system structure provides a serious challenge for data privacy, data real-time sharing and low-delay transmission. In addition, the existing robot inspection mostly takes manual operation as a main part, and the optimization of the inspection path of the robot under the condition of limited cruising ability is not considered, so that the data sharing rate is improved.
In summary, the existing power internet of things data sensing and sharing have the following disadvantages: firstly, after high-definition data of a power system field acquired by the mobile intelligent device are transmitted back to a base for processing by using a centralized power Internet of things system, the safety and integrity of the data cannot be guaranteed; secondly, the problem of insufficient cruising ability of the unmanned aerial vehicle can not be fully considered when manual operation is used for on-site routing inspection; finally, the existing motion path optimization algorithm of the mobile intelligent device does not have the autonomous learning capability, and the minimum energy consumption cost of the mobile intelligent device can not be realized while sharing data as much as possible.
Disclosure of Invention
The invention provides a data sharing method considering energy consumption efficiency in an electric power Internet of things based on a block chain, which is used for solving the technical problems of low data transmission safety and integrity, low data sharing rate and high energy consumption of the existing data sharing method.
The invention provides a data sharing method of an electric power Internet of things, which is applied to mobile intelligent equipment and comprises the following steps:
training an optimal routing inspection path at a routing inspection site of the power system;
patrolling the power system based on the optimal patrolling path to obtain sensing data;
and uploading the sensing data to a preset block chain.
Optionally, the step of training an optimal patrol route at a patrol site of the power system includes:
acquiring the current environmental state of the power system at the current moment of the inspection site;
inputting the current environment state into a preset first network to obtain a current output action;
calculating rewards according to the current output action and the current environment state, and generating a next environment state;
storing the current environmental state, the current output action, the reward, and the next environmental state in a preset playback pool;
judging whether the current time is equal to a preset time or not, if not, adopting the time corresponding to the next environment state as the current time, and returning to the step of inputting the current environment state into a preset first network to obtain a current output action until the current time is equal to the preset time;
acquiring a training sample from the playback pool, calculating a target value of the training sample through a preset second network, and obtaining a strategy gradient based on the target value;
optimizing the second network based on the target value to obtain a second optimization parameter;
optimizing the first network by adopting the strategy gradient to obtain a first optimization parameter;
and generating an optimal routing inspection path based on the first optimization parameter and the second optimization parameter.
Optionally, the step of uploading the sensing data to a preset block chain includes:
obtaining a private key;
signing the perception data by adopting the private key to obtain encrypted data;
sending the encrypted data to a preset authentication and authorization center for verification;
and when receiving verification passing information returned by the authentication and authorization center, sending the encrypted data to a preset block chain.
Optionally, the step of sending the encrypted data to a preset block chain when receiving verification passing information returned by the authentication and authorization center includes:
when verification passing information returned by the authentication and authorization center is received, a storage request is sent to the block chain; the storage request carries the encrypted data; and the block chain is used for verifying the encrypted data and storing the sensing data when the verification is passed.
The invention also provides a data sharing device of the power Internet of things, which is applied to mobile intelligent equipment, and the device comprises:
the optimal routing inspection path training module is used for training an optimal routing inspection path on a routing inspection site of the power system;
the perception data acquisition module is used for patrolling the power system based on the optimal patrolling path to acquire perception data;
and the uploading module is used for uploading the sensing data to a preset block chain.
Optionally, the optimal patrol path training module includes:
the current environment state acquisition submodule is used for acquiring the current environment state of the power system at the current moment of the inspection site;
the current output action acquisition submodule is used for inputting the current environment state into a preset first network to obtain a current output action;
the reward calculation submodule is used for calculating reward according to the current output action and the current environment state and generating the next environment state;
a storage submodule, configured to store the current environment state, the current output action, the reward, and the next environment state in a preset playback pool;
the circulation submodule is used for judging whether the current time is equal to a preset time or not, if not, the time corresponding to the next environment state is taken as the current time, and the step of inputting the current environment state into a preset first network to obtain the current output action is returned until the current time is equal to the preset time;
the strategy gradient generation submodule is used for acquiring a training sample from the playback pool, calculating a target value of the training sample through a preset second network, and obtaining a strategy gradient based on the target value;
a second optimization parameter obtaining submodule, configured to optimize the second network based on the target value, so as to obtain a second optimization parameter;
a first optimization parameter obtaining submodule, configured to optimize the first network by using the policy gradient to obtain a first optimization parameter;
and the optimal routing inspection path generation submodule is used for generating an optimal routing inspection path based on the first optimization parameter and the second optimization parameter.
Optionally, the upload module includes:
the private key obtaining sub-module is used for obtaining a private key;
the encryption submodule is used for signing the sensing data by adopting the private key to obtain encrypted data;
the verification sub-module is used for sending the encrypted data to a preset authentication authorization center for verification;
and the uploading sub-module is used for sending the encrypted data to a preset block chain when receiving verification passing information returned by the authentication and authorization center.
Optionally, the upload sub-module includes:
the uploading unit is used for sending a storage request to the block chain when receiving verification passing information returned by the authentication and authorization center; the storage request carries the encrypted data; and the block chain is used for verifying the encrypted data and storing the sensing data when the verification is passed.
The invention also provides an electronic device comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is used for executing the data sharing method of the power internet of things according to instructions in the program codes.
The invention also provides a computer readable storage medium for storing program code for executing the data sharing method of the power internet of things as described in any one of the above.
According to the technical scheme, the invention has the following advantages: the optimal routing inspection path of the mobile intelligent equipment on the routing inspection site of the power system is trained based on the preset deterministic strategy gradient algorithm, so that the mobile intelligent equipment can share data as much as possible to the maximum extent and reduce the energy consumption cost. Meanwhile, the security and the integrity of data storage are improved in a mode that sensing data sensed in the inspection process are uploaded to a block chain for storage.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a flowchart illustrating steps of a data sharing method for an internet of things of electric power according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a deep reinforcement learning process according to an embodiment of the present invention;
fig. 3 is a flowchart illustrating steps of training an optimal routing inspection path according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of data sensing based on multi-agent DRL according to an embodiment of the present invention;
FIG. 5 is an MST training framework provided by embodiments of the present invention;
fig. 6 is a flowchart illustrating a procedure of uploading sensing data to a predetermined block chain according to an embodiment of the present invention;
fig. 7 is a block diagram of a data sharing apparatus of an electric power internet of things according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a data sharing method considering energy consumption efficiency in an electric power Internet of things based on a block chain, which is used for solving the technical problems of low data transmission safety and integrity, low data sharing rate and high energy consumption in the existing data sharing method.
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a flowchart illustrating steps of a data sharing method for an internet of things of electric power according to an embodiment of the present invention.
The invention provides a data sharing method of an electric power Internet of things, which is applied to mobile intelligent equipment, wherein the mobile intelligent equipment can comprise an inspection robot and an unmanned aerial vehicle, and the method specifically comprises the following steps:
101, training an optimal routing inspection path on a routing inspection site of a power system;
the problem that the insufficient cruising ability of the unmanned aerial vehicle cannot be fully considered when manual operation is carried out on-site routing inspection; and the problem that the existing mobile intelligent equipment motion path optimization algorithm does not have autonomous learning capability and cannot realize minimum energy consumption cost per se while sharing data as much as possible, the embodiment of the invention models the optimal routing inspection path learning of the mobile intelligent equipment into a Markov Decision Process (MDP) with a continuous motion space. Each mobile smart device MST is an agent whose goal is to maximize its overall reward by learning the optimal patrol path policy through interaction with the environment. Because the invention is oriented to distributed and continuous multi-agent data sensing and sharing, the traditional DRL (Deep Learning) algorithm cannot meet the text requirement. Therefore, in the embodiment of the invention, a multi-agent DRL solution based on DDPG is provided to realize the optimal path training among the multi-agents. In particular, a mixed cooperation-competition relationship exists between the MSTs which are communicated with each other, and a single MST can cooperate with other MSTs to complete the field data perception of the power system. However, in the case that the total amount of data points is relatively fixed, there is a case that MSTs compete with each other in order to maximize the self-reward. In one example, a multi-agent DRL can employ a framework of centralized training, decentralized execution. During the training process, the additional information of the department MST (e.g., actions, rewards, training cycles, etc.) may be used to train the cooperative learning strategies of other MSTs. But may not use the private information of other MSTs in the process of execution to maintain independence and autonomy of the MSTs.
The markov decision process is a mathematical model of sequential decisions for simulating stochastic strategies and returns achievable by an agent in an environment where the system state has markov properties. The MDP is built based on a set of interactive objects, namely agents and environments, with elements including state, actions, policies and rewards. In the simulation of MDP, the agent perceives the current system state and acts on the environment in a strategic manner, thereby changing the state of the environment and receiving rewards, the accumulation of which over time is referred to as rewards.
DRL combines the perception ability of Deep Learning (DL) and the decision-making ability of Reinforcement Learning (RL), can be controlled directly according to input state information, and is an artificial intelligence method closer to a human thinking mode. The brief learning process may be as shown in FIG. 2:
at each moment, agent (software or hardware entity capable of autonomous activity, such as mobile intelligent device in the embodiment of the present invention) interacts with the environment to obtain an observation at a high latitude, and senses the observation (Observations) by using a DL method to obtain a specific state feature representation; evaluating a cost function of each Action based on expected Reward (Reward), and mapping the current state to a corresponding Action (Action) through a certain strategy; the Environment (Environment) reacts to this action and gets the next observation, and by continuously cycling the above processes, the optimal strategy for achieving the goal can be finally obtained.
102, patrolling the power system based on the optimal patrolling path to obtain sensing data;
in the embodiment of the invention, the mobile intelligent equipment can acquire the field data of the power system (such as a transformer substation, a power transmission line and the like) and acquire the running condition of the equipment.
And 103, uploading the sensing data to a preset block chain.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, a confidential algorithm and the like, and has the characteristics of decentralization, no tampering, trace remaining in the whole process, traceability, collective maintenance, openness and transparency and the like.
In order to provide a safe data storage and sharing service, the mobile intelligent device in the embodiment of the invention can realize distributed storage and sharing of the sensed field data through the blockchain with the help of the edge server.
The optimal routing inspection path of the mobile intelligent equipment on the routing inspection site of the power system is trained based on the preset deterministic strategy gradient algorithm, so that the mobile intelligent equipment can share data as much as possible to the maximum extent and reduce the energy consumption cost. Meanwhile, the security and the integrity of data storage are improved in a mode that sensing data sensed in the inspection process are uploaded to a block chain for storage.
Referring to fig. 3, fig. 3 is a flowchart illustrating a procedure for training an optimal routing inspection path according to an embodiment of the present invention.
In the embodiment of the present invention, the step of training the optimal routing inspection path at the routing inspection site of the power system may specifically include:
s31, acquiring the current environmental state of the power system at the current moment of the inspection site;
s32, inputting the current environment state into a preset first network to obtain the current output action;
s33, calculating reward according to the current output action and the current environment state, and generating the next environment state;
s34, storing the current environment state, the current output action, the reward and the next environment state in a preset playback pool;
s35, judging whether the current time is equal to a preset time, if not, adopting the time corresponding to the next environment state as the current time, and returning to the step of inputting the current environment state into a preset first network to obtain the current output action until the current time is equal to the preset time;
s36, obtaining training samples from the playback pool, calculating the target value of the training samples through a preset second network, and obtaining a strategy gradient based on the target value;
s37, optimizing the second network based on the target value to obtain a second optimization parameter;
s38, optimizing the first network by adopting a strategy gradient to obtain a first optimization parameter;
and S39, generating an optimal routing inspection path based on the first optimization parameter and the second optimization parameter.
In one example of the present invention, an embodiment of the present invention proposes a DDPG based multi-agent DRL solution to achieve optimal path training between multi-agents. In particular, a mixed cooperation-competition relationship exists between the MSTs which are communicated with each other, and a single MST can cooperate with other MSTs to complete the field data perception of the power system. However, in the case that the total amount of data points is relatively fixed, there is a case that MSTs compete with each other in order to maximize the self-reward. In one example, a multi-agent DRL can employ a framework of centralized training, decentralized execution. During the training process, the additional information (e.g., actions, rewards, training periods, etc.) of some MSTs may be used to train the cooperative learning strategies of other MSTs. But may not use the private information of other MSTs in the process of execution to maintain independence and autonomy of the MSTs.
Referring to fig. 4, fig. 4 shows a schematic diagram of data sensing based on multi-agent DRL.
As shown in fig. 4, states, actions and rewards are the basic three elements of a DRL, and given a state and a series of alternative actions, the goal of MST is to find a strategy that maximizes the cumulative rewards. It is assumed that MSTm (m 1, 2,.., m) is generated by observing the environmentAnd selects an actionActing on the environment, a prize r can be obtainedt m. The system environment is composed of a group of states, including current routing inspection data point distribution, MST position coordinates, historical tracks and the like. After the action is executedAfter that, the environmental state is represented by stIs converted into st+1. The present invention defines the following for status, actions and rewards:
1) state space S: (S) { (S)1,S2,S3) Is a description of the environment. Wherein S1Representing coordinate positions of the patrol data points and the obstacle in the two-dimensional area. The definition is as follows:
wherein the content of the first and second substances,representing a set of obstacles within the sensing region,representing a set of data points within the sensing region that need to be collected,xn,xc∈[0,Qx],yn,yc∈[0,Qy],Qx、Qyrespectively representing the X, Y-axis coordinate maximum of a mobile smart device (MST) perception data region.
S2The current position of the MST in the two-dimensional region is defined, and the formula is expressed as follows:
wherein the content of the first and second substances,representing a set of mobile smart devices, defined as:the coordinates representing the MSTm are shown,representing the percentage of remaining power at time t of MSTm.
S3Representing the perceived time h of the data point n accumulated at time tt(n)∈[0,T]And T represents the maximum number of time periods in each data sensing round.
ht+1(n)=ht(n)+1
2) An action space A: the motion space defines the continuous motion behavior of the MST within the two-dimensional target region:
wherein the content of the first and second substances,indicates the direction (angle) of the MST movement,indicates the distance moved,/maxIndicating the maximum distance that the MST can move within a unit time t.
3) Reward R: the reward includes a perceived amount of dataEnergy consumptionWhere energy consumption is mainly due to MST data perception and self-movement. Suppose thatα represents the energy expended to perceive a unit of data and β represents the energy expended to move a unit of distance.
Thus awarding rt mThe calculation can be as follows:
each MST is trained by four groups of deep neural networks, including an action network Actor network mu (s | theta)μ) Critic network Q (s, a | θ)Q) Target network T _ Actor and T _ critical. In the embodiment of the present invention, as shown in fig. 5, an action network Actor network and a target network T _ Actor constitute a first network; critic network Q (s, a | θ)Q) And the target network T _ Critic form a second network; wherein, thetaμAnd thetaQIs a random initialization parameter of the Actor and Critic networks, and an initial parameter theta of the T _ Actor network and the T _ Critic networkμ':=θμ,θQ':=θQ. The function of each neural network is as follows:
1) an Actor network: is responsible for thetaμIterative updating of parameters based on the input current environmental state stSelecting a Current output action atFor interacting with the environment and generating a next state st+1Receive the current award rt。
2) Critic network: is responsible for thetaQIteratively updating the parameters and calculating the current Q value Q (s, a | theta)Q)。
3) T _ Actor network: selecting the optimal next action a 'according to the small batch of training samples sampled in the experience playback pool B'tNetwork parameter θμ'Periodically from thetaμAnd (6) updating.
4) T _ Critic network: responsible for calculating Q ' (s ', a ' | theta)Q') Network parameter θQ'Periodically from thetaQAnd (6) updating.
In each round of data perception, the MST first observes the ambient state stE is S, will state StThe input is sent to the Actor network to generate an action output at. To increase the randomness of the training process and the exploration of the state space, a certain noise can be added to the selected actions, atThe calculation formula is as follows:
wherein the noiseCan be generated according to the Ornstein-Ullenbeck random procedure (Omstein-Uhlenbeck, Ou).
In the centralized training process, each MST has a private playback pool BmTransferring samples(s) in a storage statet,at,rt,st+1) And H samples are adopted from each private playback pool to form H groups of small training samples. Target T _ Actor network outputs action a 'through small-batch training samples'tCritic networks pass through the minimization of the Loss function Loss (θ)Q) Updating the parameters of the self, wherein the formula is as follows:
the target value y of the training sample is then calculated according to the following formulat:
Where γ ∈ (0, 1) represents the discount factor.
Then, the Actor network is updated according to the policy gradient, and the formula is as follows:
wherein the content of the first and second substances,it is noted that the target network, T _ Actor network and T _ critical network, are two copies of the Actor and critical networks. After the parameters of the Actor network and the critical network are updated, in order to improve the stability of the learning process, the parameters of the T _ Actor and the T _ critical network may be updated in a soft update manner. The details are as follows:
θμ':=τθμ+(1-τ)θμ'
θQ':=τθQ+(1-τ)θQ'
wherein τ is an update factor, and generally takes a small value (e.g., 0.1 or 0.01). After sufficient learning, all parameters of the neural network are optimized to obtain the optimal action selection strategy, so that the optimal routing inspection path is obtained. The data sensing task is completed through the optimal routing inspection path, and energy consumption cost can be reduced.
In one example, the multi-agent optimal patrol path learning process is as shown in table 1 below:
TABLE 1
Referring to fig. 6, fig. 6 is a flowchart illustrating a procedure for uploading sensing data to a predetermined block chain according to an embodiment of the present invention.
In this embodiment of the present invention, the step of uploading the sensing data to the preset block chain may include:
s61, obtaining a private key;
s62, signing the sensing data by using a private key to obtain encrypted data;
s63, sending the encrypted data to a preset authentication and authorization center for verification;
and S64, when the verification passing information returned by the authentication and authorization center is received, sending the encrypted data to a preset block chain.
In practical applications, in order to provide a secure data storage and sharing service, a private chain may be constructed based on Ethereum (etherhouse), wherein the private chain includes a miner node and a non-miner node.
Ethereum is an open-source, intelligent contract-enabled, common blockchain platform that provides decentralized ethernet Virtual machines (Ethereum Virtual machines) to handle point-to-point contracts via its dedicated cryptocurrency ethernet (ETH, abbreviated as "ETH").
1) A miner node: the data sharing transaction is written into the block and participates in transaction verification on the basis of meeting the block chain consensus protocol. Considering that the participation of block consensus and verification requires certain computational power of the MST, the embodiment of the present invention introduces the edge computing server to help the MST complete the computation task, and adds the block passing the verification to the blockchain network.
2) Non-miner nodes: since the non-mineworker node is only responsible for accepting and broadcasting the data sharing transaction request, it need not possess the same computing resources as the mineworker node.
According to the block chain characteristics, each Ethereum node keeps a complete and verified block chain and MST service copy. Assuming that each MST is actively connected to the blockchain network, after each round of data sensing, the MST uploads the data sensed from the power system site to the blockchain. Therefore, in the u-th round, the total number of data storage requests issued by all MSTs is Y ═ M × u. Where M is the number of MSTs and u is the number of data sensing rounds. In addition, to ensure that the data sent to the blockchain network is valid and not forged, the MST needs to encrypt the data using its own private key to verify the legitimacy of the data source. The data sharing process is shown in table 2 below.
TABLE 2
In Table 2, idm: represents the identity (identity) obtained after registration of the MST numbered m;
certm: an authentication certificate obtained after registration of MST with the number m;
pkm: public key of MST with number m;
skm: a private key secret key representing MST numbered m;
wam: a blockchain wallet address representing MST numbered m;
the MST with the number of m is represented in the u-th data sensing round, and the total amount of the collected data is accumulated;
the authentication authorization center verifies the encrypted data packet with the private key signature to prevent data from being forged.
In a specific implementation, Gen (1) is performed firstv) Obtaining public-private key pair (pk) of MST mm,skm) In which 1 isvIndicating a security parameter. The total number of rounds of MST perceptual data is U, each round comprising T time periods. Thus, the amount of data that MST cumulatively senses after the end of each data sensing round is as follows:
wherein the content of the first and second substances,indicating the tth time of MSTm in sensing round uSegment-aware data volume. MST uses its own private key pkmAnd after the data is signed, sending the data to an authentication and authorization center for verification. The certificate authority decrypts the data packet and verifies whether the data packet is a legitimate MST transmission. In addition, obtained after decryptionAnd the data stored in the MST is compared with the data stored in the MST so as to prevent data from being forged. After receiving the storage request from the MST, the blockchain verifies the signature on the request and determines whether to submit the transaction to the blockchain network based on the verification result. The submitted request transaction will be mined by the miner node and written to the new block.
The distributed storage and sharing of the routing inspection data of the power system are realized by using the block chain, and the safety and the integrity of the power data are ensured. Meanwhile, the decentralized sharing mode improves the flexibility and the access efficiency of the system.
Referring to fig. 7, fig. 7 is a block diagram of a data sharing device of an electric power internet of things according to an embodiment of the present invention.
The embodiment of the invention provides a data sharing device of an electric power Internet of things, which is applied to mobile intelligent equipment and comprises:
an optimal routing inspection path training module 701, configured to train an optimal routing inspection path at a routing inspection site of the power system;
a perception data obtaining module 702, configured to patrol the power system based on the optimal patrol route, and obtain perception data;
an uploading module 703 is configured to upload the sensing data to a preset block chain.
In this embodiment of the present invention, the optimal routing inspection path training module 701 includes:
the current environment state acquisition submodule is used for acquiring the current environment state of the power system at the current moment of the inspection site;
the current output action acquisition submodule is used for inputting the current environment state into a preset first network to obtain a current output action;
the reward calculation submodule is used for calculating reward according to the current output action and the current environment state and generating the next environment state;
the storage submodule is used for storing the current environment state, the current output action, the reward and the next environment state in a preset playback pool;
the circulation submodule is used for judging whether the current time is equal to the preset time or not, if not, the time corresponding to the next environment state is adopted as the current time, and the step of inputting the current environment state into the preset first network to obtain the current output action is returned until the current time is equal to the preset time;
the strategy gradient generation submodule is used for acquiring a training sample from the playback pool, calculating the target value of the training sample through a preset second network, and obtaining a strategy gradient based on the target value;
the second optimization parameter obtaining submodule is used for optimizing a second network based on the target value to obtain a second optimization parameter;
the first optimization parameter obtaining submodule is used for optimizing the first network by adopting strategy gradient to obtain a first optimization parameter;
and the optimal routing inspection path generation submodule is used for generating an optimal routing inspection path based on the first optimization parameter and the second optimization parameter.
In this embodiment of the present invention, the upload module 703 includes:
the private key obtaining sub-module is used for obtaining a private key;
the encryption submodule is used for signing the sensing data by adopting a private key to obtain encrypted data;
the verification sub-module is used for sending the encrypted data to a preset authentication authorization center for verification;
and the uploading sub-module is used for sending the encrypted data to the preset block chain when receiving the verification passing information returned by the authentication and authorization center.
In an embodiment of the present invention, the upload sub-module includes:
the uploading unit is used for sending a storage request to the block chain when receiving verification passing information returned by the authentication and authorization center; the storage request carries encrypted data; the block chain is used for verifying the encrypted data and storing the sensing data when the verification is passed.
The invention also provides an electronic device comprising a processor and a memory:
the memory is used for storing the program codes and transmitting the program codes to the processor;
the processor is used for executing the data sharing method of the power internet of things according to the instructions in the program codes.
The embodiment of the invention also provides a computer-readable storage medium, which is used for storing the program codes, and the program codes are used for executing the data sharing method of the power internet of things in the embodiment of the invention.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A data sharing method of an electric power Internet of things is applied to mobile intelligent equipment, and comprises the following steps:
training an optimal routing inspection path at a routing inspection site of the power system;
patrolling the power system based on the optimal patrolling path to obtain sensing data;
and uploading the sensing data to a preset block chain.
2. The method of claim 1, wherein the step of training an optimal routing inspection path at a routing inspection site of the power system comprises:
acquiring the current environmental state of the power system at the current moment of the inspection site;
inputting the current environment state into a preset first network to obtain a current output action;
calculating rewards according to the current output action and the current environment state, and generating a next environment state;
storing the current environmental state, the current output action, the reward, and the next environmental state in a preset playback pool;
judging whether the current time is equal to a preset time or not, if not, adopting the time corresponding to the next environment state as the current time, and returning to the step of inputting the current environment state into a preset first network to obtain a current output action until the current time is equal to the preset time;
acquiring a training sample from the playback pool, calculating a target value of the training sample through a preset second network, and obtaining a strategy gradient based on the target value;
optimizing the second network based on the target value to obtain a second optimization parameter;
optimizing the first network by adopting the strategy gradient to obtain a first optimization parameter;
and generating an optimal routing inspection path based on the first optimization parameter and the second optimization parameter.
3. The method of claim 1, wherein the step of uploading the perception data to a preset blockchain comprises:
obtaining a private key;
signing the perception data by adopting the private key to obtain encrypted data;
sending the encrypted data to a preset authentication and authorization center for verification;
and when receiving verification passing information returned by the authentication and authorization center, sending the encrypted data to a preset block chain.
4. The method according to claim 3, wherein the step of sending the encrypted data to a preset block chain when receiving verification passing information returned by the certificate authority comprises:
when verification passing information returned by the authentication and authorization center is received, a storage request is sent to the block chain; the storage request carries the encrypted data; and the block chain is used for verifying the encrypted data and storing the sensing data when the verification is passed.
5. The utility model provides a data sharing device of electric power thing networking which characterized in that is applied to mobile intelligent equipment, the device includes:
the optimal routing inspection path training module is used for training an optimal routing inspection path on a routing inspection site of the power system;
the perception data acquisition module is used for patrolling the power system based on the optimal patrolling path to acquire perception data;
and the uploading module is used for uploading the sensing data to a preset block chain.
6. The apparatus of claim 5, wherein the optimal routing inspection path training module comprises:
the current environment state acquisition submodule is used for acquiring the current environment state of the power system at the current moment of the inspection site;
the current output action acquisition submodule is used for inputting the current environment state into a preset first network to obtain a current output action;
the reward calculation submodule is used for calculating reward according to the current output action and the current environment state and generating the next environment state;
a storage submodule, configured to store the current environment state, the current output action, the reward, and the next environment state in a preset playback pool;
the circulation submodule is used for judging whether the current time is equal to a preset time or not, if not, the time corresponding to the next environment state is taken as the current time, and the step of inputting the current environment state into a preset first network to obtain the current output action is returned until the current time is equal to the preset time;
the strategy gradient generation submodule is used for acquiring a training sample from the playback pool, calculating a target value of the training sample through a preset second network, and obtaining a strategy gradient based on the target value;
a second optimization parameter obtaining submodule, configured to optimize the second network based on the target value, so as to obtain a second optimization parameter;
a first optimization parameter obtaining submodule, configured to optimize the first network by using the policy gradient to obtain a first optimization parameter;
and the optimal routing inspection path generation submodule is used for generating an optimal routing inspection path based on the first optimization parameter and the second optimization parameter.
7. The apparatus of claim 5, wherein the upload module comprises:
the private key obtaining sub-module is used for obtaining a private key;
the encryption submodule is used for signing the sensing data by adopting the private key to obtain encrypted data;
the verification sub-module is used for sending the encrypted data to a preset authentication authorization center for verification;
and the uploading sub-module is used for sending the encrypted data to a preset block chain when receiving verification passing information returned by the authentication and authorization center.
8. The apparatus of claim 7, wherein the upload sub-module comprises:
the uploading unit is used for sending a storage request to the block chain when receiving verification passing information returned by the authentication and authorization center; the storage request carries the encrypted data; and the block chain is used for verifying the encrypted data and storing the sensing data when the verification is passed.
9. An electronic device, comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is used for executing the data sharing method of the power internet of things as claimed in any one of claims 1-4 according to instructions in the program code.
10. A computer-readable storage medium for storing program code for performing the data sharing method of the power internet of things of any one of claims 1-4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110873613.6A CN113537625A (en) | 2021-07-30 | 2021-07-30 | Data sharing method considering energy consumption efficiency in power internet of things based on block chain |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110873613.6A CN113537625A (en) | 2021-07-30 | 2021-07-30 | Data sharing method considering energy consumption efficiency in power internet of things based on block chain |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113537625A true CN113537625A (en) | 2021-10-22 |
Family
ID=78121645
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110873613.6A Pending CN113537625A (en) | 2021-07-30 | 2021-07-30 | Data sharing method considering energy consumption efficiency in power internet of things based on block chain |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113537625A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109446830A (en) * | 2018-11-13 | 2019-03-08 | 中链科技有限公司 | Data center environment information processing method and device based on block chain |
CN111754020A (en) * | 2020-05-14 | 2020-10-09 | 大唐七台河发电有限责任公司 | Intelligent power plant equipment inspection system and method based on data analysis |
CN112003886A (en) * | 2020-07-03 | 2020-11-27 | 北京工业大学 | Block chain-based Internet of things data sharing system and method |
CN112581026A (en) * | 2020-12-29 | 2021-03-30 | 杭州趣链科技有限公司 | Joint path planning method for logistics robot on alliance chain |
-
2021
- 2021-07-30 CN CN202110873613.6A patent/CN113537625A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109446830A (en) * | 2018-11-13 | 2019-03-08 | 中链科技有限公司 | Data center environment information processing method and device based on block chain |
CN111754020A (en) * | 2020-05-14 | 2020-10-09 | 大唐七台河发电有限责任公司 | Intelligent power plant equipment inspection system and method based on data analysis |
CN112003886A (en) * | 2020-07-03 | 2020-11-27 | 北京工业大学 | Block chain-based Internet of things data sharing system and method |
CN112581026A (en) * | 2020-12-29 | 2021-03-30 | 杭州趣链科技有限公司 | Joint path planning method for logistics robot on alliance chain |
Non-Patent Citations (4)
Title |
---|
CHI HAROLD LIU , QIUXIA LIN , SHILIN WEN: "Blockchain-Enabled Data Collection and Sharing for Industrial IoT With Deep Reinforcement Learning", 《IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS》 * |
CHI HAROLD LIU; ZHEYU CHEN; YUFENG ZHAN: "Energy-Efficient Distributed Mobile Crowd Sensing: A Deep Learning Approach", 《IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 》 * |
TING CAI,YUXIN WU,HUI LIN,YU CAI: "Blockchain-Empowered Big Data Sharing for Internet of Things", 《INTERNATIONAL JOURNAL OF WEB SERVICES RESEARCH》 * |
格雷拉-皮奇: "DDPGN算法流程", 《HTTPS://BLOG.CSDN.NET/WEIXIN_43897187/ARTICLE/DETAILS/109673711》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Lin et al. | Task offloading for wireless VR-enabled medical treatment with blockchain security using collective reinforcement learning | |
Dai et al. | Deep reinforcement learning and permissioned blockchain for content caching in vehicular edge computing and networks | |
Lu et al. | Communication-efficient federated learning and permissioned blockchain for digital twin edge networks | |
Zhou et al. | Cyber-physical-social systems: A state-of-the-art survey, challenges and opportunities | |
Qi et al. | Federated reinforcement learning: Techniques, applications, and open challenges | |
Li et al. | Resource optimization for delay-tolerant data in blockchain-enabled IoT with edge computing: A deep reinforcement learning approach | |
Luo et al. | Cloud-based information infrastructure for next-generation power grid: Conception, architecture, and applications | |
Kotb et al. | Cloud-based multi-agent cooperation for IoT devices using workflow-nets | |
Li et al. | Minimizing packet expiration loss with path planning in UAV-assisted data sensing | |
Wang et al. | Cooperative and competitive multi-agent systems: From optimization to games | |
He et al. | A blockchain-based scheme for secure data offloading in healthcare with deep reinforcement learning | |
Xu et al. | A survey on digital twin for industrial internet of things: Applications, technologies and tools | |
Carli et al. | A distributed control algorithm for optimal charging of electric vehicle fleets with congestion management | |
Khalid et al. | A secure trust method for multi-agent system in smart grids using blockchain | |
Kong et al. | A reliable and efficient task offloading strategy based on multifeedback trust mechanism for IoT edge computing | |
Hussin et al. | Improving reliability in resource management through adaptive reinforcement learning for distributed systems | |
Rjoub et al. | Explainable AI-based federated deep reinforcement learning for trusted autonomous driving | |
CN116614385A (en) | Service scheduling path planning method, device and equipment based on digital twin | |
Li et al. | Learning-based predictive control via real-time aggregate flexibility | |
Ding et al. | Distributed machine learning for uav swarms: Computing, sensing, and semantics | |
He et al. | Towards trusted node selection using blockchain for crowdsourced abnormal data detection | |
Xiao et al. | Deep reinforcement learning for optimal resource allocation in blockchain-based IoV secure systems | |
Cui et al. | A many-objective evolutionary algorithm based on constraints for collaborative computation offloading | |
CN114567560A (en) | Edge node dynamic resource allocation method based on generation confrontation simulation learning | |
Wang et al. | Wireless powered metaverse: Joint task scheduling and trajectory design for multi-devices and multi-UAVs |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211022 |
|
RJ01 | Rejection of invention patent application after publication |