CN117291095A - Collaborative interaction method, device, equipment and medium for virtual power plant and power distribution network - Google Patents

Collaborative interaction method, device, equipment and medium for virtual power plant and power distribution network Download PDF

Info

Publication number
CN117291095A
CN117291095A CN202311194350.1A CN202311194350A CN117291095A CN 117291095 A CN117291095 A CN 117291095A CN 202311194350 A CN202311194350 A CN 202311194350A CN 117291095 A CN117291095 A CN 117291095A
Authority
CN
China
Prior art keywords
time
representing
power plant
day
distribution network
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311194350.1A
Other languages
Chinese (zh)
Inventor
季宇
徐重酉
陈蕾
张颖
宋晓阳
彭珊
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.)
China Online Shanghai Energy Internet Research Institute Co ltd
State Grid Zhejiang Electric Power Co Ltd
Original Assignee
China Online Shanghai Energy Internet Research Institute Co ltd
State Grid Zhejiang Electric Power 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 China Online Shanghai Energy Internet Research Institute Co ltd, State Grid Zhejiang Electric Power Co Ltd filed Critical China Online Shanghai Energy Internet Research Institute Co ltd
Priority to CN202311194350.1A priority Critical patent/CN117291095A/en
Publication of CN117291095A publication Critical patent/CN117291095A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/02—CAD in a network environment, e.g. collaborative CAD or distributed simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/04—Constraint-based CAD
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/08—Probabilistic or stochastic CAD
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/18—Details relating to CAD techniques using virtual or augmented reality
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/04—Power grid distribution networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/06—Power analysis or power optimisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Marketing (AREA)
  • Evolutionary Computation (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Geometry (AREA)
  • Public Health (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Game Theory and Decision Science (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • Tourism & Hospitality (AREA)
  • Supply And Distribution Of Alternating Current (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to a method, a device, equipment and a medium for collaborative interaction between a virtual power plant and a power distribution network, wherein the method comprises the following steps: establishing a virtual power plant optimization model which meets the condition of orderly operation of the virtual power plant by taking the maximum benefit as a target; aiming at cost minimization, establishing a power distribution network optimization model meeting the condition of safe and stable operation of the power distribution network; and establishing a Markov decision model based on the virtual power plant optimization model and the power distribution network optimization model, solving the Markov decision model by adopting evolutionary element reinforcement learning, and taking a solving result as a cooperative interaction strategy of the virtual power plant and the power distribution network. The invention can comprehensively cover the resources in the virtual power plant, give consideration to the benefits of the power distribution network operators and the virtual power plant operators, and provide a calculation support for the large-scale development of the virtual power plant in the power distribution network.

Description

Collaborative interaction method, device, equipment and medium for virtual power plant and power distribution network
Technical Field
The invention relates to the technical field of interaction between a virtual power plant and a power distribution network, in particular to a method, a device, equipment and a medium for collaborative interaction between the virtual power plant and the power distribution network.
Background
Under the construction background of a novel power system, a virtual power plant is vigorous in development because the virtual power plant can aggregate large-scale distributed resources and promote the consumption of renewable energy, but the virtual power plant is rich in resource types, dispersed in geographic positions, low in access voltage level and difficult to realize considerable and controllable, and large-scale application of the virtual power plant in a power distribution network is hindered, so that the research on the development of an interaction model between the virtual power plant and the power distribution network is necessary, and the energy support of the virtual power plant on an upper-level power distribution network is realized.
Currently, a plurality of researchers focus on an interaction model between a virtual power plant and a power distribution network, cheng Xuemei and the like aiming at transaction game problems among a plurality of virtual power plants, and a cooperative game strategy among a plurality of virtual power plants taking account of operation constraints of the power distribution network is proposed on the basis of considering physical network characteristics (Cheng Xueting, wang Jinhao, golden jade and the like; a multi-virtual power plant cooperative game strategy [ J ]. Southern power grid technology taking account of operation constraints of the power distribution network, 2023,17 (04): 119-131). Li Xiangyu in order to realize the coordinated optimization scheduling of multiple virtual power plants with different benefit subjects, a distributed coordinated optimization scheduling method of the multiple virtual power plants based on Lagrangian dual relaxation is provided based on the thought of 'information separation and decision coordination' (Li Xiangyu, zhao Dongmei. Distributed coordinated optimization scheduling of the multiple virtual power plants under a distributed architecture [ J ]. Technical university report, 2023,38 (07): 1852-1863). Zhang Chongbiao and the like are used for establishing a power distribution network system structure comprising a plurality of virtual power plants and constructing a multi-virtual power plant cooperative operation model (Zhang Chongbiao, gaobao, zhang Weikang and the like) aiming at the problem that the utilization rate of new energy and stored energy is low when the virtual power plants independently operate. Wang Jinhao, etc., and simulation results show that the proposed method can reduce network loss and improve benefits of a power distribution network operator (Wang Jinhao, liu Xinyuan, zhong Ying, etc.,. The power distribution network distribution robust optimization scheduling [ J ] with the participation of the virtual power plant provides power, 2022,39 (11): 71-78+86). Liu Haowen and the like, aiming at the problem of voltage out-of-limit generated by a large number of distributed power supplies connected into a power distribution network, a virtual power plant auxiliary service transaction mechanism (Liu Haowen, liu Dong, chen Zhangyu and the like) for taking voltage regulation cost and reactive power reserve into consideration is provided.
However, the above-mentioned studies have the following problems: 1) The related internal resource types of the virtual power plant are not comprehensive enough, and partial researches only establish a model of a single side of the source load storage or do not mention specific resource types; 2) The benefits of the power distribution network operators and the virtual power plant operators cannot be considered at the same time, and only one main body is used for modeling analysis; 3) The calculation speed, calculation scale and solution efficiency of the solution algorithm are limited, and the calculation requirement of interaction between the large-scale virtual power plant and the power distribution network is difficult to meet.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a collaborative interaction method, device, equipment and medium for a virtual power plant and a power distribution network, which can comprehensively cover resources in the virtual power plant, give consideration to benefits of power distribution network operators and virtual power plant operators, and provide calculation support for large-scale development of the virtual power plant in the power distribution network.
The technical scheme adopted for solving the technical problems is as follows: the utility model provides a virtual power plant and distribution network collaborative interaction method, which comprises the following steps:
establishing a virtual power plant optimization model which meets the condition of orderly operation of the virtual power plant by taking the maximum benefit as a target;
aiming at cost minimization, establishing a power distribution network optimization model meeting the condition of safe and stable operation of the power distribution network;
And establishing a Markov decision model based on the virtual power plant optimization model and the power distribution network optimization model, solving the Markov decision model by adopting evolutionary element reinforcement learning, and taking a solving result as a cooperative interaction strategy of the virtual power plant and the power distribution network.
The objective function of the virtual power plant optimization model is as follows:
wherein f VPP For an objective function of the virtual power plant optimization model, T represents the total length of time of optimization, I represents the total number of independently adjustable resources in the virtual power plant,representing the return achieved in the energy market by the independently adjustable resources in the virtual power plant before the day at time t,/->Representing the declared power in the energy market before the day at time t for the ith independently adjustable resource, +.>Representing the declared price of the ith independently adjustable resource in the energy market before the day at time t,/day>Representing the clearing power of the virtual power plant at time t-1 in the day-ahead energy market,/->Representing the price of the energy market before day at time t-1, < >>Representing the running cost of the independent adjustable resources at the moment t to participate in the day-ahead energy market; n represents the total number of independent rigid resources in the virtual power plant,representing the total revenue of rigid resources in the energy market before the day at time t,/for>Represents bidding capacity of nth rigid resource in energy market before day of t time,/day >Represents the bidding price of the nth rigid resource in the energy market before the day of time t,/->Representing the total capacity deviation of the energy market before day at time t of participation of the virtual power plant, < >>Representing the running cost of the nth rigid resource participating in the energy market before the day at time t, +.>Represents penalty cost,/->Representing the output deviation of the nth rigid resource; j represents the number of intelligent parks in the virtual power plant, < >>Indicating the electricity purchasing state of the park at the time t, < +.>Representing the total gain of the energy market of the campus before the day at time t,/o>Indicating the bidding capacity of the j-th park to participate in the day-ahead energy market at time t,/>Represents the bid price in the energy market before day at time t for the jth campus,/->Representing the running cost of the j-th park to participate in the energy market before the day at time t, +.>Output representing controllable resource at time t in jth park +.>Indicating the deviation of the output of renewable energy sources in the j-th park, +.>Represents the electricity purchasing cost of the park at the time t, < + >>Indicating the adjustable load capacity in the jth park at time t, +.>The electricity purchasing bias cost at the time t is represented,the amount of load deviation in the jth park at time t is shown.
The constraint conditions of the virtual power plant optimization model comprise:
independently adjustable resource bidding capacity upper and lower limit constraints: Wherein P is IAR,i,min Representing the lower limit of bidding capacity of the ith independently adjustable resource at time t,/for>Representing the declared power in the energy market before the day at time t for the ith independently adjustable resource, +.>Representing the upper limit of bidding capacity of the ith independently adjustable resource at the time t;
independently adjustable resource bidding price upper and lower limit constraints:wherein: />Indicating the lower limit of bidding price of the ith independently adjustable resource at time t,/->Representing the declared price of the ith independently adjustable resource in the energy market before the day at time t,/day>The upper limit of bidding electricity price of the ith independently adjustable resource at the time t is represented;
independently adjustable resource climbing upper and lower limit constraints:wherein P is ramp,i,min Represents the lower limit of climbing of the ith independently adjustable resource, P ramp,i,max Representing an upper bound of the climbing of the ith independently adjustable resource;
upper and lower limit constraints of bidding capacity of independent non-adjustable resources:wherein (1)>Represents the lower limit of bidding capacity of the nth rigid resource at the time t,/day>Represents bidding capacity of nth rigid resource in energy market before day of t time,/day>The upper limit of bidding capacity of the nth rigid resource at the time t is represented;
upper and lower limit constraints of bidding price of independent non-adjustable resources:wherein (1)>Indicating the lower limit of bidding price of the nth rigid resource at the time t,/day >Represents the bidding price of the nth rigid resource in the energy market before the day of time t,/->The upper limit of bidding electricity price of the nth rigid resource at the time t is represented;
independent non-adjustable resource climbing upper and lower limit constraint:wherein P is ramp,n,min Represents the lower limit of climbing of the nth rigid resource, P ramp,n,max Representing the upper bound of the climbing of the nth rigid resource;
upper and lower limit constraint of bid amount in park:wherein (1)>Indicating the lower limit of bidding capacity of the jth campus at time t +.>Indicating the bid amount of the jth campus participating in the day-ahead energy market at time t,the upper limit of bidding capacity of the jth park at the moment t is represented;
upper and lower limit constraint of competitive bidding price in park:wherein (1)>Indicating the lower limit of bidding price of the jth campus at time t,/for>Representing the bid price in the energy market of the jth campus before the day at time t,the upper limit of bidding electricity price of the jth park at the moment t is represented;
park climbing upper and lower limit constraint:wherein P is ramp,j,min Represents the lower limit of climbing in the jth park, P ramp,j,max Representing the upper limit of climbing in the jth campus;
park power balance constraint:wherein (1)>Indicating the internal force at time t of the j-th campus,/->Indicating the electricity purchasing state of the park at the time t, < +.>Indicating the adjustable load capacity in the jth park at time t, +. >Load-adjustable force representing time t of jth park,/->Indicating the load reduction amount at time t of the jth park,/->Indicating the total load at time t of the j-th park;
park cut load limit constraints:wherein (1)>The maximum value at which the load can be reduced at the j-th park t is shown.
The objective function of the power distribution network optimization model is as follows:
wherein f DSO Representing an objective function of an optimization model of the power distribution network, T representing an optimization total duration, G representing the number of virtual power plants interacting with the power distribution network,representing the operating costs of the distribution network at time t +.>Indicating the clear power of the power distribution network to the g-th virtual power plant at time t, < >>Indicating the price of the energy market before day at time t +.>Represents the bidding capacity of the g-th virtual power plant at time t,/->Represents the competitive price of the g-th virtual power plant at time t,/->Representing electricity purchasing cost of power distribution network at time t +.>Represents the purchase price at time t, +.>Represents the price of the electricity abandon penalty at time t, +.>Indicating the adjustable load capacity in the jth park at time t, +.>Indicating the load reduction amount of the jth park at time t, ρ DSO Shows the force deviation normalization coefficient, +.>The deviation of the output force at time t is shown.
The constraint conditions of the power distribution network optimization model comprise:
System power balance constraint:wherein G represents the number of virtual power plants interacting with the power distribution network, < >>The clear power of the power distribution network to the g virtual power plant at the moment t is represented; />The total adjustable load at the time t is represented;
and (5) clearing capacity constraint:wherein (1)>The bidding capacity of the g-th virtual power plant at the moment t is represented;
line transmission power constraints:wherein (1)>Representing the power on the o-th line at time t, P line,o,min Representing the lower limit of reverse transmission power, P, on the o-th line line,o,max Representing the upper limit of forward transmission power of the o-th line;
the system cuts the load limiting constraint:wherein (1)>Represents the system cut load quantity at time t, < + >>The maximum value of the system cut load quantity at the moment t is shown;
constraint of a tide equation:wherein (1)>Representing the active power of the branch between node i and node j at time t, k (j, k) representing the set of branches with node j as the head node, +.>Representing the active power of a branch between a node j and a node k at the moment t, r ij Represents the resistance of the branch between node i and node j, < >>Represents the current of the branch between node i and node j at time t,/, and>represents the load active power of node j at time t, < >>Represents active power consumed by node j energy storage at time t, < >>Representing the active power injected by a node j at the moment t; / >Representing the reactive power of the branch between node i and node j at time t,/>Representing the reactive power, x, of the branch between node j and node k at time t ij Representing the reactance between node i and node j, < +.>Represents the load reactive power of node j at time t, < >>Reactive power, < >/representing energy storage consumption of node j at time t>The reactive power injected by the node j at the moment t is represented; />Representing the voltage amplitude of node j at time t, V i t Representing the voltage amplitude of a node i at the time t;
node voltage constraint: v (V) i,min ≤V i t ≤V i,max The method comprises the steps of carrying out a first treatment on the surface of the Wherein V is i,min Representing the lower voltage limit of node i, V i,max Representing the upper voltage limit of node i;
line current constraint:wherein I is ij,max Representing the maximum current that the branch can withstand between node i and node j.
When the Markov decision model is established based on the virtual power plant optimization model and the power distribution network optimization model, for the virtual power plant, the action space of the Markov decision modelExpressed as:status space->Expressed as: />Revenue collection R VPP Expressed as: r is R VPP ＝{-f VPP -a }; transition probability set P VPP Expressed as: />Policy set->Expressed as: />Long-term discount rewards set->Expressed as: />For a distribution network, the action space of a Markov decision model +.>Expressed as: />Status space->Expressed as: Revenue collection R DSO Expressed as: r is R DSO ＝{f DSO -a }; transition probability set P DSO Expressed as: />Policy set->Expressed as: />Long-term discount rewards set->Expressed as: />Wherein f VPP For the objective function of the virtual power plant optimization model, +.>Representing the declared power in the energy market before the day at time t for the ith independently adjustable resource, +.>Representing the declared price of the ith independently adjustable resource in the energy market before the day at time t,/day>Represents bidding capacity of nth rigid resource in energy market before day of t time,/day>Represents the bidding price of the nth rigid resource in the energy market before the day of time t,/->Indicating the bidding capacity of the j-th park to participate in the day-ahead energy market at time t,/>Represents the bid price in the energy market before day at time t for the jth campus,/->Representing the egress of the nth rigid resourceForce deviation->Output representing controllable resource at time t in jth park +.>Indicating the deviation of the output of renewable energy sources in the j-th park, +.>Representing the clearing power of the virtual power plant at time t-1 in the day-ahead energy market,/->Representing the total capacity deviation of the energy market before the day at the moment of participation t of the virtual power plant, f DSO Objective function representing an optimization model of a power distribution network, +.>Indicating the clear power of the power distribution network to the g-th virtual power plant at time t, < > >Indicating the price of the energy market before day at time t +.>Represents the purchase price at time t, +.>Represents the price of the electricity abandon penalty at time t, +.>Represents the bidding capacity of the g-th virtual power plant at time t,/->Represents the competitive price of the g-th virtual power plant at time t,/->Indicating the adjustable load capacity in the jth campus at time t,indicating the load reduction amount of the jth park at time t,/, and>the output deviation at the time t is represented; gamma ray t Representing the discount factor at time t, E { } represents the mathematical expectation universal sign.
When the evolutionary element reinforcement learning solves the Markov decision model, pi is adopted * ＝argmaxE MDP,π (D) Solving the strategy by adoptingSolving the inner layer super parameter by adoptingCarrying out outer layer super-parameter solving; wherein pi * Represent the optimal strategy, E MDP,π () Representing the expectations in executing a policy pi in a Markov decision model, D representing a set of long-term discount rewards in the Markov decision model, θ * Represents the inner layer super parameter under the optimal strategy, < ->Representing the expectation of a Markov model under a strategy pi when an internal parameter is theta, L β () Representing the loss function, MDP represents the Markov decision model, β * Represents the outer layer super-parameters under the optimal strategy,representing expected values of a Markov decision model under an optimal strategy; the update formula of the inner layer super parameter is as follows: The outer layer is super-parametricThe update formula is: />Wherein θ i Represents the inner layer hyper-parameters after the ith iteration, sigma represents the standard deviation, ++>Represent gradient, L i () Represents the loss function after the ith iteration, beta i Represents the parameters of the outer layer after the ith iteration, alpha represents the learning rate of the outer layer, m represents the number of samples and epsilon i Representing a normal vector of standard polynomials, D i Representing the benefit after the ith iteration.
The technical scheme adopted for solving the technical problems is as follows: the utility model provides a virtual power plant and distribution network interaction device in coordination, include:
the first building module is used for building a virtual power plant optimization model which meets the condition that the virtual power plant operates orderly with the aim of benefit maximization;
the second building module is used for building a power distribution network optimization model which meets the condition of safe and stable operation of the power distribution network with the aim of minimizing cost;
and the model solving film is used for establishing a Markov decision model based on the virtual power plant optimizing model and the power distribution network optimizing model, solving the Markov decision model by adopting evolutionary element reinforcement learning, and taking the solving result as a cooperative interaction strategy of the virtual power plant and the power distribution network.
The technical scheme adopted for solving the technical problems is as follows: an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the virtual power plant and power distribution network collaborative interaction method when executing the computer program.
The technical scheme adopted for solving the technical problems is as follows: there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the virtual power plant and distribution grid collaborative interaction method described above.
Advantageous effects
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects: according to the method, the optimization models of the virtual power plant and the power distribution network are respectively established, bidding price and capacity of the virtual power plant under the condition that the virtual power plant meets the ordered operation of the virtual power plant, and the power distribution network is cleared with the operation cost minimized under the condition that the safe and stable operation condition is met, so that benign interaction between the virtual power plant and the power distribution network is realized. The solving method provided by the invention can parameterize the history experience to realize quick solving, and meanwhile, only optimize the loss function in the strategy learning process without explicit reward signals, thereby greatly simplifying the computational complexity.
Drawings
FIG. 1 is a flow chart of a method for collaborative interaction of a virtual power plant and a power distribution network in accordance with a first embodiment of the present invention.
Detailed Description
The invention will be further illustrated with reference to specific examples. It is to be understood that these examples are illustrative of the present invention and are not intended to limit the scope of the present invention. Further, it is understood that various changes and modifications may be made by those skilled in the art after reading the teachings of the present invention, and such equivalents are intended to fall within the scope of the claims appended hereto.
The first embodiment of the invention relates to a cooperative interaction method of a virtual power plant and a power distribution network, as shown in fig. 1, comprising the following steps:
and step 1, establishing a virtual power plant optimization model meeting the condition of orderly operation of the virtual power plant with the aim of maximization of the benefit.
The objective function of the established virtual power plant optimization model in the step is as follows:
wherein f VPP T represents the total optimization time for the objective function of the virtual power plant optimization modelAnd long, I represents the total number of independently adjustable resources in the virtual power plant,representing the return achieved in the energy market by the independently adjustable resources in the virtual power plant before the day at time t,/->Representing the declared power in the energy market before the day at time t for the ith independently adjustable resource, +.>Representing the declared price of the ith independently adjustable resource in the energy market before the day at time t,/day>Representing the clearing power of the virtual power plant at time t-1 in the day-ahead energy market,/->Representing the price of the energy market before day at time t-1, < >>Representing the running cost of the independent adjustable resources at the moment t to participate in the day-ahead energy market; n represents the total number of independent rigid resources in the virtual power plant,representing the total revenue of rigid resources in the energy market before the day at time t,/for >Represents bidding capacity of nth rigid resource in energy market before day of t time,/day>Represents the bidding price of the nth rigid resource in the energy market before the day of time t,/->Representing the total capacity deviation of the energy market before day at time t of participation of the virtual power plant, < >>Representing the running cost of the nth rigid resource participating in the energy market before the day at time t, +.>Represents penalty cost,/->Representing the output deviation of the nth rigid resource; j represents the number of intelligent parks in the virtual power plant, < >>Indicating the electricity purchasing state of the park at the time t, < +.>Representing the total gain of the energy market of the campus before the day at time t,/o>Indicating the bidding capacity of the j-th park to participate in the day-ahead energy market at time t,/>Represents the bid price in the energy market before day at time t for the jth campus,/->Representing the running cost of the j-th park to participate in the energy market before the day at time t, +.>Output representing controllable resource at time t in jth park +.>Indicating the deviation of the output of renewable energy sources in the j-th park, +.>The electricity purchase cost of the campus at the time t is represented,indicating the adjustable load capacity in the jth park at time t, +.>The electricity purchasing bias cost at the time t is represented,the amount of load deviation in the jth park at time t is shown.
The constraint conditions of the virtual power plant optimization model comprise:
independently adjustable resource bidding capacity upper and lower limit constraints:wherein P is IAR,i,min Representing the lower limit of bidding capacity of the ith independently adjustable resource at time t,/for>Representing the declared power in the energy market before the day at time t for the ith independently adjustable resource, +.>Representing the upper limit of bidding capacity of the ith independently adjustable resource at the time t;
independently adjustable resource bidding price upper and lower limit constraints:wherein: />Indicating that the ith independently adjustable resource is at tLower limit of bidding price, +.>Representing the declared price of the ith independently adjustable resource in the energy market before the day at time t,/day>The upper limit of bidding electricity price of the ith independently adjustable resource at the time t is represented;
independently adjustable resource climbing upper and lower limit constraints:wherein P is ramp,i,min Represents the lower limit of climbing of the ith independently adjustable resource, P ramp,i,max Representing an upper bound of the climbing of the ith independently adjustable resource;
upper and lower limit constraints of bidding capacity of independent non-adjustable resources:wherein (1)>Represents the lower limit of bidding capacity of the nth rigid resource at the time t,/day>Represents bidding capacity of nth rigid resource in energy market before day of t time,/day>The upper limit of bidding capacity of the nth rigid resource at the time t is represented;
Upper and lower limit constraints of bidding price of independent non-adjustable resources:wherein (1)>Representing the nth rigid resourceLower limit of bidding price at time t, < ->Represents the bidding price of the nth rigid resource in the energy market before the day of time t,/->The upper limit of bidding electricity price of the nth rigid resource at the time t is represented;
independent non-adjustable resource climbing upper and lower limit constraint:wherein P is ramp,n,min Represents the lower limit of climbing of the nth rigid resource, P ramp,n,max Representing the upper bound of the climbing of the nth rigid resource;
upper and lower limit constraint of bid amount in park:wherein (1)>Indicating the lower limit of bidding capacity of the jth campus at time t +.>Indicating the bid amount of the jth campus participating in the day-ahead energy market at time t,the upper limit of bidding capacity of the jth park at the moment t is represented;
upper and lower limit constraint of competitive bidding price in park:wherein (1)>Indicating the lower limit of bidding price of the jth campus at time t,/for>Representing the bid price in the energy market of the jth campus before the day at time t,the upper limit of bidding electricity price of the jth park at the moment t is represented;
park climbing upper and lower limit constraint:wherein P is ramp,j,min Represents the lower limit of climbing in the jth park, P ramp,j,max Representing the upper limit of climbing in the jth campus;
park power balance constraint:wherein (1)>Indicating the internal force at time t of the j-th campus,/- >Indicating the electricity purchasing state of the park at the time t, < +.>Indicating the adjustable load capacity in the jth park at time t, +.>Load-adjustable force representing time t of jth park,/->Indicating the load reduction amount at time t of the jth park,/->Indicating the total load at time t of the j-th park;
park cut load limit constraints:wherein (1)>The maximum value at which the load can be reduced at the j-th park t is shown.
And 2, establishing a power distribution network optimization model meeting the condition of safe and stable operation of the power distribution network with the aim of minimizing cost.
The objective function of the power distribution network optimization model established in the step is as follows:
wherein f DSO Representing an objective function of an optimization model of the power distribution network, T representing an optimization total duration, G representing the number of virtual power plants interacting with the power distribution network,representing the operating costs of the distribution network at time t +.>Indicating the clear power of the power distribution network to the g-th virtual power plant at time t, < >>Indicating the price of the energy market before day at time t +.>Represents the bidding capacity of the g-th virtual power plant at time t,/->Represents the competitive price of the g-th virtual power plant at time t,/->Representing the time t of the distribution networkCost of purchasing electricity->Represents the purchase price at time t, +.>Represents the price of the electricity abandon penalty at time t, +. >Indicating the adjustable load capacity in the jth park at time t, +.>Indicating the load reduction amount of the jth park at time t, ρ DSO Shows the force deviation normalization coefficient, +.>The deviation of the output force at time t is shown.
The constraint conditions of the power distribution network optimization model comprise:
system power balance constraint:wherein G represents the number of virtual power plants interacting with the power distribution network, < >>The clear power of the power distribution network to the g virtual power plant at the moment t is represented; />The total adjustable load at the time t is represented;
and (5) clearing capacity constraint:wherein (1)>Bidding capacity of g virtual power plant at t momentAn amount of;
line transmission power constraints:wherein (1)>Representing the power on the o-th line at time t, P line,o,min Representing the lower limit of reverse transmission power, P, on the o-th line line,o,max Representing the upper limit of forward transmission power of the o-th line;
the system cuts the load limiting constraint:wherein (1)>Represents the system cut load quantity at time t, < + >>The maximum value of the system cut load quantity at the moment t is shown;
constraint of a tide equation:wherein (1)>Representing the active power of the branch between node i and node j at time t, k (j, k) representing the set of branches with node j as the head node, +.>Representing the active power of a branch between a node j and a node k at the moment t, r ij Represents the resistance of the branch between node i and node j, < >>Represents the current of the branch between node i and node j at time t,/, and>represents the load active power of node j at time t, < >>Represents active power consumed by node j energy storage at time t, < >>Representing the active power injected by a node j at the moment t; />Representing the reactive power of the branch between node i and node j at time t,/>Representing the reactive power, x, of the branch between node j and node k at time t ij Representing the reactance between node i and node j, < +.>Represents the load reactive power of node j at time t, < >>Reactive power, < >/representing energy storage consumption of node j at time t>The reactive power injected by the node j at the moment t is represented; />Representing the voltage amplitude of node j at time t, V i t Representing the voltage amplitude of a node i at the time t;
node voltage constraint: v (V) i,min ≤V i t ≤V i,max The method comprises the steps of carrying out a first treatment on the surface of the Wherein V is i,min Representing the lower voltage limit of node i, V i,max Representing the upper voltage limit of node i;
line current constraint:wherein I is ij,max Representing the maximum current that the branch can withstand between node i and node j.
And 3, establishing a Markov decision model based on the virtual power plant optimization model and the power distribution network optimization model, solving the Markov decision model by adopting evolutionary element reinforcement learning, and taking a solving result as a cooperative interaction strategy of the virtual power plant and the power distribution network.
The Markov decision model is expressed as: mdp= { a, S, R, P, pi, D }, where: a represents an action space, S represents a state space, R represents a benefit set, P represents a transition probability set, pi represents a policy set, and D represents a long-term discount return set.
For virtual power plants, the action space of the Markov decision modelExpressed as:status space->Expressed as: />Revenue collection R VPP Expressed as: r is R VPP ＝{-f VPP -a }; transition probability set P VPP Expressed as: />Policy set->Expressed as: />Long-term discount rewards set->Expressed as: />
For a power distribution network, the action space of a Markov decision modelExpressed as:status space->Expressed as: />Revenue collection R DSO Expressed as: r is R DSO ＝{f DSO -a }; transition probability set P DSO Expressed as: />Policy set->Expressed as: />Long-term discount rewards set->Expressed as: />
Wherein, gamma t Representing the discount factor at time t, E { } represents the mathematical expectation universal sign.
When the evolutionary element reinforcement learning solves the Markov decision model, the flow is as follows:
(1) And (3) strategy solving: pi * ＝argmaxE MDP,π (D) Wherein pi * Represent the optimal strategy, E MDP,π () Representing the expectations in executing the policy pi in the markov decision model.
(2) Solving inner layer super parameters:wherein θ * Represents the inner layer super parameter under the optimal strategy, < ->Representing the expectation of a Markov model under a strategy pi when an internal parameter is theta, L β () Representing a loss function.
(3) An inner layer super parameter updating formula:wherein θ i Represents the inner layer hyper-parameters after the ith iteration, sigma represents the standard deviation, ++>Represent gradient, L i () Representing the loss function after the i-th iteration.
(4) And (3) outer layer parameter solving:wherein beta is * Represents the outer layer hyper-parameters under the optimal strategy, +.>Representing the expected value of the Markov decision model under the optimal strategy.
(5) And updating an outer layer parameter updating formula:wherein beta is i Represents the parameters of the outer layer after the ith iteration, alpha represents the learning rate of the outer layer, m represents the number of samples and epsilon i Representing a normal vector of standard polynomials, D i Representing after the ith iterationIncome.
The virtual power plant optimization model established in the embodiment comprises independent adjustable resources, independent rigid resources, parks and the like, the resources in the virtual power plant are comprehensively covered, the established virtual power plant optimization model and the established power distribution network optimization model realize benefit balance through interaction between two main bodies, and benefits of a power distribution network operator and a virtual power plant operator are considered. According to the method, the Markov decision model is rapidly solved through evolutionary element reinforcement learning, so that the calculation efficiency is improved, and calculation support is provided for large-scale development of virtual power plants in the power distribution network.
The second embodiment of the invention relates to a cooperative interaction device for a virtual power plant and a power distribution network, comprising:
the first building module is used for building a virtual power plant optimization model which meets the condition that the virtual power plant operates orderly with the aim of benefit maximization;
the second building module is used for building a power distribution network optimization model which meets the condition of safe and stable operation of the power distribution network with the aim of minimizing cost;
and the model solving film is used for establishing a Markov decision model based on the virtual power plant optimizing model and the power distribution network optimizing model, solving the Markov decision model by adopting evolutionary element reinforcement learning, and taking the solving result as a cooperative interaction strategy of the virtual power plant and the power distribution network.
The objective function of the virtual power plant optimization model is as follows:
wherein f VPP For an objective function of the virtual power plant optimization model, T represents the total length of time of optimization, I represents the total number of independently adjustable resources in the virtual power plant,representing the return achieved in the energy market by the independently adjustable resources in the virtual power plant before the day at time t,/->Representing the declared power in the energy market before the day at time t for the ith independently adjustable resource, +.>Representing the declared price of the ith independently adjustable resource in the energy market before the day at time t,/day >Representing the clearing power of the virtual power plant at time t-1 in the day-ahead energy market,/->Representing the price of the energy market before day at time t-1, < >>Representing the running cost of the independent adjustable resources at the moment t to participate in the day-ahead energy market; n represents the total number of independent rigid resources in the virtual power plant,representing the total revenue of rigid resources in the energy market before the day at time t,/for>Represents bidding capacity of nth rigid resource in energy market before day of t time,/day>Represents the bidding price of the nth rigid resource in the energy market before the day of time t,/->Representing the total capacity deviation of the energy market before day at time t of participation of the virtual power plant, < >>Representing the nth rigid resourceRunning cost of participating in the day-ahead energy market at time t,/->Represents penalty cost,/->Representing the output deviation of the nth rigid resource; j represents the number of intelligent parks in the virtual power plant, < >>Indicating the electricity purchasing state of the park at the time t, < +.>Representing the total gain of the energy market of the campus before the day at time t,/o>Indicating the bidding capacity of the j-th park to participate in the day-ahead energy market at time t,/>Represents the bid price in the energy market before day at time t for the jth campus,/->Representing the running cost of the j-th park to participate in the energy market before the day at time t, +. >Output representing controllable resource at time t in jth park +.>Indicating the deviation of the output of renewable energy sources in the j-th park, +.>The electricity purchase cost of the campus at the time t is represented,indicating the adjustable load capacity in the jth park at time t, +.>Represents the electricity purchasing deviation cost at the time t, < + >>The amount of load deviation in the jth park at time t is shown.
The constraint conditions of the virtual power plant optimization model comprise:
independently adjustable resource bidding capacity upper and lower limit constraints:wherein P is IAR,i,min Representing the lower limit of bidding capacity of the ith independently adjustable resource at time t,/for>Representing the declared power in the energy market before the day at time t for the ith independently adjustable resource, +.>Representing the upper limit of bidding capacity of the ith independently adjustable resource at the time t;
independently adjustable resource bidding price upper and lower limit constraints:wherein: />Indicating the lower limit of bidding price of the ith independently adjustable resource at time t,/->Representing the declared price of the ith independently adjustable resource in the energy market before the day at time t,/day>The upper limit of bidding electricity price of the ith independently adjustable resource at the time t is represented; />
Independently adjustable resource climbing upper and lower limit constraints:wherein P is ramp,i,min Represents the lower limit of climbing of the ith independently adjustable resource, P ramp,i,max Representing an upper bound of the climbing of the ith independently adjustable resource;
upper and lower limit constraints of bidding capacity of independent non-adjustable resources:wherein (1)>Represents the lower limit of bidding capacity of the nth rigid resource at the time t,/day>Represents bidding capacity of nth rigid resource in energy market before day of t time,/day>The upper limit of bidding capacity of the nth rigid resource at the time t is represented;
upper and lower limit constraints of bidding price of independent non-adjustable resources:wherein (1)>Indicating the lower limit of bidding price of the nth rigid resource at the time t,/day>Represents the bidding price of the nth rigid resource in the energy market before the day of time t,/->The upper limit of bidding electricity price of the nth rigid resource at the time t is represented;
independent non-adjustable resource climbing upper and lower limit constraint:wherein P is ramp,n,min Represents the lower limit of climbing of the nth rigid resource, P ramp,n,max Representing the upper bound of the climbing of the nth rigid resource;
upper and lower limit constraint of bid amount in park:wherein (1)>Indicating the lower limit of bidding capacity of the jth campus at time t +.>Indicating the bid amount of the jth campus participating in the day-ahead energy market at time t,the upper limit of bidding capacity of the jth park at the moment t is represented;
upper and lower limit constraint of competitive bidding price in park:wherein (1)>Indicating the lower limit of bidding price of the jth campus at time t,/for >Representing the bid price in the energy market of the jth campus before the day at time t,indicating that the jth campus is at tAn upper limit of bidding electricity price;
park climbing upper and lower limit constraint:wherein P is ramp,j,min Represents the lower limit of climbing in the jth park, P ramp,j,max Representing the upper limit of climbing in the jth campus;
park power balance constraint:wherein (1)>Indicating the internal force at time t of the j-th campus,/->Indicating the electricity purchasing state of the park at the time t, < +.>Indicating the adjustable load capacity in the jth park at time t, +.>Load-adjustable force representing time t of jth park,/->Indicating the load reduction amount at time t of the jth park,/->Indicating the total load at time t of the j-th park;
park cut load limit constraints:wherein (1)>Indicating that load can be cut at time t of jth parkIs a maximum value of (a).
The objective function of the power distribution network optimization model is as follows:
wherein f DSO Representing an objective function of an optimization model of the power distribution network, T representing an optimization total duration, G representing the number of virtual power plants interacting with the power distribution network,representing the operating costs of the distribution network at time t +.>Indicating the clear power of the power distribution network to the g-th virtual power plant at time t, < >>Indicating the price of the energy market before day at time t +.>Represents the bidding capacity of the g-th virtual power plant at time t,/- >Represents the competitive price of the g-th virtual power plant at time t,/->Representing electricity purchasing cost of power distribution network at time t +.>Represents the purchase price at time t, +.>Represents the price of the electricity abandon penalty at time t, +.>Indicating the adjustable load capacity in the jth park at time t, +.>Indicating the load reduction amount of the jth park at time t, ρ DSO Shows the force deviation normalization coefficient, +.>The deviation of the output force at time t is shown.
The constraint conditions of the power distribution network optimization model comprise:
system power balance constraint:wherein G represents the number of virtual power plants interacting with the power distribution network, < >>The clear power of the power distribution network to the g virtual power plant at the moment t is represented; />The total adjustable load at the time t is represented;
and (5) clearing capacity constraint:wherein (1)>The bidding capacity of the g-th virtual power plant at the moment t is represented;
line transmission power constraints:wherein (1)>Representing the power on the o-th line at time t, P line,o,min Representing the lower limit of reverse transmission power, P, on the o-th line line,o,max Representing the upper limit of forward transmission power of the o-th line;
the system cuts the load limiting constraint:wherein (1)>Represents the system cut load quantity at time t, < + >>The maximum value of the system cut load quantity at the moment t is shown;
constraint of a tide equation:wherein (1)>Representing the active power of the branch between node i and node j at time t, k (j, k) representing the set of branches with node j as the head node, +. >Representing the active power of a branch between a node j and a node k at the moment t, r ij Represents the resistance of the branch between node i and node j, < >>Represents the current of the branch between node i and node j at time t,/, and>represents the load active power of node j at time t, < >>Represents active power consumed by node j energy storage at time t, < >>Node representing time tj active power injected; />Representing the reactive power of the branch between node i and node j at time t,/>Representing the reactive power, x, of the branch between node j and node k at time t ij Representing the reactance between node i and node j, < +.>Represents the load reactive power of node j at time t, < >>Reactive power, < >/representing energy storage consumption of node j at time t>The reactive power injected by the node j at the moment t is represented; />Representing the voltage amplitude of node j at time t, V i t Representing the voltage amplitude of a node i at the time t;
node voltage constraint: v (V) i,min ≤V i t ≤V i,max The method comprises the steps of carrying out a first treatment on the surface of the Wherein V is i,min Representing the lower voltage limit of node i, V i,max Representing the upper voltage limit of node i;
line current constraint:wherein I is ij,max Representing the maximum current that the branch can withstand between node i and node j.
When the Markov decision model is established based on the virtual power plant optimization model and the power distribution network optimization model, for the virtual power plant, the action space of the Markov decision model Expressed as:status space->Expressed as: />Revenue collection R VPP Expressed as: r is R VPP ＝{-f VPP -a }; transition probability set P VPP Expressed as: />Policy set->Expressed as: />Long-term discount rewards set->Expressed as: />For a distribution network, the action space of a Markov decision model +.>Expressed as: />Status space->Expressed as:revenue collection R DSO Expressed as:R DSO ＝{f DSO -a }; transition probability set P DSO Expressed as: />Policy set->Expressed as: />Long-term discount rewards set->Expressed as: />Wherein f VPP For the objective function of the virtual power plant optimization model, +.>Representing the declared power in the energy market before the day at time t for the ith independently adjustable resource, +.>Representing the declared price of the ith independently adjustable resource in the energy market before the day at time t,/day>Represents bidding capacity of nth rigid resource in energy market before day of t time,/day>Represents the bidding price of the nth rigid resource in the energy market before the day of time t,/->Indicating the bidding capacity of the j-th park to participate in the day-ahead energy market at time t,/>Represents the bid price in the energy market before day at time t for the jth campus,/->Indicating the deviation of the force of the nth rigid resource, < >>Output representing controllable resource at time t in jth park +. >Indicating the deviation of the output of renewable energy sources in the j-th park, +.>Representing the clearing power of the virtual power plant at time t-1 in the day-ahead energy market,/->Representing the total capacity deviation of the energy market before the day at the moment of participation t of the virtual power plant, f DSO Objective function representing an optimization model of a power distribution network, +.>Indicating the clear power of the power distribution network to the g-th virtual power plant at time t, < >>Indicating the price of the energy market before day at time t +.>Represents the purchase price at time t, +.>Represents the price of the electricity abandon penalty at time t, +.>Represents time g of time tCompetitive bidding capacity of virtual power plant,/-)>Represents the competitive price of the g-th virtual power plant at time t,/->Indicating the adjustable load capacity in the jth campus at time t,indicating the load reduction amount of the jth park at time t,/, and>the output deviation at the time t is represented; gamma ray t Representing the discount factor at time t, E { } represents the mathematical expectation universal sign.
When the evolutionary element reinforcement learning solves the Markov decision model, pi is adopted * ＝argmaxE MDP,π (D) Solving the strategy by adoptingSolving inner layer super parameters by adopting +.>Carrying out outer layer super-parameter solving; wherein pi * Represent the optimal strategy, E MDP,π () Representing the expectations in executing a policy pi in a Markov decision model, D representing a set of long-term discount rewards in the Markov decision model, θ * Represents the inner layer super parameter under the optimal strategy, < ->Representing the expectation of a Markov model under a strategy pi when an internal parameter is theta, L β () Representing the loss function, MDP represents the Markov decision model, β * Represents the outer layer super-parameters under the optimal strategy,representing expected values of a Markov decision model under an optimal strategy; the update formula of the inner layer super parameter is as follows:the updating formula of the outer layer super parameter is as follows: />Wherein θ i Represents the inner layer hyper-parameters after the ith iteration, sigma represents the standard deviation, ++>Represent gradient, L i () Represents the loss function after the ith iteration, beta i Represents the parameters of the outer layer after the ith iteration, alpha represents the learning rate of the outer layer, m represents the number of samples and epsilon i Representing a normal vector of standard polynomials, D i Representing the benefit after the ith iteration.
A third embodiment of the invention relates to an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, which processor, when executing the computer program, implements the steps of the virtual power plant and distribution network collaborative interaction method of the first embodiment.
A fourth embodiment of the invention relates to a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the virtual power plant and distribution grid collaborative interaction method described above.
It is easy to find that the invention respectively establishes the optimization models of the virtual power plant and the power distribution network, and the virtual power plant can bid price and capacity under the condition of meeting the ordered operation of the virtual power plant, and the power distribution network can be cleared with the minimum operation cost under the condition of meeting the safe and stable operation, so that the benign interaction between the virtual power plant and the power distribution network is realized. The solving method provided by the invention can parameterize the history experience to realize quick solving, and meanwhile, only optimize the loss function in the strategy learning process without explicit reward signals, thereby greatly simplifying the computational complexity.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The scheme in the embodiment of the invention can be realized by adopting various computer languages, such as object-oriented programming language Java, an transliteration script language JavaScript and the like.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims (10)

1. The collaborative interaction method for the virtual power plant and the power distribution network is characterized by comprising the following steps of:
Establishing a virtual power plant optimization model which meets the condition of orderly operation of the virtual power plant by taking the maximum benefit as a target;
aiming at cost minimization, establishing a power distribution network optimization model meeting the condition of safe and stable operation of the power distribution network;
and establishing a Markov decision model based on the virtual power plant optimization model and the power distribution network optimization model, solving the Markov decision model by adopting evolutionary element reinforcement learning, and taking a solving result as a cooperative interaction strategy of the virtual power plant and the power distribution network.
2. The method for collaborative interaction between a virtual power plant and a power distribution network according to claim 1, wherein the objective function of the virtual power plant optimization model is:
wherein f VPP For an objective function of the virtual power plant optimization model, T represents the total length of time of optimization, I represents the total number of independently adjustable resources in the virtual power plant,representing the return achieved in the energy market by the independently adjustable resources in the virtual power plant before the day at time t,/->Representing the declared power in the energy market before the day at time t for the ith independently adjustable resource, +.>Representing the declared price of the ith independently adjustable resource in the energy market before the day at time t,/day>Representing the clearing power of the virtual power plant at time t-1 in the day-ahead energy market,/- >Representing the price of the energy market before day at time t-1, < >>Representing the running cost of the independent adjustable resources at the moment t to participate in the day-ahead energy market; n represents the total number of independent rigid resources in the virtual power plant,representing the total revenue of rigid resources in the energy market before the day at time t,/for>Represents bidding capacity of nth rigid resource in energy market before day of t time,/day>Represents the bidding price of the nth rigid resource in the energy market before the day of time t,/->Representing the total capacity deviation of the energy market before day at time t of participation of the virtual power plant, < >>Representing the running cost of the nth rigid resource participating in the energy market before the day at time t, +.>Represents penalty cost,/->Representing the output deviation of the nth rigid resource; j represents the number of intelligent parks in the virtual power plant, < >>Indicating the electricity purchasing state of the park at the time t, < +.>Representing the total gain of the energy market of the campus before the day at time t,/o>Indicating the bidding capacity of the j-th park to participate in the day-ahead energy market at time t,/>Represents the bid price in the energy market before day at time t for the jth campus,/->Indicating the day of participation of the jth park at time tOperating costs of the front energy market, +.>Output representing controllable resource at time t in jth park +. >Indicating the deviation of the output of renewable energy sources in the j-th park, +.>Represents the electricity purchasing cost of the park at the time t, < + >>Indicating the adjustable load capacity in the jth park at time t, +.>The electricity purchasing bias cost at the time t is represented,the amount of load deviation in the jth park at time t is shown.
3. The method of collaborative interaction between a virtual power plant and a power distribution network of claim 1, wherein constraints of the virtual power plant optimization model include:
independently adjustable resource bidding capacity upper and lower limit constraints:wherein P is IAR,i,min Representing the lower limit of bidding capacity of the ith independently adjustable resource at time t,/for>Representing the declared power in the energy market before the day at time t for the ith independently adjustable resource, +.>Representing the upper limit of bidding capacity of the ith independently adjustable resource at the time t;
independently adjustable resource bidding price upper and lower limit constraints:wherein: />Indicating the lower limit of bidding price of the ith independently adjustable resource at time t,/->Representing the declared price of the ith independently adjustable resource in the energy market before the day at time t,/day>The upper limit of bidding electricity price of the ith independently adjustable resource at the time t is represented;
independently adjustable resource climbing upper and lower limit constraints:wherein P is ramp,i,min Represents the lower limit of climbing of the ith independently adjustable resource, P ramp,i,max Representing an upper bound of the climbing of the ith independently adjustable resource;
upper and lower limit constraints of bidding capacity of independent non-adjustable resources:wherein (1)>Represents the lower limit of bidding capacity of the nth rigid resource at the time t,/day>Represents bidding capacity of nth rigid resource in energy market before day of t time,/day>The upper limit of bidding capacity of the nth rigid resource at the time t is represented;
upper and lower limit constraints of bidding price of independent non-adjustable resources:wherein (1)>Indicating the lower limit of bidding price of the nth rigid resource at the time t,/day>Represents the bidding price of the nth rigid resource in the energy market before the day of time t,/->The upper limit of bidding electricity price of the nth rigid resource at the time t is represented;
independent non-adjustable resource climbing upper and lower limit constraint:wherein P is ramp,n,min Represents the lower limit of climbing of the nth rigid resource, P ramp,n,max Representing the upper bound of the climbing of the nth rigid resource;
upper and lower limit constraint of bid amount in park:wherein (1)>Indicating the lower limit of bidding capacity of the jth campus at time t +.>Indicating the bid amount of the jth campus participating in the day-ahead energy market at time t,the upper limit of bidding capacity of the jth park at the moment t is represented;
upper and lower limit constraint of competitive bidding price in park:wherein (1)>Indicating the lower limit of bidding price of the jth campus at time t,/for >Representing the bid price in the energy market of the jth campus before the day at time t,
the upper limit of bidding electricity price of the jth park at the moment t is represented;
park climbing upper and lower limit constraint:wherein P is ramp,j,min Represents the lower limit of climbing in the jth park, P ramp,j,max Representing the upper limit of climbing in the jth campus;
park power balance constraint:
wherein,indicating the internal force at time t of the j-th campus,/->Indicating the electricity purchasing and selling state of the park at the time t,indicating the adjustable load capacity in the jth park at time t, +.>Load-adjustable force representing time t of jth park,/->Indicating the load reduction amount at time t of the jth park,/->Indicating the total load at time t of the j-th park;
park cut load limit constraints:wherein (1)>The maximum value at which the load can be reduced at the j-th park t is shown.
4. The method for collaborative interaction between a virtual power plant and a power distribution network according to claim 1, wherein the objective function of the power distribution network optimization model is:
wherein f DSO Representing an objective function of an optimization model of the power distribution network, T representing an optimization total duration, G representing the number of virtual power plants interacting with the power distribution network,representing the operating costs of the distribution network at time t +.>Indicating the clear power of the power distribution network to the g-th virtual power plant at time t, < > >Indicating the price of the energy market before day at time t +.>Represents the bidding capacity of the g-th virtual power plant at time t,/->Represents the competitive price of the g-th virtual power plant at time t,/->Representing electricity purchasing cost of power distribution network at time t +.>Represents the purchase price at time t, +.>Represents the price of the electricity abandon penalty at time t, +.>Indicating the adjustable load capacity in the jth park at time t, +.>Indicating the load reduction amount of the jth park at time t, ρ DSO Shows the force deviation normalization coefficient, +.>The deviation of the output force at time t is shown.
5. The method for collaborative interaction between a virtual power plant and a power distribution network according to claim 1, wherein constraints of the power distribution network optimization model include:
system power balance constraint:wherein G represents the number of virtual power plants interacting with the power distribution network, < >>The clear power of the power distribution network to the g virtual power plant at the moment t is represented; />The total adjustable load at the time t is represented;
and (5) clearing capacity constraint:wherein (1)>The bidding capacity of the g-th virtual power plant at the moment t is represented; line transmission power constraints: />Wherein (1)>Representing the power on the o-th line at time t, P line,o,min Representing the lower limit of reverse transmission power, P, on the o-th line line,o,max Representing the upper limit of forward transmission power of the o-th line;
The system cuts the load limiting constraint:wherein (1)>The system cut load amount at the time t is represented,the maximum value of the system cut load quantity at the moment t is shown;
constraint of a tide equation:wherein (1)>Representing the active power of the branch between node i and node j at time t, k (j, k) representing the set of branches with node j as the head node, +.>Representing the active power of a branch between a node j and a node k at the moment t, r ij Represents the resistance of the branch between node i and node j, < >>Represents the current of the branch between node i and node j at time t,/, and>represents the load active power of node j at time t, < >>Represents active power consumed by node j energy storage at time t, < >>Representing the active power injected by a node j at the moment t; />Representing the reactive power of the branch between node i and node j at time t,/>Representing the reactive power, x, of the branch between node j and node k at time t ij Representing the reactance between node i and node j, < +.>Represents the load reactive power of node j at time t, < >>Reactive power, < >/representing energy storage consumption of node j at time t>The reactive power injected by the node j at the moment t is represented; />Represents the voltage amplitude of node j at time t, +.>Representing the voltage amplitude of a node i at the time t;
node voltage constraint:wherein V is i,min Representing the lower voltage limit of node i, V i,max Representing the upper voltage limit of node i;
line current constraint:wherein I is ij,max Representing the maximum current that the branch can withstand between node i and node j.
6. The collaborative interaction method for a virtual power plant and a power distribution network according to claim 1, wherein when a markov decision model is established based on the virtual power plant optimization model and the power distribution network optimization model, for the virtual power plant, the action space of the markov decision model is calculatedExpressed as:status space->Expressed as: />Revenue collection R VPP Expressed as: r is R VPP ＝{-f VPP -a }; transition probability set P VPP Expressed as: />Policy set->Expressed as: />Long-term discount rewards set->Expressed as: />For a distribution network, the action space of a Markov decision model +.>Expressed as: />Status space->Expressed as:revenue collection R DSO Expressed as: r is R DSO ＝{f DSO -a }; transition probability set P DSO Expressed as: />Policy set->Expressed as: />Long-term discount rewards set->Expressed as: />Wherein f VPP For the objective function of the virtual power plant optimization model, +.>Representing the declared power in the energy market before the day at time t for the ith independently adjustable resource, +.>Representing the declared price of the ith independently adjustable resource in the energy market before the day at time t,/day>Represents bidding capacity of nth rigid resource in energy market before day of t time,/day >Represents the bidding price of the nth rigid resource in the energy market before the day of time t,/->Indicating the bidding capacity of the j-th park to participate in the day-ahead energy market at time t,/>Represents the bid price in the energy market before day at time t for the jth campus,/->Indicating the deviation of the force of the nth rigid resource, < >>Output representing controllable resource at time t in jth park +.>Indicating the deviation of the output of renewable energy sources in the j-th park, +.>Representing the clearing power of the virtual power plant at time t-1 in the day-ahead energy market,/->Representing the total capacity deviation of the energy market before the day at the moment of participation t of the virtual power plant, f DSO Objective function representing an optimization model of a power distribution network, +.>Indicating the clear power of the power distribution network to the g-th virtual power plant at time t, < >>Indicating the price of the energy market before day at time t +.>Represents the purchase price at time t, +.>Represents the price of the electricity abandon penalty at time t, +.>Represents the bidding capacity of the g-th virtual power plant at time t,/->Represents the competitive price of the g-th virtual power plant at time t,/->Indicating the adjustable load capacity in the jth campus at time t,indicating the load reduction amount of the jth park at time t,/, and>the output deviation at the time t is represented; gamma ray t Representing the discount factor at time t, E { } represents the mathematical expectation universal sign.
7. The method for collaborative interaction between a virtual power plant and a power distribution network according to claim 1, wherein pi is employed when the evolutionary element reinforcement learning solves the markov decision model * ＝argmaxE MDP,π (D) Solving the strategy by adoptingSolving inner layer super parameters by adopting +.>Carrying out outer layer super-parameter solving; wherein pi * Represent the optimal strategy, E MDP,π () Representing the expectations in executing a policy pi in a Markov decision model, D representing a set of long-term discount rewards in the Markov decision model, θ * Represents the inner layer super parameter under the optimal strategy, < ->Representing the expectation of a Markov model under a strategy pi when an internal parameter is theta, L β () Representing the loss function, MDP represents the Markov decision model, β * Represents the outer layer hyper-parameters under the optimal strategy, +.>Representing expected values of a Markov decision model under an optimal strategy; the update formula of the inner layer super parameter is as follows: />The updating formula of the outer layer super parameter is as follows: />Wherein θ i Represents the inner layer hyper-parameters after the ith iteration, sigma represents the standard deviation, ++>Represent gradient, L i () Represents the loss function after the ith iteration, beta i Represents the parameters of the outer layer after the ith iteration, alpha represents the learning rate of the outer layer, m represents the number of samples and epsilon i Representing a normal vector of standard polynomials, D i Representing after the ith iterationIs a benefit of (2).
8. The utility model provides a virtual power plant and distribution network collaborative interaction device which characterized in that includes:
the first building module is used for building a virtual power plant optimization model which meets the condition that the virtual power plant operates orderly with the aim of benefit maximization;
the second building module is used for building a power distribution network optimization model which meets the condition of safe and stable operation of the power distribution network with the aim of minimizing cost;
and the model solving film is used for establishing a Markov decision model based on the virtual power plant optimizing model and the power distribution network optimizing model, solving the Markov decision model by adopting evolutionary element reinforcement learning, and taking the solving result as a cooperative interaction strategy of the virtual power plant and the power distribution network.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the steps of the method for collaborative interaction of a virtual power plant with a distribution network according to any one of claims 1-7.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, carries out the steps of the method of collaborative interaction of a virtual power plant with a power distribution network according to any one of claims 1-7.
CN202311194350.1A 2023-09-15 2023-09-15 Collaborative interaction method, device, equipment and medium for virtual power plant and power distribution network Pending CN117291095A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311194350.1A CN117291095A (en) 2023-09-15 2023-09-15 Collaborative interaction method, device, equipment and medium for virtual power plant and power distribution network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311194350.1A CN117291095A (en) 2023-09-15 2023-09-15 Collaborative interaction method, device, equipment and medium for virtual power plant and power distribution network

Publications (1)

Publication Number Publication Date
CN117291095A true CN117291095A (en) 2023-12-26

Family

ID=89251034

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311194350.1A Pending CN117291095A (en) 2023-09-15 2023-09-15 Collaborative interaction method, device, equipment and medium for virtual power plant and power distribution network

Country Status (1)

Country Link
CN (1) CN117291095A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117494909A (en) * 2023-12-29 2024-02-02 国网浙江省电力有限公司营销服务中心 Electricity purchasing optimization method, device and medium based on entropy weight self-adaptive IGDT
CN117541030A (en) * 2024-01-09 2024-02-09 中建科工集团有限公司 Virtual power plant optimized operation method, device, equipment and medium

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117494909A (en) * 2023-12-29 2024-02-02 国网浙江省电力有限公司营销服务中心 Electricity purchasing optimization method, device and medium based on entropy weight self-adaptive IGDT
CN117494909B (en) * 2023-12-29 2024-05-28 国网浙江省电力有限公司营销服务中心 Electricity purchasing optimization method, device and medium based on entropy weight self-adaptive IGDT
CN117541030A (en) * 2024-01-09 2024-02-09 中建科工集团有限公司 Virtual power plant optimized operation method, device, equipment and medium
CN117541030B (en) * 2024-01-09 2024-04-26 中建科工集团有限公司 Virtual power plant optimized operation method, device, equipment and medium

Similar Documents

Publication Publication Date Title
CN117291095A (en) Collaborative interaction method, device, equipment and medium for virtual power plant and power distribution network
CN112614009B (en) Power grid energy management method and system based on deep expectation Q-learning
CN104376410B (en) A kind of planing method of Distributed Generation in Distribution System
Ehteram et al. Optimization of energy management and conversion in the multi-reservoir systems based on evolutionary algorithms
Wang et al. An improved partheno genetic algorithm for multi-objective economic dispatch in cascaded hydropower systems
CN112491094B (en) Hybrid-driven micro-grid energy management method, system and device
Zhang et al. Efficient design of energy microgrid management system: a promoted Remora optimization algorithm-based approach
CN109066741A (en) A kind of distributed energy storage method and system for planning for regional power grid peak load shifting
Ganesan et al. Hybrid neuro-swarm optimization approach for design of distributed generation power systems
Sahoo et al. Impact of energy storage system and distributed energy resources on bidding strategy of micro-grid in deregulated environment
Mori et al. Multi-objective transmission network expansion planning in consideration of wind farms
CN113410900A (en) Micro-grid HESS optimization configuration method and system based on self-adaptive difference whale optimization
CN117172486A (en) Reinforced learning-based virtual power plant optical storage resource aggregation regulation and control method
Wu et al. Low-carbon economic dispatch optimization of a virtual power plant based on deep reinforcement learning in China's carbon market environment
CN109214561A (en) Consider the distributed generation resource configuration method of active distribution system dynamic path optimization
CN117613875A (en) Electric automobile scheduling method and device based on cloud edge end cooperation and terminal equipment
CN109980695B (en) Distributed energy and user behavior prediction method for power distribution and utilization system
CN116436085A (en) Micro-energy network group hierarchical optimization control method and system based on scene construction
CN115395562A (en) Power distribution network access optimization method, device, equipment, storage medium and program product
CN116231667A (en) Rural power distribution network source-network-load-storage coordination optimization method based on PCAM-GMM
CN114285026B (en) Scheduling method for electric energy router in agriculture and animal husbandry area
CN115864364A (en) Operation strategy planning method and device for user to participate in demand response
CN114372645A (en) Energy supply system optimization method and system based on multi-agent reinforcement learning
CN114418232A (en) Energy storage system operation optimization method and system, server and storage medium
CN112365193A (en) Centralized clearing method and device for power market considering line transmission safety

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