CN109784545A - A kind of dispatching method of the distributed energy hinge based on multiple agent - Google Patents
A kind of dispatching method of the distributed energy hinge based on multiple agent Download PDFInfo
- Publication number
- CN109784545A CN109784545A CN201811581070.5A CN201811581070A CN109784545A CN 109784545 A CN109784545 A CN 109784545A CN 201811581070 A CN201811581070 A CN 201811581070A CN 109784545 A CN109784545 A CN 109784545A
- Authority
- CN
- China
- Prior art keywords
- intelligent body
- energy
- power purchase
- indicate
- purchase side
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000005611 electricity Effects 0.000 claims abstract description 33
- 239000011159 matrix material Substances 0.000 claims abstract description 23
- 230000009471 action Effects 0.000 claims abstract description 19
- 230000009916 joint effect Effects 0.000 claims abstract description 13
- 238000004519 manufacturing process Methods 0.000 claims abstract description 12
- 239000003795 chemical substances by application Substances 0.000 claims abstract description 10
- 230000000875 corresponding effect Effects 0.000 claims abstract description 8
- 239000000969 carrier Substances 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 39
- 230000000694 effects Effects 0.000 claims description 6
- 230000006399 behavior Effects 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The present invention provides a kind of distributed energy hinge dispatching method based on multiple agent, this method comprises: S1, by the hinge for exporting most type energy carriers setting sale of electricity side's intelligent body, remaining hinge is set as power purchase side's intelligent body, and determines the objective function of scheduling;S2, power purchase side's intelligent body determine whether that receiving the current optimal joint action policy that sale of electricity side's intelligent body determines then executes S3 if not accepted;S3, power purchase side's intelligent body determine its energy production;S4, power purchase side's intelligent body calculate the corresponding action value of its energy production, form yield-movement pair of each power purchase side's intelligent body;S5, power purchase side's intelligent body calculate yield-movement pair reward function, and update knowledge matrix according to reward function;S6, power purchase side's intelligent body carry out game with sale of electricity side's intelligent body according to the knowledge matrix update action strategy of update.The present invention can effectively acquire equalization point in distributed energy hinge, and can effectively improve the accuracy of optimal solution.
Description
Technical field
The present invention relates to distributed energy dispatching technique field more particularly to a kind of distributed energies based on multiple agent
The dispatching method of hinge.
Background technique
Energy resource system should provide safe and reliable, standardized electric energy to all types of user, and the moment meets power consumer i.e.
The electrical demand of load.While meeting user demand, Ying Tigao energy utilization rate reduces carbon emission and improves the energy using
Flexibility.In this context, the concept of energy hinge is proposed, energy hinge can be used between different energy sources carrier turning
Change, storage and scheduling.On this basis, this patent proposes a kind of point based on multiple agent bargaining Game Learning algorithm
Cloth energy hinge economy dispatching method.Existing method for optimizing scheduling belongs to greatly centralized optimization algorithm, is easy to processing
Device brings biggish calculating pressure.Simultaneously with the rise of scale and complexity, it is difficult to find optimal solution.
Summary of the invention
Technical problem to be solved by the present invention lies in provide a kind of dispatching party of the distributed energy hinge of multiple agent
Method, this method can effectively acquire equalization point in distributed energy hinge, and can effectively improve the accuracy of optimal solution.
The scheduling of in order to solve the above technical problem, the present invention provides a kind of distributed energy hinge based on multiple agent
Method includes the following steps:
S1, sale of electricity side's intelligent body is set by the hinge for exporting most type energy carriers, remaining hinge is set as power purchase
Square intelligent body, and determine the objective function of scheduling;
S2, power purchase side's intelligent body determine whether to receive the current optimal joint action policy that sale of electricity side's intelligent body determines, if
Do not receive, thens follow the steps S3;
S3, power purchase side's intelligent body determine its energy production,
S4, power purchase side's intelligent body calculate the corresponding action value of its corresponding energy production, form each power purchase side intelligence
Yield-movement pair of body;
S5, power purchase side's intelligent body calculate yield-movement pair reward function, and update controlled variable according to reward function
Knowledge matrix;
S6, power purchase side's intelligent body carry out game with sale of electricity side's intelligent body according to the knowledge matrix update action strategy of update.
Wherein, the objective function determined in the S1 are as follows:
Wherein, fIIt (x) is cost of electricity-generating, fCIt (x) is electric energy loss, x is the controlled variable of entire energy resource system, including every
The yield of a energy carrier and each distribution factor;xmIndicate the controlled variable vector of m-th of energy hub;Small tenon m and p points
Do not indicate that m-th of energy hub and p-th of energy carrier, M indicate the total quantity of energy hub, P is the collection of energy carrier
It closes;Indicate the demand of p-th of energy carrier of energy resource system, nm pTo be inputted with p-th of m-th of energy hub
The associated energy quantity of energy carrier, nm eIt is the generator quantity that m-th of energy hub has valve point effect,WithIt is first, second, third cost coefficient of j-th of the energy;andTo consider generator data point
First, second cost coefficient of the additional rectifier sinusoidal component of effect;For the input of j-th of the energy,It is j-th
The power output lower limit of the generator of the energy,WithRespectively p-th of the energy inputs the energy of m-th of energy hub
And output.
Wherein, the optimal joint action policy that sale of electricity side's intelligent body determines in the step S2 are as follows:
Wherein, k indicates the number of iterations;xk *Indicate the optimal joint action policy of kth time iteration;Indicate i-th of purchase
The bargaining action strategy of electricity side's intelligent body;It indicates in (k-1) secondary iteration, in addition to i-th of intelligent body, other purchases
The joint action strategy of electricity side's intelligent body;For the joint game strategy of power purchase side's intelligent body in -1 iteration of kth, UiIt indicates
The utility function of i-th of power purchase side's intelligent body;The number of n expression power purchase side's intelligent body;UsIndicate the effectiveness of sale of electricity side's intelligent body
Function.
Wherein, the step S3 is specifically included:
Wherein,Indicate the energy production of i-th of power purchase side's intelligent body,WithIt is i-th of power purchase respectively
Lower bound and the upper bound of the square intelligent body in v-th state;WithIn the input of respectively j-th power purchase side's intelligent body
Lower bound,Indicate p-th of input energy sources carrier to the current energy output quantity of m-th of energy hub.
Wherein, the step S4 is specifically included:
Wherein,It is the knowledge matrix of h-th of controlled variable of i-th of power purchase side's intelligent body in kth time iteration, q0It is
[0,1] random value in;ε is rate of exploitation;arandIndicate random action;It indicates for i-th of intelligent body, h-th of change
Measure the optimal value in d-th of section;WithRespectively indicate the upper bound and the lower bound in d-th of section;WithIt respectively indicates
The upper bound of h-th variable and lower bound;AihIt is xihMotion space;Δ (k, y) indicates the decaying letter increased with the number of iterations
Number, y are the input variable of the attenuation function, and r is the random value in [0,1];B is the system ginseng for characterizing nonuniformity degree
Number;kmaxIndicate maximum number of iterations,It is the actuating range of h-th of controlled variable of i-th of power purchase side's intelligent body,It is i-th
The action value of h-th of controlled variable of a power purchase side's intelligent body.
Wherein, the reward function of acquisition is calculated in the step S5 are as follows:
Wherein, Fi kjIt indicates in kth time iteration, the fitness function of j-th of intelligent body;pmIt is positive coefficient;SAi BestTable
Show in kth time iteration, the optimal behavior aggregate of i-th of intelligent body;F is aforementioned penalty function;NCiIt indicates to i-th of power purchase Fang Zhi
The constraint number of energy body;PFi uIndicate the penalty constrained i-th u-th of power purchase side's intelligent body;χ is penalty;Zi u
Indicate u-th of constraint to i-th of power purchase side's intelligent body;Zi u,limExpression and Zi uCorresponding restrict.
Wherein, it is specifically included in the step S5 according to the knowledge matrix that reward function updates controlled variable:
Wherein, QihIndicate the knowledge matrix of h-th of variable of i-th of power purchase side's intelligent body;The increasing of Δ Q expression knowledge quantity
It is long;α indicates knowledge learning rate;γ indicates discount factor;Indicate j-th of intelligent body to controlled variable xihPerformed
State-movement;R(sk,sk+1,ak) indicate to act a when selectionkFrom state skIt is transferred to state sk+1When reward immediately;aihIt indicates
Any one selectable action policy;AihIndicate xihBehavior aggregate;niIndicate the controlled variable number of i-th of power purchase side's intelligent body
Mesh;The population scale of J expression cooperative cluster.
Wherein, the step S6 is specifically included:
Wherein, i=1,2 ..., n.
The beneficial effect of the embodiment of the present invention is: using the betting model of a sale of electricity side and N number of power purchase side, selling first
Electricity side's intelligent body determines current optimal joint action policy, does not receive the movement plan of sale of electricity side's intelligent body in each power purchase side's intelligent body
In the case where slightly, each power purchase side's intelligent body determines state-movement pair of each controlled variable, and it is dynamic to calculate each state-
The reward function opposed updates knowledge matrix according to reward function, to update the action policy of each power purchase side's intelligent body
Carry out game.This method uses the betting model of a sale of electricity side and N number of power purchase side, can be in distributed energy hinge effectively
Acquiring equalization point, the present invention uses associative memory and swarm intelligence, it can speed up the convergence of knowledge matrix, while discovery mechanism
In the presence of the accuracy that can effectively improve optimal solution.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is that a kind of process of the dispatching method of distributed energy hinge based on multiple agent of the embodiment of the present invention is shown
It is intended to.
Specific embodiment
The explanation of following embodiment be with reference to attached drawing, can be to the specific embodiment implemented to the example present invention.
It is illustrated referring to Fig. 1, the embodiment of the present invention one provides a kind of distributed energy pivot based on multiple agent
Knob dispatching method comprising following steps:
S1, sale of electricity side's intelligent body is set by the hinge for exporting most type energy carriers, remaining hinge is set as power purchase
Square intelligent body, and determine objective function.
Specifically, selecting the hub for exporting most type energy carriers is sale of electricity side's intelligent body, remaining hub is purchase
Electricity side's intelligent body.
Objective function is the cost for considering power generation side and the comprehensive function of electric energy loss
WhereinfIIt (x) is cost of electricity-generating, fCIt (x) is electric energy loss, x is entire
The controlled variable of energy resource system, yield and each distribution factor including each energy carrier;xmIndicate m-th of energy hub
Controlled variable vector;Small tenon m and p respectively indicate m and energy hub and p-th of energy carrier, and M indicates energy hub
Total quantity, P is the set of energy carrier;Indicate the demand of p-th of energy carrier of energy resource system, fC mAnd fL mPoint
The cost of electricity-generating and energy loss for not indicating m-th of energy hub, are respectively calculated as follows:
Wherein nm pFor energy quantity associated with p-th of input energy sources carrier of m-th of energy hub, nm eIt is m
A energy hub has the generator quantity of valve point effect,WithIt is the cost coefficient of j-th of the energy;
andFor the cost coefficient of the additional rectifier sinusoidal component of consideration generator value point effect;For the defeated of j-th energy
Enter,For the power output lower limit of j-th of generator,WithRespectively p-th of the energy is to m-th energy hub
The energy enters and leaves and output.
S2, power purchase side's intelligent body determine whether to receive the current optimal joint action policy that sale of electricity side's intelligent body determines, if
Do not receive, thens follow the steps S3.
Specifically, sale of electricity side's intelligent body determines current optimal joint strategy according to the following formula:
Wherein, k indicates the number of iterations;xk *Indicate the optimal joint action policy of kth time iteration;Indicate i-th of purchase
The bargaining action strategy of electricity side's intelligent body;It indicates in (k-1) secondary iteration, in addition to i-th of intelligent body, other purchases
The joint action strategy of electricity side's intelligent body;For all power purchase side's joint game strategies in -1 iteration of kth, UiIt indicates i-th
The utility function of power purchase side's intelligent body;The number of n expression power purchase side's intelligent body;UsIndicate the utility function of sale of electricity side's intelligent body.
S3, power purchase side's intelligent body determine its energy production.
Specifically, if each intelligent body in power purchase side receives the strategy of sale of electricity side's intelligent body, iteration terminates;If not accepted, then
Each intelligent body in power purchase side determines first controlled variable state, the i.e. energy production of power purchase side's intelligent body according to the following formula.
Herein,Indicate the state of k-th of variable of i-th of power purchase side, i.e., the energy production of each power purchase side's intelligent body,WithThe lower bound for being i-th of the energy respectively in v-th state and the upper bound;WithRespectively jth
The input bound of a energy,Indicate that p-th of input energy sources carrier exports the current energy of m-th of energy hub
Amount.
S4, power purchase side's intelligent body calculate the corresponding action value of its corresponding energy production, form each power purchase side intelligence
Yield-movement pair of body.
Specifically, each power purchase side's intelligent body selects a movement plan to controlled variable according to corresponding knowledge matrix
Slightly, exact value is secondly calculated using non-homogeneous mutation operator according to the locally optimal solution of respective bins.
More specifically, each power purchase side's intelligent body selects controlled variable the range of an action policy according to the following formula
More specifically, calculating the accurate of movement using non-homogeneous mutation operator according to the locally optimal solution of respective bins
ValueIt specifically includes:
It is the knowledge matrix of h-th of controlled variable of i-th of power purchase side's intelligent body in kth time iteration, q0It is [0,1]
Interior random value;ε is rate of exploitation;arandIndicate random action;It indicates for i-th of intelligent body, h-th of variable exists
The optimal value in d-th of section;WithRespectively indicate the upper bound and the lower bound in d-th of section;WithRespectively indicate h
The upper bound of a variable and lower bound;AihIt is xihMotion space;Δ (k, y) indicates the attenuation function increased with the number of iterations, y
For the input variable of attenuation function;R is the random value in [0,1];B characterizes the system parameter of nonuniformity degree;kmaxIt indicates
Maximum number of iterations.
S5, power purchase side's intelligent body calculate yield-movement pair reward function, and update controlled variable according to reward function
Knowledge matrix.
Specifically, each power purchase side's intelligent body calculates state-movement pair reward function of each controlled variable according to the following formula:
Wherein,It indicates in kth time iteration, the fitness function of j-th of intelligent body;pmIt is positive coefficient;SAi BestTable
Show in kth time iteration, the optimal behavior aggregate of i-th of intelligent body;F is aforementioned penalty function;NCiIt indicates to i-th of power purchase Fang Zhi
The constraint number of energy body;PFi uIndicate the penalty constrained i-th u-th of power purchase side's intelligent body;χ is penalty;Zi u
Indicate u-th of constraint to i-th of power purchase side's intelligent body;Zi u,limExpression and Zi uCorresponding restrict.
Specifically, learn to carry out knowledge matrix update using Q, while in order to avoid " dimension calamity " Ying Caiyong associative memory comes
Stored knowledge.
According to reward maximization principle, power purchase side's intelligent body updates knowledge matrix, tool to each controlled variable according to the following formula
Body includes:
Wherein, QihIndicate the knowledge matrix of h-th of variable of i-th of power purchase side's intelligent body;The increasing of Δ Q expression knowledge quantity
It is long;α indicates knowledge learning rate;γ indicates discount factor;Indicate j-th of individual to controlled variable xihPerformed shape
State-movement pair;R(sk,sk+1,ak) indicate to act a when selectionkFrom state skIt is transferred to state sk+1When reward immediately;aihIt indicates
Any one selectable action policy;AihIndicate xihBehavior aggregate;niIndicate the controlled variable number of i-th of power purchase side's intelligent body
Mesh;The population scale of J expression cooperative cluster.
S6, power purchase side's intelligent body carry out game with sale of electricity side's intelligent body according to the knowledge matrix more new strategy of update.
Specifically, power purchase side's intelligent body more new strategy according to the following formula:
Wherein, i=1,2 ..., n.
A kind of distributed energy hinge dispatching method based on multiple agent of the embodiment of the present invention, using a sale of electricity side
With the betting model of N number of power purchase side, sale of electricity side's intelligent body first determines current optimal joint action policy, in each power purchase side's intelligence
In the case that body does not receive the action policy of sale of electricity side's intelligent body, each power purchase side's intelligent body determines the shape of each controlled variable
State-movement pair, and each state-movement pair reward function is calculated, knowledge matrix is updated according to reward function, to update
The action policy of each power purchase side's intelligent body carries out game.This method uses the game mould of a sale of electricity side and N number of power purchase side
Type, can effectively acquire equalization point in distributed energy hinge, and the present invention uses associative memory and swarm intelligence, can speed up
The convergence of knowledge matrix, while the presence of discovery mechanism can effectively improve the accuracy of optimal solution.
The above disclosure is only the preferred embodiments of the present invention, cannot limit the right model of the present invention with this certainly
It encloses, therefore equivalent changes made in accordance with the claims of the present invention, is still within the scope of the present invention.
Claims (8)
1. a kind of distributed energy hinge dispatching method based on multiple agent, which comprises the steps of:
S1, sale of electricity side's intelligent body is set by the hinge for exporting most type energy carriers, remaining hinge is set as power purchase Fang Zhi
Energy body, and determine the objective function of scheduling;
S2, power purchase side's intelligent body determine whether to receive the current optimal joint action policy that sale of electricity side's intelligent body determines, if not connecing
By thening follow the steps S3;
S3, power purchase side's intelligent body determine its energy production,
S4, power purchase side's intelligent body calculate the corresponding action value of its corresponding energy production, form each power purchase side's intelligent body
Yield-movement pair;
S5, power purchase side's intelligent body calculate yield-movement pair reward function, and the knowledge of controlled variable is updated according to reward function
Matrix;
S6, power purchase side's intelligent body carry out game with sale of electricity side's intelligent body according to the knowledge matrix update action strategy of update.
2. the method according to claim 1, wherein the objective function determined in the S1 are as follows:
Wherein, fIIt (x) is cost of electricity-generating, fCIt (x) is electric energy loss, x is the controlled variable of entire energy resource system, including each energy
The yield of source carrier and each distribution factor;xmIndicate the controlled variable vector of m-th of energy hub;Small tenon m and p distinguish table
Show that m-th of energy hub and p-th of energy carrier, M indicate the total quantity of energy hub, P is the set of energy carrier;Indicate the demand of p-th of energy carrier of energy resource system, nm pFor p-th of input energy sources with m-th of energy hub
The associated energy quantity of carrier, nm eIt is the generator quantity that m-th of energy hub has valve point effect,WithIt is first, second, third cost coefficient of j-th of the energy;WithTo consider that adding for generator value point effect is whole
Flow the first, second cost coefficient of sinusoidal component;For the input of j-th of the energy,For the generator of j-th of the energy
Power output lower limit,WithRespectively p-th of the energy outputs and inputs the energy of m-th of energy hub.
3. according to the method described in claim 2, it is characterized in that, in the step S2 sale of electricity side's intelligent body determine it is optimal
Close action policy are as follows:
Wherein, k indicates the number of iterations;xk *Indicate the optimal joint action policy of kth time iteration;Indicate i-th of power purchase side
The bargaining action strategy of intelligent body;It indicates in (k-1) secondary iteration, in addition to i-th of intelligent body, other power purchase sides
The joint action strategy of intelligent body;For the joint game strategy of power purchase side's intelligent body in -1 iteration of kth, UiIt indicates i-th
The utility function of power purchase side's intelligent body;The number of n expression power purchase side's intelligent body;UsIndicate the utility function of sale of electricity side's intelligent body.
4. according to the method described in claim 3, it is characterized in that, the step S3 is specifically included:
Wherein,Indicate the energy production of i-th of power purchase side's intelligent body,WithIt is i-th of power purchase Fang Zhi respectively
It can lower bound and the upper bound of the body in v-th state;WithAbove and below the input of respectively j-th power purchase side's intelligent body
Boundary,Indicate p-th of input energy sources carrier to the current energy output quantity of m-th of energy hub.
5. according to the method described in claim 4, it is characterized in that, the step S4 is specifically included:
Wherein,It is the knowledge matrix of h-th of controlled variable of i-th of power purchase side's intelligent body in kth time iteration, q0It is [0,1]
Interior random value;ε is rate of exploitation;arandIndicate random action;It indicates for i-th of intelligent body, h-th of variable exists
The optimal value in d-th of section;WithRespectively indicate the upper bound and the lower bound in d-th of section;WithRespectively indicate h
The upper bound of a variable and lower bound;AihIt is xihMotion space;Δ (k, y) indicates the attenuation function increased with the number of iterations, y
For the input variable of the attenuation function, r is the random value in [0,1];B is the system parameter for characterizing nonuniformity degree;
kmaxIndicate maximum number of iterations,It is the actuating range of h-th of controlled variable of i-th of power purchase side's intelligent body,It is i-th
The action value of h-th of controlled variable of power purchase side's intelligent body.
6. according to the method described in claim 5, it is characterized in that, calculating the reward function of acquisition in the step S5 are as follows:
Wherein, Fi kjIt indicates in kth time iteration, the fitness function of j-th of intelligent body;pmIt is positive coefficient;SAi BestIt indicates
Kth time iteration, the optimal behavior aggregate of i-th of intelligent body;F is aforementioned penalty function;NCiIt indicates to i-th of power purchase side's intelligent body
Constraint number;PFi uIndicate the penalty constrained i-th u-th of power purchase side's intelligent body;χ is penalty;Zi uIt indicates
U-th of constraint to i-th of power purchase side's intelligent body;Zi u,limExpression and Zi uCorresponding restrict.
7. according to the method described in claim 6, it is characterized in that, updating controlled variable according to reward function in the step S5
Knowledge matrix specifically include:
Wherein, QihIndicate the knowledge matrix of h-th of variable of i-th of power purchase side's intelligent body;The growth of Δ Q expression knowledge quantity;α table
Advise knowledge learning rate;γ indicates discount factor;Indicate j-th of intelligent body to controlled variable xihPerformed state-is dynamic
Make;R(sk,sk+1,ak) indicate to act a when selectionkFrom state skIt is transferred to state sk+1When reward immediately;aihIndicate any one
A selectable action policy;AihIndicate xihBehavior aggregate;niIndicate the controlled variable number of i-th of power purchase side's intelligent body;J table
Show the population scale of cooperative cluster.
8. according to the method described in claim 7, it is characterized by: the step S6 is specifically included:
Wherein, i=1,2 ..., n.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811581070.5A CN109784545A (en) | 2018-12-24 | 2018-12-24 | A kind of dispatching method of the distributed energy hinge based on multiple agent |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811581070.5A CN109784545A (en) | 2018-12-24 | 2018-12-24 | A kind of dispatching method of the distributed energy hinge based on multiple agent |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109784545A true CN109784545A (en) | 2019-05-21 |
Family
ID=66498134
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811581070.5A Pending CN109784545A (en) | 2018-12-24 | 2018-12-24 | A kind of dispatching method of the distributed energy hinge based on multiple agent |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109784545A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111047071A (en) * | 2019-10-29 | 2020-04-21 | 国网江苏省电力有限公司盐城供电分公司 | Power system real-time supply and demand interaction method based on deep migration learning and Stackelberg game |
CN115618754A (en) * | 2022-12-19 | 2023-01-17 | 中国科学院自动化研究所 | Multi-agent value evaluation method, device and readable storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100023174A1 (en) * | 2007-03-26 | 2010-01-28 | Satoshi Nagata | Electric power system |
CN103490413A (en) * | 2013-09-27 | 2014-01-01 | 华南理工大学 | Intelligent electricity generation control method based on intelligent body equalization algorithm |
CN106779177A (en) * | 2016-11-28 | 2017-05-31 | 国网冀北电力有限公司唐山供电公司 | Multiresolution wavelet neutral net electricity demand forecasting method based on particle group optimizing |
CN107045655A (en) * | 2016-12-07 | 2017-08-15 | 三峡大学 | Wolf pack clan strategy process based on the random consistent game of multiple agent and virtual generating clan |
CN108062605A (en) * | 2018-01-05 | 2018-05-22 | 国网冀北电力有限公司秦皇岛供电公司 | Electric energy fixes price according to quality method and device |
CN108985944A (en) * | 2018-08-07 | 2018-12-11 | 燕山大学 | Power market transaction method in micro-capacitance sensor group based on multiple agent and game theory |
CN108985766A (en) * | 2018-08-28 | 2018-12-11 | 东北大学 | A kind of polygon transaction system of electricity market and method based on block chain technology |
-
2018
- 2018-12-24 CN CN201811581070.5A patent/CN109784545A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100023174A1 (en) * | 2007-03-26 | 2010-01-28 | Satoshi Nagata | Electric power system |
CN103490413A (en) * | 2013-09-27 | 2014-01-01 | 华南理工大学 | Intelligent electricity generation control method based on intelligent body equalization algorithm |
CN106779177A (en) * | 2016-11-28 | 2017-05-31 | 国网冀北电力有限公司唐山供电公司 | Multiresolution wavelet neutral net electricity demand forecasting method based on particle group optimizing |
CN107045655A (en) * | 2016-12-07 | 2017-08-15 | 三峡大学 | Wolf pack clan strategy process based on the random consistent game of multiple agent and virtual generating clan |
CN108062605A (en) * | 2018-01-05 | 2018-05-22 | 国网冀北电力有限公司秦皇岛供电公司 | Electric energy fixes price according to quality method and device |
CN108985944A (en) * | 2018-08-07 | 2018-12-11 | 燕山大学 | Power market transaction method in micro-capacitance sensor group based on multiple agent and game theory |
CN108985766A (en) * | 2018-08-28 | 2018-12-11 | 东北大学 | A kind of polygon transaction system of electricity market and method based on block chain technology |
Non-Patent Citations (2)
Title |
---|
XIAOSHUN ZHANG 等: "Multi-Agent Bargaining Learning for Distributed Energy Hub Economic Dispatch", 《IEEE ACCESS》 * |
张孝顺等: "碳交易机制下多区域综合能源系统的分散调度", 《中国电机工程学报》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111047071A (en) * | 2019-10-29 | 2020-04-21 | 国网江苏省电力有限公司盐城供电分公司 | Power system real-time supply and demand interaction method based on deep migration learning and Stackelberg game |
CN115618754A (en) * | 2022-12-19 | 2023-01-17 | 中国科学院自动化研究所 | Multi-agent value evaluation method, device and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112614009B (en) | Power grid energy management method and system based on deep expectation Q-learning | |
CN108471143A (en) | Micro-grid multi-energy method for optimizing scheduling based on positive and negative feedback particle cluster algorithm | |
CN106600059A (en) | Intelligent power grid short-term load predication method based on improved RBF neural network | |
CN104009494B (en) | A kind of environmental economy power generation dispatching method | |
CN107706932B (en) | A kind of energy method for optimizing scheduling based on dynamic self-adapting fuzzy logic controller | |
CN109214095A (en) | Electric car charge and discharge Multiobjective Optimal Operation method | |
CN104636985A (en) | Method for predicting radio disturbance of electric transmission line by using improved BP (back propagation) neural network | |
CN104636801A (en) | Transmission line audible noise prediction method based on BP neural network optimization | |
CN107067190A (en) | The micro-capacitance sensor power trade method learnt based on deeply | |
CN108564205A (en) | A kind of load model and parameter identification optimization method based on measured data | |
CN106786543A (en) | A kind of distribution network optimization drop for considering net capability constraint damages reconstructing method | |
CN109858798B (en) | Power grid investment decision modeling method and device for correlating transformation measures with voltage indexes | |
CN107453396A (en) | A kind of Multiobjective Optimal Operation method that distributed photovoltaic power is contributed | |
CN113437756B (en) | Micro-grid optimization configuration method considering static voltage stability of power distribution network | |
CN114784823A (en) | Micro-grid frequency control method and system based on depth certainty strategy gradient | |
CN104123684A (en) | Power distribution network economy reconstructing method considering network loss and reliability | |
CN115986728A (en) | Power grid situation prediction method considering uncertainty factors and terminal | |
CN107516892A (en) | The method that the quality of power supply is improved based on processing active optimization constraints | |
CN111008790A (en) | Hydropower station group power generation electric scheduling rule extraction method | |
CN109784545A (en) | A kind of dispatching method of the distributed energy hinge based on multiple agent | |
CN104915788B (en) | A method of considering the Electrical Power System Dynamic economic load dispatching of windy field correlation | |
CN115660346A (en) | Large-scale vehicle network interactive load regulation and control method based on edge control | |
CN106570774A (en) | Progressive learning grid regulation and control method based on learning theory | |
CN116822719A (en) | Multi-target planning method and device for power distribution network | |
CN115795992A (en) | Park energy Internet online scheduling method based on virtual deduction of operation situation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190521 |