CN112003279B - Evaluation method for new energy consumption capability of hierarchical micro-grid - Google Patents
Evaluation method for new energy consumption capability of hierarchical micro-grid Download PDFInfo
- Publication number
- CN112003279B CN112003279B CN202010852275.3A CN202010852275A CN112003279B CN 112003279 B CN112003279 B CN 112003279B CN 202010852275 A CN202010852275 A CN 202010852275A CN 112003279 B CN112003279 B CN 112003279B
- Authority
- CN
- China
- Prior art keywords
- grid
- micro
- hierarchical micro
- power
- ith
- 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
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 27
- 238000011156 evaluation Methods 0.000 title abstract description 11
- 238000000034 method Methods 0.000 claims abstract description 53
- 238000004891 communication Methods 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 19
- 230000008485 antagonism Effects 0.000 claims abstract description 5
- 238000004146 energy storage Methods 0.000 claims description 38
- 230000009471 action Effects 0.000 claims description 29
- 238000010248 power generation Methods 0.000 claims description 13
- 238000007599 discharging Methods 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 4
- 230000005611 electricity Effects 0.000 claims description 3
- 239000012634 fragment Substances 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims 1
- 230000006870 function Effects 0.000 description 34
- 238000004422 calculation algorithm Methods 0.000 description 19
- 230000008901 benefit Effects 0.000 description 5
- 238000005457 optimization Methods 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000002787 reinforcement Effects 0.000 description 3
- 238000013256 Gubra-Amylin NASH model Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
-
- 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
-
- 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
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
-
- 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
- H02J2300/22—The renewable source being solar energy
- H02J2300/24—The renewable source being solar energy of photovoltaic 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
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/28—The renewable source being wind energy
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
- Y02E10/56—Power conversion systems, e.g. maximum power point trackers
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E70/00—Other energy conversion or management systems reducing GHG emissions
- Y02E70/30—Systems combining energy storage with energy generation of non-fossil origin
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Power Engineering (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses an evaluation method of new energy consumption capability of a hierarchical micro-grid, belongs to the technical field of power system automation, and aims to solve the problem that the accuracy of renewable energy consumption capability evaluation is poor due to communication uncertainty such as communication delay and fluctuation of the hierarchical micro-grid. It comprises the following steps: the hierarchical micro-grid is connected with the power distribution network and the user load; training the generated countermeasure network by adopting a similar time difference error method; the similar time difference error method comprises the following steps: time differencing, generating an antagonism network, and normalizing the dominance function. The method is used for evaluating the new energy consumption capability of the micro-grid.
Description
Technical Field
The invention relates to an evaluation method of new energy consumption capability of a hierarchical micro-grid, and belongs to the technical field of power system automation.
Background
Micro-grids are a trend of future grid development, and are active power distribution systems composed of different types of conventional power Distribution Generators (DG), renewable energy generators (such as photovoltaic power generation and wind power generation), energy storage devices and controllable loads. Maximizing renewable energy consumption is a critical issue, corresponding to minimizing operating costs, i.e., maximizing economic benefits. Therefore, the renewable energy capacity assessment problem can be regarded as a new model of economic dispatch problem.
Renewable energy source output has volatility and intermittence, and in order to overcome the challenges brought by renewable energy sources, the problem of economic dispatch of the micro-grid is solved by utilizing a centralized control and distributed control technology, which is attracting a great deal of attention. In the prior art, research on the problem of renewable energy consumption capability assessment shows that the energy internet (IoE) has become a new and effective method for solving the problem. IoE can be seen as a form of power grid consisting of distributed power sources (DG), distributed Energy Storage Systems (ESS) and various loads, using advanced power electronics, information technology and intelligent management technology. Hierarchical micro-grids are a novel IoE structure. The communication infrastructure is an important component of the hierarchical micro-grid, and in the logging of most prior art documents, the economic dispatch problem in the ideal case has been solved. However, due to the existence of the hierarchical model, there are many uncertainties in wireless communication, such as communication problems, wireless communication delays, packet loss, and quantization errors during information exchange in the micro-grid, waste of resources and deterioration of system performance will reduce the capacity of renewable energy sources in the hierarchical micro-grid, and result in an increase in total cost.
In previous studies, different optimization strategies have been proposed to solve the economic dispatch problem. For example, a conventional genetic algorithm and particle swarm optimization algorithm have been proposed to solve this economic dispatch problem. However, the above algorithms have certain limitations, such as an increase in the number of iterations, and the optimal solution may be unstable. Thus, there is no method in the prior art that can make an assessment of the ability to dissipate renewable energy in a hierarchical micro grid where there is communication uncertainty.
Disclosure of Invention
The invention aims to solve the problem that the renewable energy consumption capability assessment accuracy is poor due to communication uncertainty such as communication delay and fluctuation of a hierarchical micro-grid, and provides an assessment method for new energy consumption capability of the hierarchical micro-grid.
The invention relates to an evaluation method of new energy consumption capability of a hierarchical micro-grid, which comprises the following steps:
the hierarchical micro-grid is connected with the power distribution network and the user load;
training the generated countermeasure network by adopting a similar time difference error method;
the similar time difference error method comprises the following steps: time differencing, generating an antagonism network, and normalizing the dominance function.
Preferably, the specific method for training the generation of the countermeasure network by adopting the similar time difference error method comprises the following steps:
s2-1, random noise z-N (0, 1) and a state S are input into a power generation network G;
s2-2, the power generation network G outputs action values of all actions in the current state according to the dominance function:
wherein: g (q| (s, a)) represents an action value function, G (a| (s, a)) represents a dominance function;
s2-3, obtaining an action a in the current state according to an action value function, transferring the obtained action a to a next state S 'to obtain a tuple ((S, a, r, S')), and storing the tuple in a buffer B;
s2-4, judging whether the storage space of the buffer area B is full, otherwise, returning to the step S2-1, and if yes, executing the step S2-5;
s2-5, randomly extracting M experience fragments from the buffer zone B, starting training the generated countermeasure network, and outputting the optimal strategy time difference;
s2-6, training a discrimination network D by using a generation network G' and adopting a random gradient descent method, so that the discrimination network D has JS divergence between an actual action value and an estimated action value, wherein the JS divergence is a time difference error;
s2-7, generating a countermeasure network by reducing JS divergence update, and training the generated countermeasure network by a similar time difference error method.
Preferably, the objective function of the hierarchical micro-grid includes:
the objective function of the hierarchical micro-grid is:
wherein: t represents a time period, N represents the number of hierarchical micro-grids,representing the photovoltaic output used by the ith hierarchical micro-grid at time t,/->Representing an ith hierarchical micro-grid at tEtching the wind power output used;
when the equipment acquisition cost and the traditional energy output cost are unchanged, the original objective function is equivalent to a cost minimization objective function:
wherein:representing the running cost of the ith hierarchical micro-grid at the moment t, C G (t) represents the interaction cost of the ith hierarchical micro-grid at the t moment;
wherein:representing the traditional energy output cost of the ith hierarchical micro-grid at the t moment,/and the like>The method comprises the steps of representing the rejection renewable energy cost of an ith hierarchical micro-grid at the time t;
the communication uncertainty of the hierarchical micro-grid is as follows:
wherein: />
ω ij Represents a contiguous weight matrix, and ω ij ＝ω ji The weight represents a cost change coefficient caused by time-varying communication uncertainty of the connection of the ith hierarchical micro grid and the jth hierarchical micro grid;
the real cost of a single microgrid is:
the real objective function is:
preferably, the constraint conditions of the hierarchical micro-grid include: the method comprises the following steps of power balance constraint conditions of an independent micro-grid, power balance constraint conditions of a networked micro-grid, cost calculation and constraint conditions of a traditional energy generator, output constraint conditions of a renewable energy generator, energy storage operation and charge and discharge constraint conditions and power exchange constraint conditions of a power distribution network.
Preferably, the power balance constraint condition of the independent micro-grid is as follows:
wherein: l (L) i (t) represents the load demand of the ith hierarchical micro-grid at the time t,representing the output of a traditional energy generator of an ith hierarchical micro-grid at the moment t,/and a third hierarchical micro-grid at the moment t>Indicating the output of a photovoltaic generator of the ith layering micro-grid at the moment t,/and the like>Indicating the output of a wind driven generator, dis, of an ith hierarchical micro-grid at the moment t i (t) represents the energy storage and discharge power, ch, of the ith hierarchical micro-grid at the moment t i (t) represents the energy storage and charging power, delta P, of the ith hierarchical micro-grid at the t moment i (t) represents the required or insufficient power, ΔP, of the ith hierarchical micro-grid at time t i (t) > 0 indicates a power shortage, ΔP i (t) < 0 represents a power surplus.
Preferably, the power balance constraint condition of the networked micro-grid is as follows:
wherein: p (P) D (t) represents the total demand of the networked micro-grid at the moment t, L t (t) represents the load demand of the t-th hierarchical micro-grid at t time, C.dis (t) represents the energy storage and discharge power of the upper control unit, C.ch (t) represents the energy storage and charge power of the upper control unit, and p G And (t) represents the power interacting with the distribution network.
Preferably, the cost calculation and constraint conditions of the conventional energy generator are as follows:
wherein: and alpha, beta and gamma all represent the power generation cost coefficient, and alpha, beta and gamma are all normal numbers.
Preferably, the output constraint condition of the renewable energy generator is:
wherein:representing the rated power of the photovoltaic generator, +.>Indicating the rated power of the wind power generator.
Preferably, the energy storage operation and charge and discharge constraint conditions are as follows:
Soc min ≤Soc i (t)≤Soc max ，
Soc i (t)＝Soc i (t-1)+Δt(Ch i (t)·η ch -Dis i (t)/η dis )；
wherein: soc i (t) represents the energy storage capacity of the ith hierarchical micro-grid at the t moment, soc i (t-1) represents the energy storage capacity of the ith layered micro-grid at time t-1, Δt represents the operation time period, η ch And eta dis Respectively representing the energy storage charging coefficient and the energy storage discharging coefficient, soc max And Soc min Respectively representing an upper limit and a lower limit of the charge capacity;
0≤Ch i (t)≤U.ch i (t)·Ch max ，
0≤Dis i (t)≤U.dis i (t)·Dis max ，
U.ch i (t)+U.dis i (t)≤1；
wherein: U.CH i (t) and U.dis i (t) respectively represents the charging state and the discharging state of the ith hierarchical micro-grid at the moment t, wherein the charging state and the discharging state are respectively 0 or 1, and Ch is the value max And Dis max And respectively representing the upper limits of the energy storage charging power and the energy storage discharging power of the ith hierarchical micro-grid.
Preferably, the constraint condition of the power exchange of the power distribution network is as follows:
C G (t)＝p G (t)·p(t)；
wherein: p (t) represents the interactive electricity price of the ith hierarchical micro-grid at the time t.
The invention has the advantages that:
the evaluation method of the new energy consumption capability of the hierarchical micro-grid adopts a new deep reinforcement learning algorithm, combines a generated countermeasure network (GAN), a Time Difference (TD) method and a normalized dominant function (NAF) to solve the problem of the maximization of the renewable energy capacity, and can evaluate the new energy consumption capability of the hierarchical micro-grid model considering communication uncertainty. The invention adopts a similar Time Difference (TD) error method to train the generation network (GAN), can better solve the distributed problem in the hybrid control, and solves the problem that the continuous action space can not be processed by using a normalized dominant function (NAF).
According to the evaluation method for the new energy consumption capability of the hierarchical micro-grid, the hierarchical micro-grid is directly connected with the power distribution network and the user load, so that the supply and the demand of the hierarchical micro-grid are balanced, and the capacity of renewable energy sources is improved to the greatest extent. The objective function and related constraint conditions of the hierarchical micro-grid are also provided, the running cost of the conventional micro-grid and the interaction cost with a power distribution system are considered, and the cost change caused by communication uncertainty is also considered, so that the evaluation of the new energy consumption capability is closer to the actual situation.
Drawings
FIG. 1 is a hybrid control architecture of a hierarchical micro-grid according to the present invention;
FIG. 2 is a flow chart of a method for evaluating new energy consumption capability of the hierarchical micro-grid;
FIG. 3 is a graph of wind energy variation characteristics over two days, with time on the abscissa and speed on the ordinate, in hours;
FIG. 4 is a graph of the characteristics of photovoltaic changes over two days, with the abscissa representing time, units of hours, and the ordinate representing energy;
fig. 5 is a graph showing the load change characteristics over two days, the abscissa represents time, the unit is hours, and the ordinate represents energy.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.
The first embodiment is as follows: next, referring to fig. 1, a method for evaluating new energy consumption capability of a hierarchical micro-grid according to the present embodiment will be described, which includes:
the hierarchical micro-grid is connected with the power distribution network and the user load;
training the generated countermeasure network by adopting a similar time difference error method;
the similar time difference error method comprises the following steps: time differencing, generating an antagonism network, and normalizing the dominance function.
In the present embodiment, the generation of the countermeasure network (GAN, generative Adversarial Networks) is a deep learning model, the Time Difference (TD) method is a method for solving the reinforcement learning problem without using a complete state sequence, and the normalized dominance function (NAF, normalized Advantage Functions) is a method for solving the continuous motion space problem based on the RL algorithm of the value function. A similar time difference error method is TD-GAN.
In this embodiment, the time-difference error method is similar to the TD-GAN method, which is a value function-based method, and the method can better solve the distributed problem in the hybrid control compared with the policy-based method. Furthermore, the problem that the method cannot handle continuous motion space is solved by using a normalized dominance function (NAF).
Further, as shown in fig. 2, a specific method for training the generation of the countermeasure network by using a similar time difference error method includes:
s2-1, random noise z-N (0, 1) and a state S are input into a power generation network G;
s2-2, the power generation network G outputs action values of all actions in the current state according to the dominance function:
wherein: g (q| (s, a)) represents an action value function, G (a| (s, a)) represents a dominance function;
s2-3, obtaining an action a in the current state according to an action value function, transferring the obtained action a to a next state S 'to obtain a tuple ((S, a, r, S')), and storing the tuple in a buffer B;
s2-4, judging whether the storage space of the buffer area B is full, otherwise, returning to the step S2-1, and if yes, executing the step S2-5;
s2-5, randomly extracting M experience fragments from the buffer zone B, starting training the generated countermeasure network, and outputting the optimal strategy time difference;
s2-6, training a discrimination network D by using a generation network G' and adopting a random gradient descent method, so that the discrimination network D has JS divergence between an actual action value and an estimated action value, wherein the JS divergence is a time difference error;
s2-7, generating a countermeasure network by reducing JS divergence update, and training the generated countermeasure network by a similar time difference error method.
In this embodiment, when the state space and the action space are large, the TD algorithm cannot update the state space and the action space by storing the action value function, that is, the TD algorithm cannot solve the continuous action space; in the GAN, the generation network (GAN) cannot obtain the policy; therefore, the mere use of time-difference (TD) algorithms and generation of a antagonism network (GAN) is not sufficient to solve the current problem.
In this embodiment, two participants in the GAN model are respectively a generation network G 'model and a discrimination network D model, the generation network G' model captures the distribution of sample data, the discrimination network D model is a binary classifier, and the probability that the sample is derived from training data rather than generated data is estimated. G' and D are typically nonlinear mapping functions such as multi-layer perceptions, neural networks, etc. Meanwhile, the input is random noise z subjected to simple distribution (such as Gaussian distribution), and an image with the same size as the training image is output. For D, by inputting the sample into the discriminant model D, it is desirable to output a low probability (judgment to be a generated sample); for G', D is spoofed as much as possible so that the output of the discriminant model has a high probability (misjudgment as a true sample), thereby forming competition and countermeasure. The GAN model has no loss function.
In the present embodiment, the generation network is trained based on the result of the discrimination network, and the discrimination network is the probability extracted from the actual sample operation value function. After a certain number of iterations, the parameters of the generated network G are copied into G'. Finally, training until the parameters gradually converge. As the number of iterations increases, the parameters of the generated countermeasure network will gradually conform to the model parameters. That is, as the model is trained, the parameters gradually converge.
Still further, the objective function of the hierarchical micro-grid includes:
the level ofThe objective function of the chemical microgrid is:
wherein: t represents a time period, N represents the number of hierarchical micro-grids,representing the photovoltaic output used by the ith hierarchical micro-grid at time t,/->The wind power output of the ith hierarchical micro-grid at the time t is represented;
when the equipment acquisition cost and the traditional energy output cost are unchanged, the original objective function is equivalent to a cost minimization objective function:
wherein:representing the running cost of the ith hierarchical micro-grid at the moment t, C G (t) represents the interaction cost of the ith hierarchical micro-grid at the t moment;
wherein:representing the traditional energy output cost of the ith hierarchical micro-grid at the t moment,/and the like>The method comprises the steps of representing the rejection renewable energy cost of an ith hierarchical micro-grid at the time t;
the communication uncertainty of the hierarchical micro-grid is as follows:
wherein: />
ω ij Represents a contiguous weight matrix, and ω ij ＝ω ji The weight represents a cost change coefficient caused by time-varying communication uncertainty of the connection of the ith hierarchical micro grid and the jth hierarchical micro grid;
the real cost of a single microgrid is:
the real objective function is:
still further, the constraints of the hierarchical micro-grid include: the method comprises the following steps of power balance constraint conditions of an independent micro-grid, power balance constraint conditions of a networked micro-grid, cost calculation and constraint conditions of a traditional energy generator, output constraint conditions of a renewable energy generator, energy storage operation and charge and discharge constraint conditions and power exchange constraint conditions of a power distribution network.
Still further, the power balance constraint conditions of the independent micro-grid are:
wherein: l (L) i (t) represents the load demand of the ith hierarchical micro-grid at the time t,representing the output of a traditional energy generator of an ith hierarchical micro-grid at the moment t,/and a third hierarchical micro-grid at the moment t>Indicating the output of a photovoltaic generator of the ith layering micro-grid at the moment t,/and the like>Indicating the output of a wind driven generator, dis, of an ith hierarchical micro-grid at the moment t i (t) represents the energy storage and discharge power, ch, of the ith hierarchical micro-grid at the moment t i (t) represents the energy storage and charging power, delta P, of the ith hierarchical micro-grid at the t moment i (t) represents the required or insufficient power, ΔP, of the ith hierarchical micro-grid at time t i (t) > 0 indicates a power shortage, ΔP i (t) < 0 represents a power surplus.
Still further, the power balance constraint conditions of the networked micro-grid are:
wherein: p (P) D (t) represents the total demand of the networked micro-grid at the moment t, L t (t) represents the load demand of the t-th hierarchical micro-grid at t time, C.dis (t) represents the energy storage and discharge power of the upper control unit, C.ch (t) represents the energy storage and charge power of the upper control unit, and p G And (t) represents the power interacting with the distribution network.
Still further, the cost calculation and constraint conditions of the conventional energy generator are as follows:
wherein: and alpha, beta and gamma all represent the power generation cost coefficient, and alpha, beta and gamma are all normal numbers.
Still further, the output constraint condition of the renewable energy generator is:
wherein:representing the rated power of the photovoltaic generator, +.>Indicating the rated power of the wind power generator.
Still further, the energy storage operation and charge-discharge constraint conditions are:
Soc min ≤Soc i (t)≤Soc max ，
Soc i (t)＝Soc i (t-1)+Δt(Ch i (t)·η ch -Dis i (t)/η dis )；
wherein: soc i (t) represents the energy storage capacity of the ith hierarchical micro-grid at the t moment, soc i (t-1) represents the energy storage capacity of the ith layered micro-grid at time t-1, Δt represents the operation time period, η ch And eta dis Respectively representing the energy storage charging coefficient and the energy storage discharging coefficient, soc max And Soc min Respectively representing an upper limit and a lower limit of the charge capacity;
0≤Ch i (t)≤U.ch i (t)·Ch max ，
0≤Dis i (t)≤U.dis i (t)·Dis max ，
U.ch i (t)+U.dis i (t)≤1；
wherein: U.CH i (t) and U.dis i (t) respectively represents the charging state and the discharging state of the ith hierarchical micro-grid at the moment t, wherein the values of the charging state and the discharging state are 0 or 1, and Ch max And Dis max And respectively representing the upper limit of the energy storage charging power and the energy storage discharging power of the ith hierarchical micro-grid.
Still further, the constraint condition of the power distribution network exchanging power is as follows:
C G (t)＝p G (t)·p(t)；
wherein: p (t) represents the interactive electricity price of the ith hierarchical micro-grid at the time t.
In the invention, as the objective function is the objective function with the maximum benefit of the micro-grid, the constraint condition and the cost of the traditional micro-grid are considered, and the cost change caused by communication uncertainty is also considered, so that the layered micro-grid provided by the invention is more in line with the actual situation.
In the invention, a hierarchical micro-grid structure consisting of three independent micro-grids and an upper control unit is adopted to carry out simulation experiments on the evaluation method of the new energy consumption capability of the hierarchical micro-grid.
MG1 was equipped with a gas turbine generator having a maximum output power of 100kW, a solar generator having a rated power of 70kW, and a turbine having a rated power of 40kW for the wind generator. MG2 is equipped with a gas turbine generator having a maximum output power of 150kW, a solar generator having a power rating of 70kW and a wind generator having a power rating of 40 kW. MG3 is equipped with a gas turbine generator having a maximum output power of 200kW, a solar generator having a capacity of 120kW, a solar generator having a rated power of 70kW, and a wind generator having a rated power of 40 kW. The upper control unit consists of a battery and a diesel generator.
Figures 3, 4 and 5 show the variation characteristics of wind energy, photovoltaic and load over two days, respectively. It can be seen from fig. 4 that the photovoltaic output has a strong regularity, 7:00 to 17:00 per day, which is the time at which renewable energy sources can be produced, at 12:00, 13:00 and 14:00 it reaches substantially maximum output, then gradually decreases. It can be seen from fig. 3 that the fluctuation of the wind energy output has no obvious rule, the wind energy is greatly affected by weather, and the estimation of the output condition is not easy. As can be seen from fig. 5, loads of 1:00 to 5:00 per day are used less often, with some regularity but the regularity of the rest of the time is not apparent. Compared with the two-day power generation condition, the overall change conditions of wind energy, photovoltaic power generation and load utilization rate are not well estimated, so that the DRL is well used.
The above simulation illustrates the authenticity of the model and the validity of the algorithm. To prove the authenticity of the model, whether the comparison model takes into account the economic benefits of the communication uncertainty, accounts for the change in the cost impact of the communication uncertainty. To demonstrate the effectiveness of this algorithm, we use DRL and RL to demonstrate the different regulatory capabilities of renewable energy sources.
The economic cost of the ideal model is substantially the same as that of the real model during the first few hours, but the cost of the real model, which takes into account the communication uncertainty, is always disturbed around the ideal model over time, but the overall variation is not large, since it is considered that the communication uncertainty is bounded by a consistency. But at the same time, a certain difference between the actual scene and the ideal scene is reflected. It is necessary to take into account communication uncertainties in real scenes. The DRL algorithm based on GAN network and TD learning has a stronger capacity than the RL-based algorithm. This is because deep learning can better perceive the environment, allowing strong learning to achieve the best strategy rate to complete the exploration process. In most cases, the renewable energy regulating capabilities of DRL and RL are similar, but the difference between the two can effectively indicate that the DRL algorithm proposed by the invention improves the performance of the RL algorithm by 5%. However, as the amount of data and the number of iterations increases, the capacity of the RL and DRL are substantially the same, but using DRL is more efficient when there is less data.
To effectively compare the performance of the algorithm, we calculated through 100 sets of experiments. The reward mean and standard deviation of the DPG algorithm and the TD-GAN algorithm are calculated and compared. The optimization results are compared mainly by means of average values. The magnitude of the standard deviation reflects the degree of fluctuation of the algorithm. The average value of the TD-GAN is obviously smaller than that of the DPG, which is the opposite, and the optimization effect of the TD-GAN is better. The shadow area of TD-GAN is smaller than DPG, which shows that the fluctuation degree is small and the stability is high. The simulation experiment shows that the algorithm adopted by the invention is more effective in solving the problem.
The invention provides a DRL method combining an countermeasure network generation and time sequence differential learning to solve the problem of renewable energy regulation in a layered micro-grid. And (3) integrally dispatching the IoE hierarchical micro-grid by adopting a hybrid micro-grid control method, and controlling the hierarchical micro-grid by adopting a hierarchical structure. To reflect the actual situation more clearly, uncertainty of communication between the micro-network layers is considered. The results indicate that the adoption of DRL to accommodate renewable energy sources can reduce the need for data compared to pure reinforcement learning. In addition, the timing difference method does not require state transition probabilities and an overall environment. The simulation result shows the influence of communication uncertainty, and proves the superiority of the evaluation method for the new energy consumption capability of the hierarchical micro-grid.
Although the invention herein has been described with reference to particular embodiments, it is to be understood that these embodiments are merely illustrative of the principles and applications of the present invention. It is therefore to be understood that numerous modifications may be made to the illustrative embodiments and that other arrangements may be devised without departing from the spirit and scope of the present invention as defined by the appended claims. It should be understood that the different dependent claims and the features described herein may be combined in ways other than as described in the original claims. It is also to be understood that features described in connection with separate embodiments may be used in other described embodiments.
Claims (8)
1. The method for evaluating the new energy consumption capacity of the hierarchical micro-grid is characterized by comprising the following steps of:
the hierarchical micro-grid is connected with the power distribution network and the user load;
training the generated countermeasure network by adopting a similar time difference error method;
the similar time difference error method comprises the following steps: time difference, generation of an antagonism network and normalization dominance function;
the specific method for training the generation of the countermeasure network by adopting the similar time difference error method comprises the following steps:
s2-1, random noise z-N (0, 1) and a state S are input into a power generation network G;
s2-2, the power generation network G outputs action values of all actions in the current state according to the dominance function:
wherein: g (q| (s, a)) represents an action value function, G (a| (s, a)) represents a dominance function;
s2-3, obtaining an action a in the current state according to an action value function, transferring the obtained action a to a next state S 'to obtain a tuple ((S, a, r, S')), and storing the tuple in a buffer B;
s2-4, judging whether the storage space of the buffer area B is full, otherwise, returning to the step S2-1, and if yes, executing the step S2-5;
s2-5, randomly extracting M experience fragments from the buffer zone B, starting training the generated countermeasure network, and outputting the optimal strategy time difference;
s2-6, training a discrimination network D by using a generation network G' and adopting a random gradient descent method, so that the discrimination network D has JS divergence between an actual action value and an estimated action value, wherein the JS divergence is a time difference error;
s2-7, generating an countermeasure network by reducing JS divergence update, and completing training of the generated countermeasure network by a similar time difference error method;
the objective function of the hierarchical micro-grid comprises:
the objective function of the hierarchical micro-grid is:
wherein: t represents a time period, N represents the number of hierarchical micro-grids,representing the photovoltaic output used by the ith hierarchical micro-grid at time t,/->The wind power output of the ith hierarchical micro-grid at the time t is represented;
when the equipment acquisition cost and the traditional energy output cost are unchanged at the beginning of the time t, the original objective function is equivalent to a cost minimization objective function:
wherein:representing the ith hierarchyRunning cost of micro-grid at t moment, C G (t) represents the interaction cost of the ith hierarchical micro-grid at the t moment;
wherein:representing the traditional energy output cost of the ith hierarchical micro-grid at the t moment,/and the like>The method comprises the steps of representing the rejection renewable energy cost of an ith hierarchical micro-grid at the time t;
the communication uncertainty of the hierarchical micro-grid is as follows:
wherein: />
ω ij Represents a contiguous weight matrix, and ω ij ＝ω ji The weight represents a cost change coefficient caused by time-varying communication uncertainty of the connection of the ith hierarchical micro grid and the jth hierarchical micro grid;
the real cost of a single microgrid is:
the real objective function is:
2. the method for evaluating new energy consumption capability of a hierarchical micro-grid according to claim 1, wherein the constraint conditions of the hierarchical micro-grid include: the method comprises the following steps of power balance constraint conditions of an independent micro-grid, power balance constraint conditions of a networked micro-grid, cost calculation and constraint conditions of a traditional energy generator, output constraint conditions of a renewable energy generator, energy storage operation and charge and discharge constraint conditions and power exchange constraint conditions of a power distribution network.
3. The method for evaluating new energy consumption capability of a hierarchical micro-grid according to claim 2, wherein the power balance constraint condition of the independent micro-grid is:
wherein: l (L) i (t) represents the load demand of the ith hierarchical micro-grid at the time t,representing the output of a traditional energy generator of an ith hierarchical micro-grid at the moment t,/and a third hierarchical micro-grid at the moment t>Representing the photovoltaic generator output of the ith hierarchical micro-grid at the moment t,/and the like>Indicating the output of a wind driven generator, dis, of an ith hierarchical micro-grid at the moment t i (t) represents the energy storage and discharge power, ch, of the ith hierarchical micro-grid at the moment t i (t) represents the energy storage and charging power, delta P, of the ith hierarchical micro-grid at the t moment i (t) represents the required or insufficient power, ΔP, of the ith hierarchical micro-grid at time t i (t) > 0 indicates a power shortage, ΔP i (t) < 0 represents a power surplus.
4. The method for evaluating new energy consumption capability of a hierarchical micro-grid according to claim 3, wherein the power balance constraint condition of the networked micro-grid is:
wherein: p (P) D (t) represents the total demand of the networked micro-grid at the moment t, L t (t) represents the load demand of the t-th hierarchical micro-grid at the t moment, C.dis (t) represents the energy storage and discharge power of the upper control unit, C.ch (t) represents the energy storage and charge power of the upper control unit, and p G And (t) represents the power interacting with the distribution network.
5. The method for evaluating new energy consumption capability of a hierarchical micro-grid according to claim 4, wherein the cost calculation and constraint conditions of the conventional energy generator are as follows:
wherein: and alpha, beta and gamma all represent the power generation cost coefficient, and alpha, beta and gamma are all normal numbers.
6. The method for evaluating new energy consumption capability of a hierarchical micro-grid according to claim 5, wherein the output constraint condition of the renewable energy generator is:
wherein:representing the rated power of the photovoltaic generator, +.>Indicating the rated power of the wind power generator.
7. The method for evaluating new energy consumption capability of a hierarchical micro-grid according to claim 6, wherein the constraint conditions of energy storage operation and charge and discharge are as follows:
Soc min ≤Soc i (t)≤Soc max ，
Soc i (t)＝Soc i (t-1)+Δt(Ch i (t)·η ch -Dis i (t)/η dis )；
wherein: soc i (t) represents the energy storage capacity of the ith hierarchical micro-grid at the t moment, soc i (t-1) represents the energy storage capacity of the ith hierarchical micro-grid at the time t-1, Δt represents the operation time period, η ch And eta dis Respectively represent an energy storage charging coefficient and an energy storage discharging coefficient, soc max And Soc min Respectively representing an upper limit and a lower limit of the charge capacity;
0≤Ch i (t)≤U.ch i (t)·Ch max ，
0≤Dis i (t)≤U.dis i (t)·Dis max ，
U.ch i (t)+U.dis i (t)≤1；
wherein: U.CH i (t) and U.dis i (t) respectively represents the charging state and the discharging state of the ith hierarchical micro-grid at the moment t, wherein the charging state and the discharging state are respectively 0 or 1, and Ch is the value max And Dis max And respectively representing the upper limits of the energy storage charging power and the energy storage discharging power of the ith hierarchical micro-grid.
8. The method for evaluating new energy consumption capability of a hierarchical micro-grid according to claim 7, wherein the constraint condition of power exchange of the power distribution network is:
C G (t)＝p G (t)·p(t)；
wherein: p (t) represents the interactive electricity price of the ith hierarchical micro-grid at the time t.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010852275.3A CN112003279B (en) | 2020-08-21 | 2020-08-21 | Evaluation method for new energy consumption capability of hierarchical micro-grid |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010852275.3A CN112003279B (en) | 2020-08-21 | 2020-08-21 | Evaluation method for new energy consumption capability of hierarchical micro-grid |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112003279A CN112003279A (en) | 2020-11-27 |
| CN112003279B true CN112003279B (en) | 2024-03-08 |
Family
ID=73472322
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010852275.3A Active CN112003279B (en) | 2020-08-21 | 2020-08-21 | Evaluation method for new energy consumption capability of hierarchical micro-grid |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112003279B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117175694B (en) * | 2023-11-03 | 2024-01-23 | 江苏龙擎动力科技股份有限公司 | Micro-grid optimal scheduling method and system based on new energy consumption |
| CN118657264A (en) * | 2024-08-21 | 2024-09-17 | 中国电力科学研究院有限公司 | Energy Internet optimization operation method and related device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570611A (en) * | 2016-09-29 | 2017-04-19 | 重庆大学 | Load demand response-based grid-connected micro power grid reliability assessment method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11526746B2 (en) * | 2018-11-20 | 2022-12-13 | Bank Of America Corporation | System and method for incremental learning through state-based real-time adaptations in neural networks |
-
2020
- 2020-08-21 CN CN202010852275.3A patent/CN112003279B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570611A (en) * | 2016-09-29 | 2017-04-19 | 重庆大学 | Load demand response-based grid-connected micro power grid reliability assessment method |
Non-Patent Citations (4)
| Title |
|---|
| Adaptive Consensus-Based Robust Strategy for Economic Dispatch of Smart Grids Subject to Communication Uncertainties;Wen G等;IEEE Transactions on Industrial informatics;全文 * |
| 深度学习在智能电网中的应用现状分析与展望;周念成廖建权王强钢李春艳李剑;电力系统自动化;全文 * |
| 考虑空调负荷虚拟储能的产消者鲁棒日前申报策略;殷爽睿;艾芊;王大鹏;丁永清;吴俊宏;谢胤喆;;电力系统自动化(04);全文 * |
| 蒙东地区适应新能源消纳的储能系统配置效果分析;肖冰;吴晓丹;尹宏学;吴冠宇;孙睿;周京华;;热力发电(07);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112003279A (en) | 2020-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Optimal sizing of a wind-energy storage system considering battery life | |
| Kou et al. | Stochastic coordination of plug-in electric vehicles and wind turbines in microgrid: A model predictive control approach | |
| CN111709672B (en) | Virtual power plant economic dispatching method based on scene and deep reinforcement learning | |
| CN107979111A (en) | A kind of energy management method for micro-grid based on the optimization of two benches robust | |
| CN112131733B (en) | Distributed power supply planning method considering influence of charging load of electric automobile | |
| CN105071389B (en) | The alternating current-direct current mixing micro-capacitance sensor optimizing operation method and device of meter and source net load interaction | |
| CN110994694B (en) | Micro-grid source-charge-storage coordination optimization scheduling method considering differentiated demand response | |
| CN114021390A (en) | Random robust optimization method for urban comprehensive energy system and application thereof | |
| CN112003279B (en) | Evaluation method for new energy consumption capability of hierarchical micro-grid | |
| CN111934360A (en) | Virtual power plant-energy storage system energy collaborative optimization regulation and control method based on model predictive control | |
| Fang et al. | Distributed deep reinforcement learning for renewable energy accommodation assessment with communication uncertainty in Internet of Energy | |
| CN116993205A (en) | Urban comprehensive energy system day-to-day operation adjustment capability assessment method | |
| CN117595392A (en) | Power distribution network joint optimization method and system considering light Fu Xiaona and light storage and charge configuration | |
| CN117060386A (en) | Micro-grid energy storage scheduling optimization method based on value distribution depth Q network | |
| CN105279575B (en) | Multiple-energy-source main body distributed game optimization method based on generating prediction | |
| CN105305485A (en) | Safety constraint economic dispatching method for consuming large-scale intermittent energy | |
| CN114676921A (en) | Method for calculating wind power receptibility of system by considering source load storage coordination optimization | |
| Kaur et al. | Design of the ANFIS based optimized frequency control module for an electric vehicle charging station | |
| Zhang et al. | Sizing and operation co‐optimization strategy for flexible traction power supply system | |
| Shang et al. | Distributed V2G dispatching via LSTM network within cloud-edge collaboration framework | |
| Li et al. | Multiobjective Optimization Model considering Demand Response and Uncertainty of Generation Side of Microgrid | |
| CN110766285A (en) | Day-ahead energy scheduling method based on virtual power plant | |
| CN116562542A (en) | Distribution network optimization operation method and system considering ordered charging of community electric vehicles | |
| CN116865270A (en) | Optimal scheduling method and system for flexible interconnection power distribution network containing embedded direct current | |
| Jin et al. | Joint scheduling of electric vehicle charging and energy storage operation |
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 |