CN114362221B - Regional intelligent power grid partition evaluation method based on deep reinforcement learning - Google Patents

Regional intelligent power grid partition evaluation method based on deep reinforcement learning Download PDF

Info

Publication number
CN114362221B
CN114362221B CN202210048549.2A CN202210048549A CN114362221B CN 114362221 B CN114362221 B CN 114362221B CN 202210048549 A CN202210048549 A CN 202210048549A CN 114362221 B CN114362221 B CN 114362221B
Authority
CN
China
Prior art keywords
partition
evaluation index
power
time
micro
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.)
Active
Application number
CN202210048549.2A
Other languages
Chinese (zh)
Other versions
CN114362221A (en
Inventor
华昊辰
陈星莺
董正涛
余昆
甘磊
梅飞
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.)
Hohai University HHU
Original Assignee
Hohai University HHU
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 Hohai University HHU filed Critical Hohai University HHU
Priority to CN202210048549.2A priority Critical patent/CN114362221B/en
Publication of CN114362221A publication Critical patent/CN114362221A/en
Application granted granted Critical
Publication of CN114362221B publication Critical patent/CN114362221B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/28—Arrangements for balancing of the load in a network by storage of energy
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0206—Price or cost determination based on market factors
    • 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
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/12—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load
    • H02J3/14—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load by switching loads on to, or off from, network, e.g. progressively balanced loading
    • H02J3/144—Demand-response operation of the power transmission or distribution network
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/381—Dispersed generators
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
    • H02J3/466—Scheduling the operation of the generators, e.g. connecting or disconnecting generators to meet a given demand
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/20—The dispersed energy generation being of renewable origin
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/40—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation wherein a plurality of decentralised, dispersed or local energy generation technologies are operated simultaneously
    • Y—GENERAL 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
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B70/00—Technologies for an efficient end-user side electric power management and consumption
    • Y02B70/30—Systems integrating technologies related to power network operation and communication or information technologies for improving the carbon footprint of the management of residential or tertiary loads, i.e. smart grids as climate change mitigation technology in the buildings sector, including also the last stages of power distribution and the control, monitoring or operating management systems at local level
    • Y02B70/3225—Demand response systems, e.g. load shedding, peak shaving
    • Y—GENERAL 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
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S20/00—Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
    • Y04S20/20—End-user application control systems
    • Y04S20/222—Demand response systems, e.g. load shedding, peak shaving
    • Y—GENERAL 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
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
    • Y04S50/14—Marketing, i.e. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Health & Medical Sciences (AREA)
  • Power Engineering (AREA)
  • Accounting & Taxation (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Finance (AREA)
  • Evolutionary Computation (AREA)
  • Tourism & Hospitality (AREA)
  • Mathematical Physics (AREA)
  • Educational Administration (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Supply And Distribution Of Alternating Current (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a regional intelligent power grid partition evaluation method based on deep reinforcement learning, which comprises the following steps: (1) establishing a multi-micro-grid system partition evaluation index system; (2) setting a multi-microgrid system power balance limit; (3) establishing an evaluation index weight intelligent agent; (4) Constructing an evaluation index system of the intra-zone and inter-zone dividing effect; (5) designing a multi-micro-grid partition comprehensive evaluation index; (6) A multi-microgrid repartitioning mechanism is designed that accounts for system node variations. According to the regional intelligent power grid partition evaluation index system, multiple indexes are considered, and the regional intelligent power grid partition evaluation index system is more comprehensive than the existing regional intelligent power grid partition indexes; the invention adopts a deep reinforcement learning method, determines the weights of various indexes based on the historical data of each node, is easier to resist the influence of bad data on the weights, and has stronger robustness; the invention can update and adjust the partition evaluation index system in time according to the state change of the network nodes so as to ensure the rationality and coordination of the partition evaluation index.

Description

Regional intelligent power grid partition evaluation method based on deep reinforcement learning
Technical Field
The invention relates to the application field of crossing technology of power system theory and artificial intelligence, in particular to a regional intelligent power grid partition evaluation method based on deep reinforcement learning.
Background
At present, the traditional energy sources such as petroleum, natural gas and the like are gradually exhausted, and the problems of environmental pollution, excessive carbon emission and the like in the development and utilization of the energy sources are increasingly severe. Development of renewable energy and construction of micro-grids are effective ways to promote green transformation of energy systems and achieve the goals of "peak carbon, carbon neutralization". In a regional smart grid system comprising a plurality of micro-grids and containing a high proportion of renewable energy sources, a distributed power source is connected with a load and an energy storage device through an energy router to promote energy to be changed from unidirectional supply to bidirectional interaction. Due to the development of the sensing technology of the Internet of things and the power electronic technology, various distributed renewable energy sources can be effectively fused with the regional intelligent power grid system, and the distributed renewable energy sources can respond quickly along with the change of load demands. But the access of controllable equipment greatly increases the decision complexity and the system control problem dimension of the regional smart grid system energy management. Therefore, in the scene of containing high proportion renewable energy sources, how to design reasonable energy scheduling and management and control strategies in order to reduce the overall operation and maintenance cost of the intelligent power grid system to the greatest extent, promote the full in-situ consumption of the renewable energy sources, improve the energy utilization efficiency and reduce the carbon emission becomes a problem to be solved urgently. And the implementation of energy scheduling and management and control strategies directly aiming at regional intelligent power grid scenes of high-proportion renewable energy sources can encounter dimension disasters. Therefore, the dimension of the control problem needs to be reduced, the control problem is decomposed into a plurality of sub-problems, namely, the overall control problem of the regional intelligent power grid system is converted into the control problem of a plurality of sub-regions, and the regional intelligent power grid system is partitioned, so that 'local autonomous first and wide area interconnection later' are realized. However, how do reasonably effective partitioning proceed? The determination of regional smart grid system partition boundaries typically depends on certain partition indicators. The construction of a reasonable, comprehensive and efficient partition index system is particularly important.
The traditional regional intelligent power grid partition index has the following defects:
(1) The partition index is too simple. Only the system power distribution, the energy flow and the geographic factors are considered, comprehensive consideration on various indexes is lacked, and the system power distribution, the energy flow and the geographic factors cannot be effectively matched with actual conditions. Multiple indexes are required to be incorporated into an evaluation system to perform scientific and reasonable evaluation on the partition method.
(2) Conventional partitioning metrics typically take into account line loss, power balancing, and other factors. However, with the development of energy storage technology in recent years, more and more energy storage devices are used in regional smart grid systems. Conventional partition indicators are not effective in this situation.
(3) The weight value is set manually, and errors exist. The conventional partition indexes are generally based on index weight values set by people, and have errors with actual conditions, so that the follow-up partition results are affected.
Disclosure of Invention
The invention aims to: the invention aims to provide a regional intelligent power grid partition evaluation method based on deep reinforcement learning, which has intelligence, coordination, sociality and self-learning.
The technical scheme is as follows: the regional intelligent power grid partition evaluation method based on deep reinforcement learning provided by the invention comprises the following steps of:
(1) Establishing a multi-micro-grid system partition evaluation index system, wherein the multi-micro-grid system partition evaluation index system comprises an intra-area evaluation index system and an inter-area evaluation index system;
(1.1) establishing an intra-area evaluation index system of the multi-micro-grid system partition, wherein the evaluation indexes in the intra-area evaluation index system comprise:
renewable energy utilization rate:P c (t) is the actual power of renewable energy source at time t, P st (t) is the rated power of renewable energy source at the moment t, and t is the moment of the multi-microgrid system;
degree of supply and demand balance in a zone:P prc (t) is the power generated by the energy supply side at time t, P u (t) is the user load at time t;
distributed power supply adjustable capacity: e (E) in,3 ＝P st (t)-P c (t)，P c (t) is the actual power of renewable energy source at time t, P st (t) is the rated power of renewable energy source at time t;
degree of electrical coupling between nodes: e (E) in,4 When there is energy interaction between the nodes, its value is 1; when there is no interaction between the nodes, its value is 0;
load and distributed power supply matching degree:P c (t) is the actual power of renewable energy source at time t, P u (t) is the user load at time t;
energy storage device adjustable capacity: e (E) in,6 ＝P ba,st (t)-P ba,c (t)，P ba,c (t) is the actual power generated by the energy storage device at the moment t, P ba,st And (t) is the rated power of the energy storage device at the moment t.
(1.2) establishing a section evaluation index system of a multi-micro-grid system partition, wherein evaluation indexes in the section evaluation index system comprise:
interval average electrical distance:L cir,i sigma L is the electrical distance between the current partition and the surrounding ith partition cir,i N is the sum of the electrical distances of the current zone and the surrounding zones cir The number of surrounding partitions;
interval power interaction capacity: e (E) ex,2 ＝∑P cir,i (t)，P cir,i (t) is the interaction power of the partition and the ith partition around the partition at time t, ΣP cir,i (t) is the sum of the interaction power of the current partition and the surrounding partitions at time t;
power scheduling cost: e (E) ex,3 For each interaction of the partition and surrounding partitions, 1kElectric energy loss generated by Wh electric energy;
line loss: e (E) ex,4 The sum of the power loss generated by the power interaction of the partition and the surrounding partitions is the sum of the power loss generated by the power interaction of the partition and the surrounding partitions;
whether each sub-area is connected to the backbone: e (E) ex,5 When the partition is connected with the backbone network, the value is 1; when the partition is not connected with the backbone network, the value is 0;
energy storage equipment breakage cost: e (E) ex,6 The loss of the energy storage device generated for each time of storing/releasing 1kWh of electric energy by the energy storage device;
E in,i and E is ex,i Is the main component of the corresponding in-zone and out-zone evaluation index.
(2) Setting power balance limit of the multi-micro-grid system; the power balance relation corresponding to the power balance limit in the step (2) is as follows:
P trans (t)＝P prc (t)-P u (t)
wherein P is trans (t) represents the interaction power of the micro-grid and the backbone network at the moment t, P prc (t) represents the power generated by the energy supply side at time t, P u And (t) represents the user coincidence power at the moment t.
(3) Establishing an evaluation index weight intelligent agent;
(3.1) setting the observed state quantity required by the agent: the method comprises the following steps of (1) and (2) and comprises the following steps of:
s t ∈S:{E in,i,t ,E ex,i,t }
in the state space S, E in,i,t Representing the state quantity of the index in the ith zone at the time t, E ex,i,t Representing the state quantity of the ith interval index at the time t, s t The state of the intelligent agent at the time t is shown, and t is the time at which the multi-micro-grid system is located;
(3.2) setting an action value of the agent: the actions of the agent include increasing the weight, decreasing the weight and not changing, the action space is as follows:
a t ∈A{0,1,2}
in the motion space a, 0 means decreasing weight, 1 means increasing weight, and 2 means not changing;
(3.3) setting an agent rewarding function when the agent is in state s t Action a is taken at that time t The obtained rewards are the running cost of the multi-micro network system at the time t, and the running cost is as follows:
r t ＝P trans ×R t ×Δt
wherein r is t Representing the running cost of the multi-micro-grid system at the time t, R t The method comprises the steps of expressing the interactive electricity price of a multi-micro-grid system and a backbone network at the moment t, wherein deltat represents the action time interval;
(3.4) simulating the motion of the agent using the deep neural network, inputting the state quantity in the motion space into the deep neural network, and outputting the index weight value λ (s, a) in the observed state by the deep neural network:
λ(s,a)＝E(r t +λ(s t+1 ,a t+1 )|s t ,a t )
wherein lambda (s, a) represents the state s of observation of the agent t When and as desired to take action, E () represents the desired value.
(4) Constructing an evaluation index system of the intra-zone and inter-zone dividing effect; the evaluation index systems of the zone division effect and the zone division effect in the step (4) are respectively as follows:
G in ＝∑ i λ in,i E in,i ,G ex ＝∑ i λ ex,i E ex,i
wherein G is in And G ex Respectively, is an evaluation index of the intra-zone and inter-zone dividing effect, lambda in,i And lambda (lambda) ex,i The higher index value represents a better dynamic partitioning strategy for the principal component contribution coefficient; the partition evaluation index system changes with the change of the state information of the micro-grid.
(5) Designing a multi-micro-grid partition comprehensive evaluation index; the formula of the multi-micro-grid partition comprehensive evaluation index in the step (5) is as follows:
wherein G is in,j G is the j-th in-zone evaluation index ex,j And n is the number of partitions for the j-th interval evaluation index.
(6) Designing a multi-micro-network re-partition mechanism taking system node change into consideration; the step (6) specifically comprises the following steps: considering the change of the nodes of the multi-micro-grid system along with the environment and time, if a certain block of the system is partitioned, comprehensively evaluating the index M IE Less than 90% of the original, the multi-micro-network needs to be partitioned again; if the comprehensive evaluation index M of all partitions in the system IE And if the current partition strategy is greater than 90% of the original partition strategy, the current partition strategy is better, and re-partition is not needed.
A computer storage medium having stored thereon a computer program which, when executed by a processor, implements a regional smart grid partition assessment method based on deep reinforcement learning as described above.
A computer device comprises a storage, a processor and a computer program which is stored in the storage and can be run on the processor again, wherein the processor realizes the regional intelligent power grid partition evaluation method based on deep reinforcement learning when executing the computer program.
The beneficial effects are that: compared with the prior art, the invention has the following advantages:
1. according to the regional intelligent power grid partition evaluation index system, multiple indexes such as renewable energy utilization rate, in-region supply and demand balance degree, distributed power supply adjustable capacity, electric coupling degree among nodes, load and distributed power supply matching degree, energy storage equipment adjustable capacity, interval average electric distance, interval power interaction capacity, power scheduling cost, line loss, whether each subarea is connected with a main network, energy storage equipment damage cost and the like are considered, and the regional intelligent power grid partition evaluation index system is more comprehensive than the existing regional intelligent power grid partition indexes;
2. the invention adopts a deep reinforcement learning method, determines the weights of various indexes based on the historical data of each node, is easier to resist the influence of bad data on the weights, and has stronger robustness;
3. the invention can update and adjust the partition evaluation index system in time according to the state change of the network nodes so as to ensure the rationality and coordination of the partition evaluation index.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a schematic diagram of partitioning a multi-microgrid system according to a partition evaluation index system.
Detailed Description
The technical scheme of the invention is further described below with reference to the accompanying drawings.
As shown in fig. 1 and 2, a regional smart grid partition evaluation method based on deep reinforcement learning includes the following steps:
(1) Establishing a multi-micro-grid system partition evaluation index system, wherein the multi-micro-grid system partition evaluation index system comprises an intra-area evaluation index system and an inter-area evaluation index system;
(1.1) establishing an intra-area evaluation index system of the multi-micro-grid system partition, wherein the evaluation indexes in the intra-area evaluation index system comprise:
renewable energy utilization rate:P c (t) is the actual power of renewable energy source at time t, P st (t) is the rated power of renewable energy source at the moment t, and t is the moment of the multi-microgrid system;
degree of supply and demand balance in a zone:P prc (t) is the power generated by the energy supply side at time t, P u (t) is the user load at time t;
distributed power supply adjustable capacity: e (E) in,3 ＝P st (t)-P c (t)，P c (t) is the actual power of renewable energy source at time t, P st (t) is the rated power of renewable energy source at time t;
degree of electrical coupling between nodes: e (E) in,4 When there is energy interaction between the nodes, its value is 1; when there is no interaction between the nodes, its value is 0;
load and distributed power supply matching degree:P c (t) is the actual power of renewable energy source at time t, P u (t) is the user load at time t;
energy storage device adjustable capacity: e (E) in,6 ＝P ba,st (t)-P ba,c (t)，P ba,c (t) is the actual power generated by the energy storage device at the moment t, P ba,st And (t) is the rated power of the energy storage device at the moment t.
(1.2) establishing a section evaluation index system of a multi-micro-grid system partition, wherein evaluation indexes in the section evaluation index system comprise:
interval average electrical distance:L cir,i sigma L is the electrical distance between the current partition and the surrounding ith partition cir,i N is the sum of the electrical distances of the current zone and the surrounding zones cir The number of surrounding partitions;
interval power interaction capacity: e (E) ex,2 ＝∑P cir,i (t)，P cir,i (t) is the interaction power of the partition and the ith partition around the partition at time t, ΣP cir,i (t) is the sum of the interaction power of the current partition and the surrounding partitions at time t;
power scheduling cost: e (E) ex,3 The power loss generated for each interaction of 1kWh of power between the partition and the surrounding partitions;
line loss: e (E) ex,4 The sum of the power loss generated by the power interaction of the partition and the surrounding partitions is the sum of the power loss generated by the power interaction of the partition and the surrounding partitions;
whether each sub-area is connected to the backbone: e (E) ex,5 When the partition is connected with the backbone network, the value is 1; when the partition is not connected with the backbone network, the value is 0;
energy storage equipment breakage cost: e (E) ex,6 The loss of the energy storage device generated for each time of storing/releasing 1kWh of electric energy by the energy storage device;
E in,i and E is ex,i Is the main component of the corresponding in-zone and out-zone evaluation index.
(2) Setting power balance limit of the multi-micro-grid system; the power balance relation corresponding to the power balance limit in the step (2) is as follows:
P trans (t)＝P prc (t)-P u (t)
wherein P is trans (t) represents the interaction power of the micro-grid and the backbone network at the moment t, P prc (t) represents the power generated by the energy supply side at time t, P u And (t) represents the user coincidence power at the moment t.
(3) Establishing an evaluation index weight intelligent agent;
(3.1) setting the observed state quantity required by the agent: the method comprises the following steps of (1) and (2) and comprises the following steps of:
s t ∈S:{E in,i,t ,E ex,i,t }
in the state space S, E in,i,t Representing the state quantity of the index in the ith zone at the time t, E ex,i,t Representing the state quantity of the ith interval index at the time t, s t The state of the intelligent agent at the time t is shown, and t is the time at which the multi-micro-grid system is located;
(3.2) setting an action value of the agent: the actions of the agent include increasing the weight, decreasing the weight and not changing, the action space is as follows:
a t ∈A{0,1,2}
in the motion space a, 0 means decreasing weight, 1 means increasing weight, and 2 means not changing;
(3.3) setting an agent rewarding function when the agent is in state s t Action a is taken at that time t The obtained rewards are the running cost of the multi-micro network system at the time t, and the running cost is as follows:
r t ＝P trans ×R t ×Δt
wherein r is t Representing the running cost of the multi-micro-grid system at the time t, R t The method comprises the steps of expressing the interactive electricity price of a multi-micro-grid system and a backbone network at the moment t, wherein deltat represents the action time interval;
(3.4) simulating the motion of the agent using the deep neural network, inputting the state quantity in the motion space into the deep neural network, and outputting the index weight value λ (s, a) in the observed state by the deep neural network:
λ(s,a)＝E(r t +λ(s t+1 ,a t+1 )|s t ,a t )
wherein lambda (s, a) represents the state s of observation of the agent t When and as desired to take action, E () represents the desired value.
(4) Constructing an evaluation index system of the intra-zone and inter-zone dividing effect; the evaluation index systems of the zone division effect and the zone division effect in the step (4) are respectively as follows:
G in ＝∑ i λ in,i E in,i ,G ex ＝∑ i λ ex,i E ex,i
wherein G is in And G ex Respectively, is an evaluation index of the intra-zone and inter-zone dividing effect, lambda in,i And lambda (lambda) ex,i The higher index value represents a better dynamic partitioning strategy for the principal component contribution coefficient; the partition evaluation index system changes with the change of the state information of the micro-grid.
(5) Designing a multi-micro-grid partition comprehensive evaluation index; the formula of the multi-micro-grid partition comprehensive evaluation index in the step (5) is as follows:
wherein G is in,j G is the j-th in-zone evaluation index ex,j And n is the number of partitions for the j-th interval evaluation index.
(6) Designing a multi-micro-network re-partition mechanism considering system node change, wherein the step (6) specifically comprises the following steps: considering the change of the nodes of the multi-micro-grid system along with the environment and time, if a certain block of the system is partitioned, comprehensively evaluating the index M IE Less than 90% of the original, the multi-micro-network needs to be partitioned again; if the comprehensive evaluation index M of all partitions in the system IE All are greater than 90% of the original, the current partition strategy is better and notRepartitioning is required.
A computer storage medium having stored thereon a computer program which, when executed by a processor, implements a regional smart grid partition assessment method based on deep reinforcement learning as described above.
A computer device comprises a storage, a processor and a computer program which is stored in the storage and can be run on the processor again, wherein the processor realizes the regional intelligent power grid partition evaluation method based on deep reinforcement learning when executing the computer program.

Claims (7)

1. The regional intelligent power grid partition evaluation method based on deep reinforcement learning is characterized by comprising the following steps of:
(1) Establishing a multi-micro-grid system partition evaluation index system, wherein the multi-micro-grid system partition evaluation index system comprises an intra-area evaluation index system and an inter-area evaluation index system;
(1.1) establishing an intra-area evaluation index system of the multi-micro-grid system partition, wherein the evaluation indexes in the intra-area evaluation index system comprise:
renewable energy utilization rate:P c (t) is the actual power of renewable energy source at time t, P st (t) is the rated power of renewable energy source at the moment t, and t is the moment of the multi-microgrid system;
degree of supply and demand balance in a zone:P prc (t) is the power generated by the energy supply side at time t, P u (t) is the user load at time t;
distributed power supply adjustable capacity: e (E) in,3 ＝P st (t)-P c (t)，P c (t) is the actual power of renewable energy source at time t, P st (t) is the rated power of renewable energy source at time t;
degree of electrical coupling between nodes: e (E) in,4 When there is energy interaction between the nodes, its value is 1; when there is no interaction between the nodes, its value is 0;
load and distributed power supply matching degree:P c (t) is the actual power of renewable energy source at time t, P u (t) is the user load at time t;
energy storage device adjustable capacity: e (E) in,6 ＝P ba,st (t)-P ba,c (t)，P ba,c (t) is the actual power generated by the energy storage device at the moment t, P ba,st (t) is the rated power of the energy storage device at the moment t;
(1.2) establishing a section evaluation index system of a multi-micro-grid system partition, wherein evaluation indexes in the section evaluation index system comprise:
interval average electrical distance:L cir,i sigma L is the electrical distance between the current partition and the surrounding ith partition cir,i N is the sum of the electrical distances of the current zone and the surrounding zones cir The number of surrounding partitions;
interval power interaction capacity: e (E) ex,2 ＝∑P cir,i (t)，P cir,i (t) is the interaction power of the partition and the ith partition around the partition at time t, ΣP cir,i (t) is the sum of the interaction power of the current partition and the surrounding partitions at time t;
power scheduling cost: e (E) ex,3 The power loss generated for each interaction of 1kWh of power between the partition and the surrounding partitions;
line loss: e (E) ex,4 The sum of the power loss generated by the power interaction of the partition and the surrounding partitions is the sum of the power loss generated by the power interaction of the partition and the surrounding partitions;
whether each sub-area is connected to the backbone: e (E) ex,5 When the partition is connected with the backbone network, the value is 1; when the partition is not connected with the backbone network, the value is 0;
energy storage equipment is rolled overLoss cost: e (E) ex,6 The loss of the energy storage device generated for each time of storing/releasing 1kWh of electric energy by the energy storage device;
E in,i and E is ex,i Is the main component of the corresponding in-zone and out-zone evaluation index;
(2) Setting power balance limit of the multi-micro-grid system;
(3) Establishing an evaluation index weight intelligent agent;
(3.1) setting the observed state quantity required by the agent: the method comprises the following steps of (1) and (2) and comprises the following steps of:
s t ∈S:{E in,i,t ,E ex,i,t }
in the state space S, E in,i,t Representing the state quantity of the index in the ith zone at the time t, E ex,i,t Representing the state quantity of the ith interval index at the time t, s t The state of the intelligent agent at the time t is shown, and t is the time at which the multi-micro-grid system is located;
(3.2) setting an action value of the agent: the actions of the agent include increasing the weight, decreasing the weight and not changing, the action space is as follows:
a t ∈A{0,1,2}
in the motion space a, 0 means decreasing weight, 1 means increasing weight, and 2 means not changing;
(3.3) setting an agent rewarding function when the agent is in state s t Action a is taken at that time t The obtained rewards are the running cost of the multi-micro network system at the time t, and the running cost is as follows:
r t ＝P trans ×R t ×Δt
wherein r is t Representing the running cost of the multi-micro-grid system at the time t, R t The method comprises the steps of expressing the interactive electricity price of a multi-micro-grid system and a backbone network at the moment t, wherein deltat represents the action time interval;
(3.4) simulating the motion of the agent using the deep neural network, inputting the state quantity in the motion space into the deep neural network, and outputting the index weight value λ (s, a) in the observed state by the deep neural network:
λ(s,a)＝E(r t +λ(s t+1 ,a t+1 )|s t ,a t )
wherein lambda (s, a) represents the state s of observation of the agent t When and as desired to take action, E () represents a desired value;
(4) Constructing an evaluation index system of the intra-zone and inter-zone dividing effect;
(5) Designing a multi-micro-grid partition comprehensive evaluation index;
(6) A multi-microgrid repartitioning mechanism is designed.
2. The regional smart grid partition evaluation method based on deep reinforcement learning according to claim 1, wherein the power balance relation corresponding to the power balance limit in step (2) is as follows:
P trans (t)＝P prc (t)-P u (t)
wherein P is trans (t) represents the interaction power of the micro-grid and the backbone network at the moment t, P prc (t) represents the power generated by the energy supply side at time t, P u And (t) represents the user coincidence power at the moment t.
3. The regional smart grid partition evaluation method based on deep reinforcement learning according to claim 1, wherein the evaluation index systems of the intra-region and inter-region partition effects in the step (4) are respectively:
G in ＝∑ i λ in,i E in,i ,G ex ＝∑ i λ ex,i E ex,i
wherein G is in And G ex Respectively, is an evaluation index of the intra-zone and inter-zone dividing effect, lambda in,i And lambda (lambda) ex,i The higher index value represents a better dynamic partitioning strategy for the principal component contribution coefficient; the partition evaluation index system changes with the change of the state information of the micro-grid.
4. The regional smart grid partition evaluation method based on deep reinforcement learning according to claim 1, wherein the formula of the multi-micro-grid partition comprehensive evaluation index in step (5) is as follows:
wherein G is in,j G is the j-th in-zone evaluation index ex,j And n is the number of partitions for the j-th interval evaluation index.
5. The regional smart grid partition evaluation method based on deep reinforcement learning according to claim 1, wherein the step (6) is specifically: if a block of the system is partitioned to comprehensively evaluate the index M IE Less than 90% of the original, the multi-micro-network needs to be partitioned again; if the comprehensive evaluation index M of all partitions in the system IE And if the current partition strategy is greater than 90% of the original partition strategy, the current partition strategy is better, and re-partition is not needed.
6. A computer storage medium having a computer program stored thereon, which when executed by a processor implements a deep reinforcement learning based regional smart grid partition assessment method as claimed in any one of claims 1 to 5.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements a regional smart grid partition assessment method based on deep reinforcement learning as claimed in any one of claims 1 to 5 when the computer program is executed by the processor.
CN202210048549.2A 2022-01-17 2022-01-17 Regional intelligent power grid partition evaluation method based on deep reinforcement learning Active CN114362221B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210048549.2A CN114362221B (en) 2022-01-17 2022-01-17 Regional intelligent power grid partition evaluation method based on deep reinforcement learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210048549.2A CN114362221B (en) 2022-01-17 2022-01-17 Regional intelligent power grid partition evaluation method based on deep reinforcement learning

Publications (2)

Publication Number Publication Date
CN114362221A CN114362221A (en) 2022-04-15
CN114362221B true CN114362221B (en) 2023-10-13

Family

ID=81092263

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210048549.2A Active CN114362221B (en) 2022-01-17 2022-01-17 Regional intelligent power grid partition evaluation method based on deep reinforcement learning

Country Status (1)

Country Link
CN (1) CN114362221B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106655253A (en) * 2016-10-26 2017-05-10 华南理工大学 Single-/three-phase multi-micro-grid region dynamic partitioning method
CN109255514A (en) * 2018-07-19 2019-01-22 国网上海市电力公司 A kind of independently-powered capability assessment method of intelligent distribution network subregion
WO2020000399A1 (en) * 2018-06-29 2020-01-02 东莞理工学院 Multi-agent deep reinforcement learning proxy method based on intelligent grid
CN111146815A (en) * 2018-11-05 2020-05-12 西交利物浦大学 Intelligent power distribution network distributed power generation planning configuration method
CN113780622A (en) * 2021-08-04 2021-12-10 华南理工大学 Multi-micro-grid power distribution system distributed scheduling method based on multi-agent reinforcement learning
CN113852080A (en) * 2021-08-25 2021-12-28 中国电力科学研究院有限公司 Method, system, equipment and storage medium for optimizing power flow of smart power grid

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106655253A (en) * 2016-10-26 2017-05-10 华南理工大学 Single-/three-phase multi-micro-grid region dynamic partitioning method
WO2020000399A1 (en) * 2018-06-29 2020-01-02 东莞理工学院 Multi-agent deep reinforcement learning proxy method based on intelligent grid
CN109255514A (en) * 2018-07-19 2019-01-22 国网上海市电力公司 A kind of independently-powered capability assessment method of intelligent distribution network subregion
CN111146815A (en) * 2018-11-05 2020-05-12 西交利物浦大学 Intelligent power distribution network distributed power generation planning configuration method
CN113780622A (en) * 2021-08-04 2021-12-10 华南理工大学 Multi-micro-grid power distribution system distributed scheduling method based on multi-agent reinforcement learning
CN113852080A (en) * 2021-08-25 2021-12-28 中国电力科学研究院有限公司 Method, system, equipment and storage medium for optimizing power flow of smart power grid

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
Towards Intelligent Energy Control and Optimization in Energy Internet: A Review;Haochen Hua等;《2019 IEEE International Conference on Energy Internet》;573-578 *

Also Published As

Publication number Publication date
CN114362221A (en) 2022-04-15

Similar Documents

Publication Publication Date Title
Hosseini et al. Robust optimal energy management of a residential microgrid under uncertainties on demand and renewable power generation
Li et al. Data-driven charging strategy of PEVs under transformer aging risk
Xia et al. An autonomous real-time charging strategy for plug-in electric vehicles to regulate frequency of distribution system with fluctuating wind generation
Dimeas et al. Multi-agent reinforcement learning for microgrids
Agamah et al. Energy storage system scheduling for peak demand reduction using evolutionary combinatorial optimisation
Ospina et al. Sampling-based model predictive control of PV-integrated energy storage system considering power generation forecast and real-time price
US10804702B2 (en) Self-organizing demand-response system
Wang et al. An improved substation locating and sizing method based on the weighted voronoi diagram and the transportation model
CN110362845B (en) Method and device for determining regional power market development planning mode
CN106529737A (en) Planning and distribution method for peak load regulation power source on supply side of power distribution network
Amasyali et al. Hierarchical model-free transactional control of building loads to support grid services
CN116169776A (en) Cloud edge cooperative artificial intelligent regulation and control method, system, medium and equipment for electric power system
Shi et al. Preventive allocation and post-disaster cooperative dispatch of emergency mobile resources for improved distribution system resilience
Bai et al. Robust online operation of power systems with advanced adiabatic compressed air energy storage and renewable generation
Liu et al. Consensus-based energy management of multi-microgrid: An improved SoC-based power coordinated control method
CN117254464B (en) Control method and system of energy storage system
CN114336594A (en) Energy aggregation customer monitoring and demand response scheduling system and method
Hasanat et al. An ant colony optimization algorithm for load shedding minimization in smart grids
CN114362221B (en) Regional intelligent power grid partition evaluation method based on deep reinforcement learning
Shah et al. Optimization solutions for demand side management and monitoring
Kadir et al. Reinforcement learning based proactive control for transmission grid resilience to wildfire
Phommixay et al. Comparative analysis of continuous and hybrid binary-continuous particle swarm optimization for optimal economic operation of a microgrid
EP3059646A1 (en) Method and controller for controlling a power grid
Kumari et al. Dynamic distribution network expansion planning under energy storage integration using PSO with controlled particle movement
Doagou-Mojarrad et al. Probabilistic interactive fuzzy satisfying generation and transmission expansion planning using fuzzy adaptive chaotic binary PSO algorithm

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