CN111651461A - Energy storage operation monitoring method and system based on machine learning - Google Patents

Energy storage operation monitoring method and system based on machine learning Download PDF

Info

Publication number
CN111651461A
CN111651461A CN202010553872.6A CN202010553872A CN111651461A CN 111651461 A CN111651461 A CN 111651461A CN 202010553872 A CN202010553872 A CN 202010553872A CN 111651461 A CN111651461 A CN 111651461A
Authority
CN
China
Prior art keywords
energy storage
energy
distributed
monitoring
control point
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.)
Granted
Application number
CN202010553872.6A
Other languages
Chinese (zh)
Other versions
CN111651461B (en
Inventor
郭子健
郑熙
陈家良
商金来
陈祯
张玲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Kubo Energy Science & Technology Co ltd
Original Assignee
Shenzhen Kubo Energy Science & Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Kubo Energy Science & Technology Co ltd filed Critical Shenzhen Kubo Energy Science & Technology Co ltd
Priority to CN202010553872.6A priority Critical patent/CN111651461B/en
Publication of CN111651461A publication Critical patent/CN111651461A/en
Application granted granted Critical
Publication of CN111651461B publication Critical patent/CN111651461B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/22Indexing; Data structures therefor; Storage structures
    • G06F16/2228Indexing structures
    • G06F16/2246Trees, e.g. B+trees
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/245Query processing
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/248Presentation of query results
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00Machine learning
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management, e.g. organising, planning, scheduling or allocating time, human or machine resources; Enterprise planning; Organisational models
    • G06Q10/063Operations research or analysis
    • G06Q10/0639Performance analysis
    • G06Q10/06393Score-carding, benchmarking or key performance indicator [KPI] analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06Electricity, gas or water supply
    • HELECTRICITY
    • H02GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02JCIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00002Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
    • HELECTRICITY
    • H02GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02JCIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00032Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/80Management or planning
    • Y02P90/82Energy audits or management systems therefor

Abstract

The invention provides an energy storage operation monitoring method and system based on machine learning, wherein the method comprises the following steps: acquiring energy storage operation data of the distributed energy storage device; monitoring energy transmission data between the distributed energy storage device and a target load; performing pre-analysis on the energy storage operation data and the energy transmission data based on a machine learning algorithm to obtain a pre-analysis result; and transmitting the pre-analysis result to a display terminal for displaying. By monitoring the energy storage operation data and the energy transmission data of the target load and the distributed energy storage device and analyzing based on a machine learning algorithm, the method is convenient for effective monitoring and improves the rationality of the use of the distributed energy storage device on energy storage and the like.

Description

Energy storage operation monitoring method and system based on machine learning
Technical Field
The invention relates to the technical field of machine learning, in particular to an energy storage operation monitoring method and system based on machine learning.
Background
Energy storage is taken as an important support technology for energy internet development, more and more attention and recognition are paid, the market scale presents a rapid development situation, particularly on the user side, the fixed energy storage of industrial/commercial/residential users and the rapid development of electric vehicles, and the distributed energy storage resource scale of the user side stock is continuously enlarged.
The invention provides an energy storage operation monitoring method and system based on machine learning, which are provided by the invention, and have the advantages that when the energy storage is used by related loads such as a user side due to insufficient deep fusion of the current energy storage facility and an information technology, a user side and an energy storage device of the user side are not effectively monitored, so that a lot of negative effects are brought in the process of using the energy storage, for example, whether the energy use between the load and the energy storage device is reasonable or not can not be known in time.
Disclosure of Invention
The invention provides an energy storage operation monitoring method and system based on machine learning, which are used for analyzing energy storage operation data and energy transmission data related to a target load and a distributed energy storage device through monitoring and based on a machine learning algorithm, thereby facilitating effective monitoring and improving the rationality of the use of energy storage and the like.
The invention provides an energy storage operation monitoring method based on machine learning, which comprises the following steps:
acquiring energy storage operation data of the distributed energy storage device;
monitoring energy transmission data between the distributed energy storage device and a target load;
performing pre-analysis on the energy storage operation data and the energy transmission data based on a machine learning algorithm to obtain a pre-analysis result;
and transmitting the pre-analysis result to a display terminal for displaying.
In a possible implementation manner, the obtaining of the energy storage operation data of the distributed energy storage device includes:
based on an energy storage database, obtaining energy storage attributes of the distributed energy storage device, wherein the energy storage attributes are obtained based on energy storage indexes, and the energy storage indexes comprise: when external equipment transmits energy to be stored to the distributed energy storage devices, the energy storage efficiency of the distributed energy storage devices, the energy storage types of the distributed energy storage devices and the consumption efficiency of the distributed energy storage devices on the stored energy are improved;
establishing an energy storage structure tree related to the energy storage attribute, wherein the energy storage structure tree comprises energy storage nodes, and the energy storage nodes are arranged in one-to-one correspondence with the energy storage indexes;
collecting index parameters related to the energy storage indexes, and correspondingly storing the index parameters into related energy storage nodes based on timestamps and node storage rules;
and constructing the energy storage operation data based on all the index parameters stored in each storage node.
In one possible implementation manner, the monitoring of the energy transmission data between the distributed energy storage apparatus and the target load includes:
monitoring a current state of the target load;
when the current state of the target load is a working state, dynamically tracking an energy supplier of the target load, and judging whether the energy supplier is related to a distributed energy storage device;
if the correlation exists, the distributed energy storage device and the target load are synchronously monitored, and energy transmission data between the distributed energy storage device and the target load are obtained;
otherwise, the distributed energy storage devices are independently monitored, and energy loss data of the distributed energy storage devices are obtained;
and storing the energy transmission data and the energy loss data.
In a possible implementation manner, the pre-analyzing process of the energy storage operation data and the energy transmission data based on a machine learning algorithm includes:
performing first clustering processing on the energy storage operation data to obtain a first cluster set, wherein the first cluster set comprises n1 energy storage operation subsequences;
performing second clustering processing on the energy transmission data to obtain a second clustering set, wherein the second clustering set comprises n2 energy transmission subsequences;
establishing a mapping relation between the n1 energy storage operation subsequences and n2 energy transmission subsequences;
based on a machine learning algorithm, performing machine processing on the mapping relation, and judging whether a machine processing result is different from a normal data result in a machine database;
and if so, marking the subsequence corresponding to the machine processing result, and transmitting the subsequence to a display terminal for displaying.
In one possible implementation manner, in monitoring energy transmission data between the distributed energy storage apparatus and a target load, the method further includes:
monitoring the energy demand of the target load in a preset time period and the energy supply of the distributed energy storage device in the preset time period;
when the energy demand is greater than or equal to energy supply and an energy supplier of the target load is a distributed energy storage device, triggering a standby energy supply device to be in a standby state;
monitoring the residual energy of the distributed energy storage device in real time, and when the residual energy is in a preset energy range, triggering the standby energy supply device to be converted from a standby state to a working state and providing energy for the target load;
providing energy to the target load based on the distributed energy storage when the energy demand is less than the energy supply and the energy supplier of the target load is a distributed energy storage.
In a possible implementation manner, before obtaining the energy storage attribute of the distributed energy storage device based on the energy storage database, the method further includes:
testing the energy storage power and the energy storage efficiency of the distributed energy storage device, wherein the testing steps comprise:
when the target load is an empty load, acquiring initial instantaneous energy storage power and tail instantaneous energy storage power of the distributed energy storage device in an energy storage state within a preset time period based on the empty load;
calculating the energy storage efficiency of the distributed energy storage device according to the initial instantaneous energy storage power and the tail instantaneous energy storage power;
when the target load is a real load, acquiring initial instantaneous energy storage power and tail instantaneous energy storage power of the distributed energy storage device in an energy storage state within a preset time period based on the real load;
meanwhile, the energy storage time of the distributed energy storage device in an energy storage state is also obtained;
calculating the energy storage efficiency of the distributed energy storage device according to the initial instantaneous energy storage power, the tail instantaneous energy storage power and the energy storage time;
and storing the energy storage power and the energy storage efficiency into an energy storage database.
In one possible implementation manner, the method further includes: and monitoring the input control points of the distributed energy storage device in real time, wherein the monitoring step comprises the following steps:
step A1: acquiring all input control points of the distributed energy storage device, and controlling a first control point of all the input control points to be opened and a second control point to be closed based on an input rule, wherein the number of the first control points is N1, the number of the second control points is N2, N1+ N2 is N, and N represents the number of all the input control points;
step A2: calculating an energy loss value H1 of the second control point according to the following formula;
wherein G (K1, K2, K3) represents an energy loss function of the second control point based on an input interface position point K1 of the distributed storage device, an energy conversion efficiency K2 of the input interface, and an off state K3 of the input interface; i denotes the ith second control point in N2; r isiRepresenting the load capacity of the ith second control point; piThe effective power corresponding to the ith second control point; qiThe invalid power corresponding to the ith second control point; vN2Represents a nominal voltage of the second control point;
step A3: calculating an energy loss value H2 of the first control point according to the following formula;
wherein G (K11, K12, K13) represents an energy loss function of the first control point based on an input interface position point K11, an energy conversion efficiency K12 of an input interface, and an on state K13 of the input interface of the distributed storage device; i1 denotes the i1 th first control point in N1; r isi1Representing the load capacity of the ith first control point; pi1The effective power corresponding to the i1 th first control point; qi1The invalid power corresponding to the i1 th first control point; vN1A nominal voltage representative of the first control point;
step A4: determining an energy input deviation value D based on the distributed storage devices according to the first energy loss value H1 and a second energy loss value H2;
wherein μ represents a control adjustment factor based on a first control point corresponding to the first energy loss value;
step A5: when the energy input deviation value is lower than a preset deviation value, determining a first dynamic power adjustment threshold corresponding to the first control point and a second dynamic power adjustment threshold corresponding to the second control point according to the input attributes of all input control points and the energy input deviation value;
step A6: adjusting the input power of a corresponding input control point in the distributed energy storage device according to the first power adjustment threshold and the second power adjustment threshold;
step A7: and after the input power of the corresponding input control point is adjusted, continuing adjusting the adjusted input control point according to the steps A1-A6 until the energy input deviation value is not lower than the preset deviation value, and performing early warning and reminding.
In one possible implementation manner, the monitoring of the energy transmission data between the distributed energy storage apparatus and the target load further includes: verifying energy quality of target transmission energy between the distributed energy storage device and a target load, wherein the verifying step comprises:
recording target transmission energy of nodes at different time to obtain a recording result, wherein the recording result comprises: the adjustment frequency, the adjustment voltage and the peak-to-valley value of the target transmission energy;
monitoring the transmission process of target transmission energy between the distributed energy storage device and a target load in real time, and verifying whether energy blockage exists in the transmission process of the target transmission energy based on an energy verification database;
and if the load frequency deviation value corresponding to the load charge does not exceed the maximum frequency deviation, adjusting the existing energy blockage according to a preset time shifting rule and a recorded result.
The invention provides an energy storage operation monitoring system based on machine learning, which comprises:
the acquisition module is used for acquiring energy storage operation data of the distributed energy storage device;
the monitoring module is used for monitoring energy transmission data between the distributed energy storage device and a target load;
and the analysis module is used for performing pre-analysis on the energy storage operation data and the energy transmission data based on a machine learning algorithm to obtain a pre-analysis result, and transmitting the pre-analysis result to a display terminal for displaying.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a flowchart of an energy storage operation monitoring method based on machine learning according to an embodiment of the present invention;
fig. 2 is a structural diagram of an energy storage operation monitoring system based on machine learning according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
The invention provides an energy storage operation monitoring method based on machine learning, as shown in fig. 1, comprising the following steps:
step 1: acquiring energy storage operation data of the distributed energy storage device;
step 2: monitoring energy transmission data between the distributed energy storage device and a target load;
and step 3: performing pre-analysis on the energy storage operation data and the energy transmission data based on a machine learning algorithm to obtain a pre-analysis result;
and 4, step 4: and transmitting the pre-analysis result to a display terminal for displaying.
In this embodiment, the distributed energy storage device is used to improve energy storage efficiency, and the distributed energy storage device may be a device for storing electric energy;
the energy storage operation data are acquired, so that the operating condition of the distributed energy storage device can be known in time;
in this embodiment, the energy transmission data between the distributed energy storage device and the target load (user side, electrical equipment, etc.) is monitored to effectively determine energy consumption, energy storage, etc. between the distributed energy storage device and the target load;
in this embodiment, a machine learning algorithm is used for pre-analysis, for example, energy storage operation data and energy transmission data are compared and analyzed, and a comparison and analysis result is obtained, for example: the energy storage operation data is related to electric energy storage and electric energy loss, and the energy transmission data is that the distributed energy storage device supplies power to a target load and the like;
in this embodiment, the display terminal is, for example, an intelligent device such as a mobile phone and a computer.
The beneficial effects of the above technical scheme are: by monitoring the energy storage operation data and the energy transmission data of the target load and the distributed energy storage device and analyzing based on a machine learning algorithm, the method is convenient for effective monitoring and improves the rationality of the use of the distributed energy storage device on energy storage and the like.
The invention provides an energy storage operation monitoring method based on machine learning, which comprises the following steps of:
based on an energy storage database, obtaining energy storage attributes of the distributed energy storage device, wherein the energy storage attributes are obtained based on energy storage indexes, and the energy storage indexes comprise: when external equipment transmits energy to be stored to the distributed energy storage devices, the energy storage efficiency of the distributed energy storage devices, the energy storage types of the distributed energy storage devices and the consumption efficiency of the distributed energy storage devices on the stored energy are improved;
establishing an energy storage structure tree related to the energy storage attribute, wherein the energy storage structure tree comprises energy storage nodes, and the energy storage nodes are arranged in one-to-one correspondence with the energy storage indexes;
collecting index parameters related to the energy storage indexes, and correspondingly storing the index parameters into related energy storage nodes based on timestamps and node storage rules;
and constructing the energy storage operation data based on all the index parameters stored in each storage node.
In this embodiment, since the energy storage nodes correspond to the energy storage indexes one to one, the number of the nodes of the energy storage nodes may be 3;
in this embodiment, the index parameter is related to the energy storage index, for example, when the energy storage index is the energy storage efficiency, the corresponding index parameter includes: the distributed energy storage device is related to effective work, ineffective work and the like, and when the energy storage indexes are energy storage types, corresponding index parameters comprise the following parameters: energy conversion types and the like are related, and when the energy storage index is consumption efficiency, the corresponding index parameters comprise: the effective consumption power, the ineffective consumption power, etc. of the target load are related.
The beneficial effects of the above technical scheme are: the structure tree is built through energy storage attributes, energy storage nodes are optimized through energy storage indexes, energy storage parameters are collected and stored in the energy storage nodes, and then energy storage operation data are obtained conveniently.
The invention provides an energy storage operation monitoring method based on machine learning, which comprises the following steps of in the process of monitoring energy transmission data between a distributed energy storage device and a target load:
monitoring a current state of the target load;
when the current state of the target load is a working state, dynamically tracking an energy supplier of the target load, and judging whether the energy supplier is related to a distributed energy storage device;
if the correlation exists, the distributed energy storage device and the target load are synchronously monitored, and energy transmission data between the distributed energy storage device and the target load are obtained;
otherwise, the distributed energy storage devices are independently monitored, and energy loss data of the distributed energy storage devices are obtained;
and storing the energy transmission data and the energy loss data.
In this embodiment, the current state includes: working state and non-working state;
in the embodiment, the two situations are divided, namely when the target load is in a working state, the energy supplier is dynamically tracked, and whether the target load is related to the distributed energy storage device or not is judged, so that the function of the distributed energy storage device in the process can be effectively determined, and the target load can be effectively monitored.
In this embodiment, the energy supplier may directly supply the electric energy to the distributed energy storage device, or may supply the electric energy to the target load by using another energy supply device.
In the embodiment, when the target load is in a non-working state, the distributed energy storage device is monitored independently, so that the energy loss of the device is ensured in the process that no power is supplied to any external load.
The beneficial effects of the above technical scheme are: by monitoring the current state of the target load, monitoring in different modes is facilitated, and the efficiency of monitoring energy transmission data is facilitated to be improved.
The invention provides an energy storage operation monitoring method based on machine learning, which is based on a machine learning algorithm, and comprises the following steps of:
performing first clustering processing on the energy storage operation data to obtain a first cluster set, wherein the first cluster set comprises n1 energy storage operation subsequences;
performing second clustering processing on the energy transmission data to obtain a second clustering set, wherein the second clustering set comprises n2 energy transmission subsequences;
establishing a mapping relation between the n1 energy storage operation subsequences and n2 energy transmission subsequences;
based on a machine learning algorithm, performing machine processing on the mapping relation, and judging whether a machine processing result is different from a normal data result in a machine database;
and if so, marking the subsequence corresponding to the machine processing result, and transmitting the subsequence to a display terminal for displaying.
In this embodiment, the first clustering process is performed on the energy storage operation data, and if the energy storage data includes: performing a first clustering process, such as clustering classification of storage, consumption, conversion and the like, within the electric energy storage data, electric energy consumption data, electric energy conversion efficiency and the like;
in this embodiment, the second clustering process is performed on the energy transmission data, for example, clustering of the power receiving efficiency of the target load, the power providing efficiency of the target load by the distributed energy storage device, and the like is performed.
In this embodiment, n1 and n2 are respectively associated with the corresponding clustering results, for example: the energy storage operation subsequence comprises classification results such as storage, consumption and conversion corresponding to the time point A;
the energy transmission subsequence comprises the results of mutual energy transmission, conversion and the like of the distributed energy storage device corresponding to the time point A and the target load;
at this time, a mapping relationship between the transformation corresponding to the energy storage operation sub-sequence and the transformation corresponding to the energy transmission sub-sequence at the same time point a may be established.
In this embodiment, based on a machine learning algorithm, the mapping relationship is subjected to machine processing, and it is determined whether there is a difference between a machine processing result and a normal data result in the machine database, for example, it is determined whether the mapping relationship between the conversion corresponding to the energy storage operation sub-sequence and the conversion corresponding to the energy transmission sub-sequence is established at the same time point a, and the mapping relationship may be one-to-one, one-to-many, or many-to-one.
The beneficial effects of the above technical scheme are: through the energy storage operation subsequence of confirming energy storage operation data, and through the energy transmission subsequence of confirming energy transmission data, and then establish the mapping relation, carry out machine processing, be convenient for follow-up effective control, improve its rationality to use such as energy storage, provide the basis.
The invention provides an energy storage operation monitoring method based on machine learning, which further comprises the following steps in the process of monitoring energy transmission data between a distributed energy storage device and a target load:
monitoring the energy demand of the target load in a preset time period and the energy supply of the distributed energy storage device in the preset time period;
when the energy demand is greater than or equal to energy supply and an energy supplier of the target load is a distributed energy storage device, triggering a standby energy supply device to be in a standby state;
monitoring the residual energy of the distributed energy storage device in real time, and when the residual energy is in a preset energy range, triggering the standby energy supply device to be converted from a standby state to a working state and providing energy for the target load;
providing energy to the target load based on the distributed energy storage when the energy demand is less than the energy supply and the energy supplier of the target load is a distributed energy storage.
In the embodiment, by monitoring the energy demand of the target load and the energy supply of the distributed energy storage device, the subsequent supply device for the target load can be conveniently and effectively determined, the function of the target load is ensured to be sufficient, and the target load can conveniently and effectively work.
The beneficial effects of the above technical scheme are: by monitoring the energy demand and energy supply, the standby energy supply device is convenient to trigger in time, and the normal work of the target load is convenient to guarantee.
The invention provides an energy storage operation monitoring method based on machine learning, which is based on an energy storage database and comprises the following steps of before the energy storage attribute of a distributed energy storage device is obtained:
testing the energy storage power and the energy storage efficiency of the distributed energy storage device, wherein the testing steps comprise:
when the target load is an empty load, acquiring initial instantaneous energy storage power and tail instantaneous energy storage power of the distributed energy storage device in an energy storage state within a preset time period based on the empty load;
calculating the energy storage efficiency of the distributed energy storage device according to the initial instantaneous energy storage power and the tail instantaneous energy storage power;
when the target load is a real load, acquiring initial instantaneous energy storage power and tail instantaneous energy storage power of the distributed energy storage device in an energy storage state within a preset time period based on the real load;
meanwhile, the energy storage time of the distributed energy storage device in an energy storage state is also obtained;
calculating the energy storage efficiency of the distributed energy storage device according to the initial instantaneous energy storage power, the tail instantaneous energy storage power and the energy storage time;
and storing the energy storage power and the energy storage efficiency into an energy storage database.
In this embodiment, the preset time period may be any time period set by default.
The beneficial effects of the above technical scheme are: when the target load is an empty load and the distributed energy storage devices are in an energy storage state, the energy storage power of the distributed energy storage devices can be conveniently and effectively determined, when the target load is a real load and the distributed energy storage devices are in the energy storage state, the energy storage efficiency of the distributed energy storage devices can be conveniently and effectively determined, and convenience is brought to follow-up monitoring.
The invention provides an energy storage operation monitoring method based on machine learning, which further comprises the following steps: and monitoring the input control points of the distributed energy storage device in real time, wherein the monitoring step comprises the following steps:
step A1: acquiring all input control points of the distributed energy storage device, and controlling a first control point of all the input control points to be opened and a second control point to be closed based on an input rule, wherein the number of the first control points is N1, the number of the second control points is N2, N1+ N2 is N, and N represents the number of all the input control points;
step A2: calculating an energy loss value H1 of the second control point according to the following formula;
wherein G (K1, K2, K3) represents an energy loss function of the second control point based on an input interface position point K1 of the distributed storage device, an energy conversion efficiency K2 of the input interface, and an off state K3 of the input interface; i denotes the ith second control point in N2; r isiRepresenting the load capacity of the ith second control point; piThe effective power corresponding to the ith second control point; qiThe invalid power corresponding to the ith second control point; vN2Represents a nominal voltage of the second control point;
step A3: calculating an energy loss value H2 of the first control point according to the following formula;
wherein G (K11, K12, K13) represents an energy loss function of the first control point based on an input interface position point K11, an energy conversion efficiency K12 of an input interface, and an on state K13 of the input interface of the distributed storage device; i1 denotes the i1 th first control point in N1; r isi1Representing the load capacity of the ith first control point; pi1The effective power corresponding to the i1 th first control point; qi1The invalid power corresponding to the i1 th first control point; vN1A nominal voltage representative of the first control point;
step A4: determining an energy input deviation value D based on the distributed storage devices according to the first energy loss value H1 and a second energy loss value H2;
wherein μ represents a control adjustment factor based on a first control point corresponding to the first energy loss value;
step A5: when the energy input deviation value is lower than a preset deviation value, determining a first dynamic power adjustment threshold corresponding to the first control point and a second dynamic power adjustment threshold corresponding to the second control point according to the input attributes of all input control points and the energy input deviation value;
step A6: adjusting the input power of a corresponding input control point in the distributed energy storage device according to the first power adjustment threshold and the second power adjustment threshold;
step A7: and after the input power of the corresponding input control point is adjusted, continuing adjusting the adjusted input control point according to the steps A1-A6 until the energy input deviation value is not lower than the preset deviation value, and performing early warning and reminding.
The beneficial effects of the above technical scheme are: all input control points of the distributed energy storage device are obtained, the first control point is opened, the second control point is closed, the first control point and the second control point can be effectively adjusted according to the requirement of a target load, the effectiveness of energy output of the first control point and the second control point is improved, energy loss values corresponding to the first control point and the second control point are calculated, the energy input deviation value is convenient to effectively calculate, the power of the first control point and the power of the second control point are effectively adjusted, the effective output of the first control point and the power of the second control point are improved, and a foundation is provided for follow-up effective monitoring of energy transmission.
The invention provides an energy storage operation monitoring method based on machine learning, which further comprises the following steps in the process of monitoring energy transmission data between a distributed energy storage device and a target load: verifying energy quality of target transmission energy between the distributed energy storage device and a target load, wherein the verifying step comprises:
recording target transmission energy of nodes at different time to obtain a recording result, wherein the recording result comprises: the adjustment frequency, the adjustment voltage and the energy peak-valley value of the target transmission energy;
monitoring the transmission process of target transmission energy between the distributed energy storage device and a target load in real time, and verifying whether energy blockage exists in the transmission process of the target transmission energy based on an energy verification database;
if the target load exists, monitoring the load charge of the target load, and if the load frequency deviation value corresponding to the load charge does not exceed the maximum frequency deviation, adjusting the existing energy blockage according to a preset time shifting rule and a recorded result;
if the load frequency deviation value corresponding to the load charge exceeds the maximum frequency deviation, adjusting the load frequency of the load charge until the load frequency deviation value corresponding to the load charge does not exceed the maximum frequency deviation, and continuing to execute subsequent operation;
based on the adjustment result, an energy quality of the target transmission energy is determined.
In this embodiment, the energy congestion may refer to that when the target loads a1, a2, a3 are supplied with electric energy based on the distributed storage device, the electric energy transmission is delayed in the process of supplying the electric energy to the target load a3, and at this time, the electric energy is considered to be congested, and at this time, the electric energy needs to be adjusted.
In this embodiment, the performing of the subsequent operation refers to adjusting the existing energy blockage according to a preset time shifting rule and a recorded result;
in this embodiment, the energy quality of the target transmission energy may be determined based on the adjustment of the energy blockage, so that the reliability of energy transmission may be effectively ensured.
The beneficial effects of the above technical scheme are: by recording the target transmission energy and monitoring the transmission process in real time, the energy jam condition can be effectively verified, the energy jam is adjusted, the energy quality can be effectively determined, a basis is provided for energy transmission data, and the transmission of related data can be guaranteed on the basis of reliable energy quality.
An embodiment of the present invention provides an energy storage operation monitoring system based on machine learning, as shown in fig. 2, including:
the acquisition module is used for acquiring energy storage operation data of the distributed energy storage device;
the monitoring module is used for monitoring energy transmission data between the distributed energy storage device and a target load;
and the analysis module is used for performing pre-analysis on the energy storage operation data and the energy transmission data based on a machine learning algorithm to obtain a pre-analysis result, and transmitting the pre-analysis result to a display terminal for displaying.
The beneficial effects of the above technical scheme are: by monitoring the energy storage operation data and the energy transmission data of the target load and the distributed energy storage device and analyzing based on a machine learning algorithm, the method is convenient for effective monitoring and improves the rationality of the use of the distributed energy storage device on energy storage and the like.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (9)

1. An energy storage operation monitoring method based on machine learning is characterized by comprising the following steps:
acquiring energy storage operation data of the distributed energy storage device;
monitoring energy transmission data between the distributed energy storage device and a target load;
performing pre-analysis on the energy storage operation data and the energy transmission data based on a machine learning algorithm to obtain a pre-analysis result;
and transmitting the pre-analysis result to a display terminal for displaying.
2. The energy storage operation monitoring method according to claim 1, wherein the process of obtaining energy storage operation data of the distributed energy storage device comprises:
based on an energy storage database, obtaining energy storage attributes of the distributed energy storage device, wherein the energy storage attributes are obtained based on energy storage indexes, and the energy storage indexes comprise: when external equipment transmits energy to be stored to the distributed energy storage devices, the energy storage efficiency of the distributed energy storage devices, the energy storage types of the distributed energy storage devices and the consumption efficiency of the distributed energy storage devices on the stored energy are improved;
establishing an energy storage structure tree related to the energy storage attribute, wherein the energy storage structure tree comprises energy storage nodes, and the energy storage nodes are arranged in one-to-one correspondence with the energy storage indexes;
collecting index parameters related to the energy storage indexes, and correspondingly storing the index parameters into related energy storage nodes based on timestamps and node storage rules;
and constructing the energy storage operation data based on all the index parameters stored in each storage node.
3. The energy storage operation monitoring method according to claim 1, wherein the monitoring of the energy transmission data between the distributed energy storage device and the target load comprises:
monitoring a current state of the target load;
when the current state of the target load is a working state, dynamically tracking an energy supplier of the target load, and judging whether the energy supplier is related to a distributed energy storage device;
if the correlation exists, the distributed energy storage device and the target load are synchronously monitored, and energy transmission data between the distributed energy storage device and the target load are obtained;
otherwise, the distributed energy storage devices are independently monitored, and energy loss data of the distributed energy storage devices are obtained;
and storing the energy transmission data and the energy loss data.
4. The energy storage operation monitoring method according to claim 1, wherein the process of performing pre-analysis on the energy storage operation data and the energy transmission data based on a machine learning algorithm includes:
performing first clustering processing on the energy storage operation data to obtain a first cluster set, wherein the first cluster set comprises n1 energy storage operation subsequences;
performing second clustering processing on the energy transmission data to obtain a second clustering set, wherein the second clustering set comprises n2 energy transmission subsequences;
establishing a mapping relation between the n1 energy storage operation subsequences and n2 energy transmission subsequences;
based on a machine learning algorithm, performing machine processing on the mapping relation, and judging whether a machine processing result is different from a normal data result in a machine database;
and if so, marking the subsequence corresponding to the machine processing result, and transmitting the subsequence to a display terminal for displaying.
5. The energy storage operation monitoring method according to claim 1, wherein in the process of monitoring energy transmission data between the distributed energy storage apparatus and a target load, further comprising:
monitoring the energy demand of the target load in a preset time period and the energy supply of the distributed energy storage device in the preset time period;
when the energy demand is greater than or equal to energy supply and an energy supplier of the target load is a distributed energy storage device, triggering a standby energy supply device to be in a standby state;
monitoring the residual energy of the distributed energy storage device in real time, and when the residual energy is in a preset energy range, triggering the standby energy supply device to be converted from a standby state to a working state and providing energy for the target load;
providing energy to the target load based on the distributed energy storage when the energy demand is less than the energy supply and the energy supplier of the target load is a distributed energy storage.
6. The energy storage operation monitoring method according to claim 2, wherein before obtaining the energy storage attribute of the distributed energy storage device based on the energy storage database, the method further comprises:
testing the energy storage power and the energy storage efficiency of the distributed energy storage device, wherein the testing steps comprise:
when the target load is an empty load, acquiring initial instantaneous energy storage power and tail instantaneous energy storage power of the distributed energy storage device in an energy storage state within a preset time period based on the empty load;
calculating the energy storage efficiency of the distributed energy storage device according to the initial instantaneous energy storage power and the tail instantaneous energy storage power;
when the target load is a real load, acquiring initial instantaneous energy storage power and tail instantaneous energy storage power of the distributed energy storage device in an energy storage state within a preset time period based on the real load;
meanwhile, the energy storage time of the distributed energy storage device in an energy storage state is also obtained;
calculating the energy storage efficiency of the distributed energy storage device according to the initial instantaneous energy storage power, the tail instantaneous energy storage power and the energy storage time;
and storing the energy storage power and the energy storage efficiency into an energy storage database.
7. The energy storage operation monitoring method of claim 1, further comprising: and monitoring the input control points of the distributed energy storage device in real time, wherein the monitoring step comprises the following steps:
step A1: acquiring all input control points of the distributed energy storage device, and controlling a first control point of all the input control points to be opened and a second control point to be closed based on an input rule, wherein the number of the first control points is N1, the number of the second control points is N2, N1+ N2 is N, and N represents the number of all the input control points;
step A2: calculating an energy loss value H1 of the second control point according to the following formula;
wherein G (K1, K2, K3) represents an energy loss function of the second control point based on an input interface position point K1 of the distributed storage device, an energy conversion efficiency K2 of the input interface, and an off state K3 of the input interface; i denotes the ith second control point in N2; r isiRepresenting the load capacity of the ith second control point; piThe effective power corresponding to the ith second control point; qiThe invalid power corresponding to the ith second control point; vN2Represents a nominal voltage of the second control point;
step A3: calculating an energy loss value H2 of the first control point according to the following formula;
wherein G (K11, K12, K13) represents an energy loss function of the first control point based on an input interface position point K11, an energy conversion efficiency K12 of an input interface, and an on state K13 of the input interface of the distributed storage device; i1 denotes the i1 th first control point in N1; r isi1Representing the load capacity of the ith first control point; pi1The effective power corresponding to the i1 th first control point; qi1The invalid power corresponding to the i1 th first control point; vN1A nominal voltage representative of the first control point;
step A4: determining an energy input deviation value D based on the distributed storage devices according to the first energy loss value H1 and a second energy loss value H2;
wherein μ represents a control adjustment factor based on a first control point corresponding to the first energy loss value;
step A5: when the energy input deviation value is lower than a preset deviation value, determining a first dynamic power adjustment threshold corresponding to the first control point and a second dynamic power adjustment threshold corresponding to the second control point according to the input attributes of all input control points and the energy input deviation value;
step A6: adjusting the input power of a corresponding input control point in the distributed energy storage device according to the first power adjustment threshold and the second power adjustment threshold;
step A7: and after the input power of the corresponding input control point is adjusted, continuing adjusting the adjusted input control point according to the steps A1-A6 until the energy input deviation value is not lower than the preset deviation value, and performing early warning and reminding.
8. The energy storage operation monitoring method according to claim 1, wherein the monitoring of the energy transmission data between the distributed energy storage device and the target load further comprises: verifying energy quality of target transmission energy between the distributed energy storage device and a target load, wherein the verifying step comprises:
recording target transmission energy of nodes at different time to obtain a recording result, wherein the recording result comprises: the adjustment frequency, the adjustment voltage and the peak-to-valley value of the target transmission energy;
monitoring the transmission process of target transmission energy between the distributed energy storage device and a target load in real time, and verifying whether energy blockage exists in the transmission process of the target transmission energy based on an energy verification database;
and if the load frequency deviation value corresponding to the load charge does not exceed the maximum frequency deviation, adjusting the existing energy blockage according to a preset time shifting rule and a recorded result.
9. An energy storage operation monitoring system based on machine learning, comprising:
the acquisition module is used for acquiring energy storage operation data of the distributed energy storage device;
the monitoring module is used for monitoring energy transmission data between the distributed energy storage device and a target load;
and the analysis module is used for performing pre-analysis on the energy storage operation data and the energy transmission data based on a machine learning algorithm to obtain a pre-analysis result, and transmitting the pre-analysis result to a display terminal for displaying.
CN202010553872.6A 2020-06-17 2020-06-17 Energy storage operation monitoring method and system based on machine learning Active CN111651461B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010553872.6A CN111651461B (en) 2020-06-17 2020-06-17 Energy storage operation monitoring method and system based on machine learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010553872.6A CN111651461B (en) 2020-06-17 2020-06-17 Energy storage operation monitoring method and system based on machine learning

Publications (2)

Publication Number Publication Date
CN111651461A true CN111651461A (en) 2020-09-11
CN111651461B CN111651461B (en) 2020-12-18

Family

ID=72347306

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010553872.6A Active CN111651461B (en) 2020-06-17 2020-06-17 Energy storage operation monitoring method and system based on machine learning

Country Status (1)

Country Link
CN (1) CN111651461B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102280935A (en) * 2011-06-24 2011-12-14 中国科学院电工研究所 Intelligent power grid management system
CN102738815A (en) * 2012-05-28 2012-10-17 深圳市科陆电子科技股份有限公司 System and method for managing energy-storage equipment system
CN102867239A (en) * 2012-09-12 2013-01-09 华电国际电力股份有限公司山东分公司 Low-carbon dispatching module for intelligent operation control system of regional power generation company
CN103559653A (en) * 2013-11-08 2014-02-05 国家电网公司 Energy-storing configuration evaluation method based on microgrid
CN107154626A (en) * 2017-06-02 2017-09-12 张飞飞 Distributed photovoltaic intelligent energy manages SaaS systems with energy storage
US9960637B2 (en) * 2015-07-04 2018-05-01 Sunverge Energy, Inc. Renewable energy integrated storage and generation systems, apparatus, and methods with cloud distributed energy management services
CN109870057A (en) * 2017-12-01 2019-06-11 萨博能源物联网科技(苏州)有限公司 A kind of energy supply operation system

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102280935A (en) * 2011-06-24 2011-12-14 中国科学院电工研究所 Intelligent power grid management system
CN102738815A (en) * 2012-05-28 2012-10-17 深圳市科陆电子科技股份有限公司 System and method for managing energy-storage equipment system
CN102867239A (en) * 2012-09-12 2013-01-09 华电国际电力股份有限公司山东分公司 Low-carbon dispatching module for intelligent operation control system of regional power generation company
CN103559653A (en) * 2013-11-08 2014-02-05 国家电网公司 Energy-storing configuration evaluation method based on microgrid
US9960637B2 (en) * 2015-07-04 2018-05-01 Sunverge Energy, Inc. Renewable energy integrated storage and generation systems, apparatus, and methods with cloud distributed energy management services
CN107154626A (en) * 2017-06-02 2017-09-12 张飞飞 Distributed photovoltaic intelligent energy manages SaaS systems with energy storage
CN109870057A (en) * 2017-12-01 2019-06-11 萨博能源物联网科技(苏州)有限公司 A kind of energy supply operation system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
胡阳春: ""基于改进k均值聚类算法的电力负荷模式识别方法研究"", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 *

Also Published As

Publication number Publication date
CN111651461B (en) 2020-12-18

Similar Documents

Publication Publication Date Title
CN109492667A (en) A kind of feature selecting discrimination method for non-intrusive electrical load monitoring
CN104022552A (en) Intelligent detection method for electric vehicle charging control
Maddikunta et al. Predictive model for battery life in IoT networks
Tripathi et al. Dynamic prediction of powerline frequency for wide area monitoring and control
CN105225065A (en) Based on serondary lithium battery supervisory system and the management method thereof of Electronic Health Record system
Adhikaree et al. Cloud-based battery condition monitoring platform for large-scale lithium-ion battery energy storage systems using internet-of-things (IoT)
CN105137215A (en) Medical equipment cost-benefit wireless monitoring analysis system and medical equipment cost-benefit wireless monitoring analysis method
CN109934356A (en) A kind of computer room method for inspecting and relevant device based on big data
CN111651461B (en) Energy storage operation monitoring method and system based on machine learning
CN106600465A (en) Processing apparatus, system and method for electricity fee exception
Luo et al. Power system reliability evaluation using self organizing map
Petrović et al. Enabling Adaptivity in IoT-based Smart Grid Architecture
CN103825301B (en) A kind of unified interface modeling method of distributed energy access active distribution system
CN101155369A (en) Power-saving system and method for mobile device
CN109657943A (en) Dynamic assessment method, device and the electronic equipment of wind power plant operating states of the units
CN107807860B (en) Power failure analysis method and system based on matrix decomposition
CN108681625A (en) Transformer short period overload capability intelligent evaluation system based on big data technology
CN111711209B (en) Optical storage and charging combined operation method and system based on energy storage life and frequency modulation performance
CN113009869A (en) Intelligent power maintenance management system
CN107662506A (en) A kind of method and apparatus of intelligent monitoring wireless charging
CN110647086B (en) Intelligent operation and maintenance monitoring system based on operation big data analysis
CN111260505B (en) Big data analysis method and device based on power Internet of things and computer equipment
CN211702078U (en) Battery manager based on cloud-end mixed state estimation
CN102055032B (en) Initiative maintenance management digital system for accumulator energy
Lai et al. A dynamic power features selection method for multi-appliance recognition on cloud-based smart grid

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
GR01 Patent grant
GR01 Patent grant