CN111224433A - Secondary frequency modulation control method and system for distributed energy storage system - Google Patents
Secondary frequency modulation control method and system for distributed energy storage system Download PDFInfo
- Publication number
- CN111224433A CN111224433A CN202010151834.8A CN202010151834A CN111224433A CN 111224433 A CN111224433 A CN 111224433A CN 202010151834 A CN202010151834 A CN 202010151834A CN 111224433 A CN111224433 A CN 111224433A
- Authority
- CN
- China
- Prior art keywords
- reinforcement learning
- learning matrix
- matrix
- energy storage
- storage system
- 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
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—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
- H02J3/48—Controlling the sharing of the in-phase component
-
- 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
- H02J3/24—Arrangements for preventing or reducing oscillations of power in 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a distributed energy storage system secondary frequency modulation control method, which comprises the following steps: determining a system frequency state interval of the power system according to the allowable frequency deviation range of the power system; determining a state interval of the energy storage system; establishing a reinforcement learning matrix according to the system frequency state interval and the state interval, and determining a reinforcement learning rate; initializing the state interval; calculating the reward values of all actions at the next moment according to the updating strategy of the reinforcement learning matrix, and adopting the selection action corresponding to the strategy with the maximum reward value; acquiring the value of a certain element of the reinforcement learning matrix by using the selection action, and updating the reinforcement learning matrix; when the reinforcement learning matrix meets the convergence condition, storing the reinforcement learning matrix; and controlling the secondary frequency modulation of the distributed energy storage system by using the stored reinforcement learning matrix.
Description
Technical Field
The invention relates to the technical field of power energy storage, in particular to a distributed energy storage system secondary frequency modulation control method and system.
Background
Energy storage technology refers primarily to the storage of electrical energy. The stored energy can be used as emergency energy, can also be used for storing energy when the load of the power grid is low, and can be used for outputting energy when the load of the power grid is high, so that the energy can be used for clipping peaks and filling valleys and reducing the fluctuation of the power grid. Energy takes many forms, including radiation, chemical, gravitational potential, electrical potential, electricity, heat, latent heat, and kinetic energy. Energy storage involves the conversion of energy in a form that is difficult to store into a more convenient or economically storable form. A large amount of stored energy is mainly composed of power generation dams at present, and water is pumped by a water pump or a traditional water pump.
In recent years, the energy storage technology is rapidly developed, and the energy storage cost is obviously reduced under the national policy support and the guidance of the market. The rapid development of the energy storage system brings a new generator for the safe and stable operation of the power system, and the battery energy storage technology has rapid and accurate response capability and is more efficient than the traditional frequency modulation means. Reinforcement learning (reinforcement learning) is an important machine learning method, and has many applications in the fields of intelligent control, analysis and prediction, etc., and applying artificial intelligence technology to power systems is a development trend of future power systems.
Therefore, a technique is needed to control the secondary frequency modulation of the distributed energy storage system.
Disclosure of Invention
The technical scheme of the invention provides a distributed energy storage system secondary frequency modulation control method and a distributed energy storage system secondary frequency modulation control system, and aims to solve the problem of how to perform secondary frequency modulation control on a distributed energy storage system.
In order to solve the above problem, the present invention provides a distributed energy storage system secondary frequency modulation control method, including:
determining a system frequency state interval of the power system according to the allowable frequency deviation range of the power system;
determining a state interval of the energy storage system;
establishing a reinforcement learning matrix according to the system frequency state interval and the state interval, and determining a reinforcement learning rate;
initializing the state interval;
calculating the reward values of all actions at the next moment according to the updating strategy of the reinforcement learning matrix, and adopting the selection action corresponding to the strategy with the maximum reward value;
acquiring the value of a certain element of the reinforcement learning matrix by using the selection action, and updating the reinforcement learning matrix;
when the reinforcement learning matrix meets the convergence condition, storing the reinforcement learning matrix; and controlling the secondary frequency modulation of the distributed energy storage system by using the stored reinforcement learning matrix.
Preferably, the convergence condition of the reinforcement learning matrix is:
when the reinforcement learning matrix has not changed in k cycles, i.e. Qi＝Qi+1＝Qi+2＝…＝Qi+k-1＝Qi+kWherein Q isi、Qi+1、Qi+2、Qi+k-1、Qi+kRespectively are reinforcement learning matrixes obtained by the circulation of the ith, i +1, i +2, i + k-1 and i + k times, and the k value is set according to needs.
Preferably, when the reinforcement learning matrix still does not meet the convergence condition after reaching the preset time, the calculation of reward values of all actions at the next moment is stopped.
Preferably, the method further includes performing normalization processing on the reinforcement learning matrix Q, where the normalization rule is:
wherein QuniFor normalized reinforcement learning matrix Q, QmaxIs the largest element in the reinforcement learning matrix Q.
Preferably, when the policy with the largest prize value is plural, any one of the selection actions is taken.
Based on another aspect of the present invention, a distributed energy storage system secondary frequency modulation control system is provided, where the system includes:
the system comprises a first initial unit, a second initial unit and a control unit, wherein the first initial unit is used for determining a system frequency state interval of a power system according to an allowable frequency deviation range of the power system;
the second initial unit is used for determining the state interval of the energy storage system;
a third initial unit, configured to establish a reinforcement learning matrix according to the system frequency state interval and the state interval, and determine a reinforcement learning rate;
a fourth initialization unit, configured to initialize the state interval;
the calculation unit is used for calculating the reward values of all actions at the next moment according to the updating strategy of the reinforcement learning matrix and adopting the selection action corresponding to the strategy with the maximum reward value;
the updating unit is used for acquiring the value of a certain element of the reinforcement learning matrix by using the selection action and updating the reinforcement learning matrix;
the control unit is used for storing the reinforcement learning matrix when the reinforcement learning matrix meets a convergence condition; and controlling the secondary frequency modulation of the distributed energy storage system by using the stored reinforcement learning matrix.
Preferably, the convergence condition of the reinforcement learning matrix is:
when the reinforcement learning matrix has not changed in k cycles, i.e. Qi＝Qi+1＝Qi+2＝…＝Qi+k-1＝Qi+kWherein Q isi、Qi+1、Qi+2、Qi+k-1、Qi+kRespectively are reinforcement learning matrixes obtained by the circulation of the ith, i +1, i +2, i + k-1 and i + k times, and the k value is set according to needs.
Preferably, the device further comprises a termination unit, configured to stop calculating the reward values of all actions at the next time when the reinforcement learning matrix still does not meet the convergence condition after reaching the preset time.
Preferably, the apparatus further includes a normalization unit, configured to perform normalization processing on the reinforcement learning matrix Q, where a normalization rule is:
wherein QuniFor normalized reinforcement learning matrix Q, QmaxIs the largest element in the reinforcement learning matrix Q.
Preferably, the computing unit is further configured to: when the strategy of the maximum reward value is a plurality of strategies, any one of the selection actions is taken.
The technical scheme of the invention provides a distributed energy storage system secondary frequency modulation control method and system, which are used for realizing the no-difference adjustment of the frequency of a power system. The method comprises the following steps: determining a system frequency state interval of the power system according to the allowable frequency deviation range of the power system; determining a state interval of the energy storage system; establishing a reinforcement learning matrix according to the system frequency state interval and the state interval, and determining the reinforcement learning rate; initializing a state interval; calculating the reward values of all actions at the next moment according to the updating strategy of the reinforcement learning matrix, and adopting the selection action corresponding to the strategy with the maximum reward value; acquiring the value of a certain element of the reinforcement learning matrix by using the selection action, and updating the reinforcement learning matrix; when the reinforcement learning matrix meets the convergence condition, storing the reinforcement learning matrix; and controlling the secondary frequency modulation of the distributed energy storage system by using the stored reinforcement learning matrix. According to the technical scheme, the distributed energy storage system can accurately participate in secondary frequency modulation of the power system, so that the frequency of the power system is maintained at a rated frequency, the frequency fluctuation is improved, and the stability of the power system is improved. Meanwhile, the service life of the battery energy storage system is prolonged, and the cost is reduced.
Drawings
A more complete understanding of exemplary embodiments of the present invention may be had by reference to the following drawings in which:
fig. 1 is a flow chart of a distributed energy storage system secondary frequency modulation control method according to a preferred embodiment of the invention;
fig. 2 is a flow chart of a distributed energy storage system secondary frequency modulation control method according to a preferred embodiment of the invention;
FIG. 3 is a schematic diagram of a distributed energy storage system accessing a power grid according to a preferred embodiment of the present invention; and
fig. 4 is a structural diagram of a distributed energy storage system secondary frequency modulation control system according to a preferred embodiment of the invention.
Detailed Description
The exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, however, the present invention may be embodied in many different forms and is not limited to the embodiments described herein, which are provided for complete and complete disclosure of the present invention and to fully convey the scope of the present invention to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the accompanying drawings is not intended to be limiting of the invention. In the drawings, the same units/elements are denoted by the same reference numerals.
Unless otherwise defined, terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Further, it will be understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense.
Fig. 1 is a flowchart of a distributed energy storage system secondary frequency modulation control method according to a preferred embodiment of the present invention. The energy storage system in the power grid gradually adopts a distributed access mode, the frequency modulation control method of the distributed energy storage system participation system is more complex, and the application introduces a reinforcement learning theory into the control of distributed energy storage so as to realize the accurate control of the multipoint-accessed distributed pure pumpkin system participating in the secondary frequency modulation of the power system. The embodiment of the invention provides a distributed electric energy storage system secondary frequency modulation control method and system, and mainly aims at controlling the secondary frequency modulation of a system by a distributed energy storage system when the system frequency fluctuates due to load changes in an electric power system and when the system primary frequency modulation is subjected to poor adjustment and the system frequency still has deviation. The application provides a distributed energy storage system secondary frequency modulation control method, including: allowing a frequency deviation range for the power system, and dividing a frequency state index; and dividing the state indexes of the energy storage system according to the SOC state of the distributed energy storage system, thereby determining a reinforcement learning state space set. The reinforcement learning reward function is a main determining factor of the selection action of the distributed energy storage system, and the system updates a reinforcement learning matrix Q matrix through continuous learning so as to obtain an optimal control strategy. The obtained Q matrix can be continuously put into online learning, and the longer the learning time is, the better the control effect is. As shown in fig. 1, a method for controlling secondary frequency modulation of a distributed energy storage system includes:
preferably, in step 101: and determining a system frequency state interval of the power system according to the allowable frequency deviation range of the power system. According to the method and the device, the frequency state indexes of the power system are divided according to the allowable change range of the frequency of the power system. The rated frequency of the power system in China is 50HZ, the allowable value of normal frequency deviation is +/-0.2 HZ, and when the system capacity is small, the frequency difference can be widened to +/-0.5 HZ. In order to achieve precise frequency control, the system frequency state is divided into 17 intervals, which are { (0, 48.0) (48.0, 49.0), (49.0, 49.5)],(49.5,49.6],(49.6,49.7],(49.7,49.8],(49.8,49.9],(49.9,49.95],(49.95,50.05],(50.05,50.1],(50.1,50.2],(50.2,50.3],(50.3,50.4],(50.4,50.5],(50.5,51.0](51.0,52.0), (52.0, + ∞) }, which named these 17 state intervals, respectively
Visible, state Sf9Is the optimal state of the system frequency.
Preferably, at step 102: and determining the state interval of the energy storage system. In the present application, an energy storage system state space and an action state set are determined. As shown in fig. 3, the energy storage energy is distributed in the power system, and it is assumed that a regional power system has N (N ═ 1,2, …) points to access the energy storage system, and each energy storage system has a rated capacity of CN(N is 1,2, …), and the SOC state at time t is SOCN(t) of (d). According to the SOC state of each energy storage system, each energy storage system is divided into 11 intervals which are respectively { (0, 0.1)]，(0.1，0.2),(0.2,0.3],(0.3,0.4],(0.4,0.45],(0.45,0.55],(0.55,0.6],(0.6,0.7],(0.7,0.8],(0.8,0.9],(0.9,1.0]And, the 17 intervals are named as
The closer the SOC of the energy storage system is to 0.5, the more beneficial the adjustment of the frequency through charging and discharging, and the visible state
And the optimal state of the energy storage system is obtained. Discretizing the action (absorbed power or output power) of each energy storage system into K fixed values
Preferably, in step 103: and establishing a reinforcement learning matrix according to the system frequency state interval and the state interval, and determining the reinforcement learning rate. The method and the device for determining the reinforcement learning rate determine the reinforcement learning Q matrix. According to 17 divided system frequency state intervals and 11 multiplied by N distributed energy storage system state intervals, the secondary frequency modulation control state space of one regional distributed electric energy storage system is totally 17 multiplied by 11NEach state, in total, has 11KAnd (6) an action. Thus, the reinforcement learning Q matrix can be expressed as:
and initializing the Q matrix into a 0 matrix, and determining the reinforcement learning rate Gamma.
Preferably, at step 104: initializing a state interval;
preferably, at step 105: calculating the reward values of all actions at the next moment according to the updating strategy of the reinforcement learning matrix, and adopting the selection action corresponding to the strategy with the maximum reward value;
preferably, when the policy with the largest prize value is plural, any one of the selection actions is taken.
As shown in FIG. 2, in the present application, the reinforcement learning system state space is initialized randomly. And (4) according to the Q matrix updating strategy, calculating the reward values of all actions at the next moment, adopting the strategy selection action with the maximum reward value, and randomly selecting one action if the reward values of a plurality of actions are the same. And (5) obtaining the value of a certain element of the Q matrix according to the action strategy in the step (5), and updating the Q matrix.
In the learning process, the updating strategy of the Q matrix is as follows:
Q(state,action)＝R(state,action)+Gamma×Max[Q(next state,allactions)]
wherein, R (state, action) is the reward function, and Gamma is the learning rate.
The reward function R (state, action) is composed of two parts, represented as follows:
R(state,action)＝αR1(f_state,action)+βR2(e_state,action)
wherein R is1(f _ state, action) is the system frequency reward function, R2and (e _ state, action) is a distributed energy storage system state reward function, α and β are respectively a system frequency and a distributed energy storage system state reward weight coefficient, and α + β is 1.
System frequency reward function R1The (f _ state, action) rule can be expressed as:
distributed energy storage system state reward function R2The (e _ state, action) rule can be expressed as:
preferably, at step 106: acquiring the value of a certain element of the reinforcement learning matrix by using the selection action, and updating the reinforcement learning matrix;
preferably, in step 107: when the reinforcement learning matrix meets the convergence condition, storing the reinforcement learning matrix; and controlling the secondary frequency modulation of the distributed energy storage system by using the stored reinforcement learning matrix.
Preferably, the convergence condition of the reinforcement learning matrix is:
when the reinforcement learning matrix has not changed in k cycles, i.e. Qi＝Qi+1＝Qi+2＝…＝Qi+k-1＝Qi+kWherein Q isi、Qi+1、Qi+2、Qi+k-1、Qi+kRespectively are reinforcement learning matrixes obtained by the circulation of the ith, i +1, i +2, i + k-1 and i + k times, and the k value is set according to needs.
Preferably, when the reinforcement learning matrix still does not satisfy the convergence condition after reaching the preset time, the calculation of the reward values of all actions at the next moment is stopped.
The convergence conditions of the present application are two types: one is that the Q matrix has no change in k cycles, i.e. Qi＝Qi+1＝Qi+2＝…＝Qi+k-1＝Qi+kThe value of k can be set manually as required. Another way to address the situation where the Q matrix does not converge for a long time, the maximum number of cycles or the longest cycle may be set.
Preferably, the method further includes performing normalization processing on the reinforcement learning matrix Q, where the normalization rule is:
wherein QuniFor normalized reinforcement learning matrix Q, QmaxIs the largest element in the reinforcement learning matrix Q.
The Q matrix normalization rule is as follows:
wherein QuniIs a normalized Q matrix, QmaxIs the largest element in the Q matrix.
Fig. 4 is a structural diagram of a distributed energy storage system secondary frequency modulation control system according to a preferred embodiment of the invention. As shown in fig. 4, a distributed energy storage system secondary frequency modulation control system includes:
the first initialization unit 401 is configured to determine a system frequency state interval of the power system according to the allowable frequency deviation range of the power system.
A second initialization unit 402 is configured to determine a state interval of the energy storage system.
A third initial unit 403, configured to establish a reinforcement learning matrix according to the system frequency state interval and the state interval, and determine a reinforcement learning rate.
A fourth initializing unit 404, configured to initialize the state interval.
The calculating unit 405 is configured to calculate reward values of all actions at the next time according to the update policy of the reinforcement learning matrix, and take a selection action corresponding to the policy with the largest reward value. Preferably, the system computing unit 405 is further configured to: when the strategy of the maximum reward value is a plurality of strategies, any one of the selection actions is taken.
An updating unit 406, configured to obtain a value of an element of the reinforcement learning matrix by using the selecting action, and update the reinforcement learning matrix.
A control unit 407, configured to store the reinforcement learning matrix when the reinforcement learning matrix satisfies the convergence condition; and controlling the secondary frequency modulation of the distributed energy storage system by using the stored reinforcement learning matrix.
Preferably, the convergence condition of the reinforcement learning matrix is:
when the reinforcement learning matrix has not changed in k cycles, i.e. Qi＝Qi+1＝Qi+2＝…＝Qi+k-1＝Qi+kWherein Q isi、Qi+1、Qi+2、Qi+k-1、Qi+kRespectively are reinforcement learning matrixes obtained by the circulation of the ith, i +1, i +2, i + k-1 and i + k times, and the k value is set according to needs.
Preferably, the system further comprises a termination unit for stopping calculating the reward value of all actions at the next moment when the reinforcement learning matrix still does not meet the convergence condition after reaching the preset time.
Preferably, the system further includes a normalization unit, configured to perform normalization processing on the reinforcement learning matrix Q, where the normalization rule is:
wherein QuniFor normalized reinforcement learning matrix Q, QmaxIs the largest element in the reinforcement learning matrix Q.
The distributed energy storage system secondary frequency modulation control system 400 according to a preferred embodiment of the present invention corresponds to the distributed energy storage system secondary frequency modulation control method 100 according to another preferred embodiment of the present invention, and details thereof are not repeated herein.
The invention has been described with reference to a few embodiments. However, other embodiments of the invention than the one disclosed above are equally possible within the scope of the invention, as would be apparent to a person skilled in the art from the appended patent claims.
Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to "a/an/the [ device, component, etc ]" are to be interpreted openly as referring to at least one instance of said device, component, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.
Claims (10)
1. A distributed energy storage system secondary frequency modulation control method comprises the following steps:
determining a system frequency state interval of the power system according to the allowable frequency deviation range of the power system;
determining a state interval of the energy storage system;
establishing a reinforcement learning matrix according to the system frequency state interval and the state interval, and determining a reinforcement learning rate;
initializing the state interval;
calculating the reward values of all actions at the next moment according to the updating strategy of the reinforcement learning matrix, and adopting the selection action corresponding to the strategy with the maximum reward value;
acquiring the value of a certain element of the reinforcement learning matrix by using the selection action, and updating the reinforcement learning matrix;
when the reinforcement learning matrix meets the convergence condition, storing the reinforcement learning matrix; and controlling the secondary frequency modulation of the distributed energy storage system by using the stored reinforcement learning matrix.
2. The method of claim 1, the convergence condition of the reinforcement learning matrix is:
when the reinforcement learning matrix has not changed in k cycles, i.e. Qi＝Qi+1＝Qi+2＝…＝Qi+k-1＝Qi+kWherein Q isi、Qi+1、Qi+2、Qi+k-1、Qi+kRespectively are reinforcement learning matrixes obtained by the cycles of i, i +1, i +2, i + k-1 and i + k, wherein Qi、Qi+1、Qi+2、Qi+k-1、Qi+kRespectively are reinforcement learning matrixes obtained by the circulation of the ith, i +1, i +2, i + k-1 and i + k times, and the k value is set according to needs.
3. The method of claim 1, when the reinforcement learning matrix does not satisfy the convergence condition after reaching a preset time, stopping calculating the reward value of all actions at the next moment.
4. The method according to claim 1, further comprising normalizing the reinforcement learning matrix Q by:
wherein QuniFor normalized reinforcement learning matrix Q, QmaxIs the largest element in the reinforcement learning matrix Q.
5. The method of claim 1, wherein when there are a plurality of strategies with the highest reward value, any one of the selection actions is taken.
6. A distributed energy storage system secondary frequency modulation control system, the system comprising:
the system comprises a first initial unit, a second initial unit and a control unit, wherein the first initial unit is used for determining a system frequency state interval of a power system according to an allowable frequency deviation range of the power system;
the second initial unit is used for determining the state interval of the energy storage system;
a third initial unit, configured to establish a reinforcement learning matrix according to the system frequency state interval and the state interval, and determine a reinforcement learning rate;
a fourth initialization unit, configured to initialize the state interval;
the calculation unit is used for calculating the reward values of all actions at the next moment according to the updating strategy of the reinforcement learning matrix and adopting the selection action corresponding to the strategy with the maximum reward value;
the updating unit is used for acquiring the value of a certain element of the reinforcement learning matrix by using the selection action and updating the reinforcement learning matrix;
the control unit is used for storing the reinforcement learning matrix when the reinforcement learning matrix meets a convergence condition; and controlling the secondary frequency modulation of the distributed energy storage system by using the stored reinforcement learning matrix.
7. The system of claim 6, the convergence condition of the reinforcement learning matrix is:
when the reinforcement learning matrix has not changed in k cycles, i.e. Qi＝Qi+1＝Qi+2＝…＝Qi+k-1＝Qi+kWherein Q isi、Qi+1、Qi+2、Qi+k-1、Qi+kRespectively are reinforcement learning matrixes obtained by the cycles of i, i +1, i +2, i + k-1 and i + k, wherein Qi、Qi+1、Qi+2、Qi+k-1、Qi+kRespectively are reinforcement learning matrixes obtained by the circulation of the ith, i +1, i +2, i + k-1 and i + k times, and the k value is set according to needs.
8. The system of claim 6, further comprising a termination unit for stopping calculating the reward value of all actions at the next moment when the reinforcement learning matrix still does not satisfy the convergence condition after reaching the preset time.
9. The system according to claim 6, further comprising a normalization unit for normalizing the reinforcement learning matrix Q, wherein the normalization rule is:
wherein QuniFor normalized reinforcement learning matrix Q, QmaxIs the largest element in the reinforcement learning matrix Q.
10. The method of claim 6, the computing unit to further: when the strategy of the maximum reward value is a plurality of strategies, any one of the selection actions is taken.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010151834.8A CN111224433A (en) | 2020-03-06 | 2020-03-06 | Secondary frequency modulation control method and system for distributed energy storage system |
| PCT/CN2020/131558 WO2021174918A1 (en) | 2020-03-06 | 2020-11-25 | Secondary frequency modulation control method and system for distributed energy storage system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010151834.8A CN111224433A (en) | 2020-03-06 | 2020-03-06 | Secondary frequency modulation control method and system for distributed energy storage system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111224433A true CN111224433A (en) | 2020-06-02 |
Family
ID=70826271
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010151834.8A Pending CN111224433A (en) | 2020-03-06 | 2020-03-06 | Secondary frequency modulation control method and system for distributed energy storage system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111224433A (en) |
| WO (1) | WO2021174918A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112103971A (en) * | 2020-09-01 | 2020-12-18 | 广西大学 | Vector reinforcement learning control method for power grid frequency modulation type flywheel energy storage system |
| WO2021174918A1 (en) * | 2020-03-06 | 2021-09-10 | 国网新源张家口风光储示范电站有限公司 | Secondary frequency modulation control method and system for distributed energy storage system |
| CN114189207A (en) * | 2021-11-19 | 2022-03-15 | 中国科学院电工研究所 | Control method and device for solar controller in light storage system |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113937790B (en) * | 2021-10-12 | 2024-02-06 | 云南电网有限责任公司电力科学研究院 | Matching method for primary frequency modulation and secondary frequency modulation of electrochemical energy storage system |
| CN114709857B (en) * | 2022-05-18 | 2022-09-06 | 华北电力大学 | Independent energy storage power station calling method and system for typical secondary frequency modulation scene |
| CN116131289B (en) * | 2023-02-22 | 2023-12-15 | 上海采日能源科技有限公司 | Frequency modulation control method, apparatus and computer readable storage medium |
| CN118017545B (en) * | 2024-02-21 | 2024-09-24 | 华能山东发电有限公司烟台发电厂 | Power grid frequency modulation optimization method and system based on deep learning and control theory |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105870942A (en) * | 2016-05-18 | 2016-08-17 | 中国电力科学研究院 | Primary frequency regulation additional learning control method based on approximate dynamic programming algorithm |
| CN109193721A (en) * | 2018-09-29 | 2019-01-11 | 华南理工大学 | A kind of electric car charge and discharge policy optimization method based on intensified learning |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7536240B2 (en) * | 2005-07-22 | 2009-05-19 | Ut-Battelle, Llc | Real power regulation for the utility power grid via responsive loads |
| CN103490413B (en) * | 2013-09-27 | 2015-09-02 | 华南理工大学 | A kind of intelligent power generation control method based on intelligent body equalization algorithm |
| CN103904641B (en) * | 2014-03-14 | 2016-05-04 | 华南理工大学 | The micro-electrical network intelligent power generation of isolated island control method based on correlated equilibrium intensified learning |
| CN111224433A (en) * | 2020-03-06 | 2020-06-02 | 中国电力科学研究院有限公司 | Secondary frequency modulation control method and system for distributed energy storage system |
-
2020
- 2020-03-06 CN CN202010151834.8A patent/CN111224433A/en active Pending
- 2020-11-25 WO PCT/CN2020/131558 patent/WO2021174918A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105870942A (en) * | 2016-05-18 | 2016-08-17 | 中国电力科学研究院 | Primary frequency regulation additional learning control method based on approximate dynamic programming algorithm |
| CN109193721A (en) * | 2018-09-29 | 2019-01-11 | 华南理工大学 | A kind of electric car charge and discharge policy optimization method based on intensified learning |
Non-Patent Citations (1)
| Title |
|---|
| 茆美琴等: "基于Q学习的微网二次频率在线自适应控制", 《电力系统自动化》, vol. 39, no. 20, 25 October 2015 (2015-10-25), pages 26 - 31 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021174918A1 (en) * | 2020-03-06 | 2021-09-10 | 国网新源张家口风光储示范电站有限公司 | Secondary frequency modulation control method and system for distributed energy storage system |
| CN112103971A (en) * | 2020-09-01 | 2020-12-18 | 广西大学 | Vector reinforcement learning control method for power grid frequency modulation type flywheel energy storage system |
| CN112103971B (en) * | 2020-09-01 | 2023-07-28 | 广西大学 | Vector reinforcement learning control method of power grid frequency modulation type flywheel energy storage system |
| CN114189207A (en) * | 2021-11-19 | 2022-03-15 | 中国科学院电工研究所 | Control method and device for solar controller in light storage system |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021174918A1 (en) | 2021-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111224433A (en) | Secondary frequency modulation control method and system for distributed energy storage system | |
| US11326579B2 (en) | Adaptive dynamic planning control method and system for energy storage station, and storage medium | |
| CN109799851B (en) | User side load response method based on load cluster temperature regulation and control | |
| CN109617103B (en) | Energy control method and system for gradient utilization energy storage battery of energy storage unit | |
| CN109066743B (en) | Self-adaptive control method and system for multi-machine parallel battery energy storage system | |
| CN112531689B (en) | Source network load storage coordination control capability assessment method and equipment of receiving-end power system | |
| CN117154906B (en) | Wireless charging regulation and control method with refrigeration function | |
| US20230344242A1 (en) | Method for automatic adjustment of power grid operation mode base on reinforcement learning | |
| CN114154790A (en) | Industrial park light storage capacity configuration method based on demand management and flexible load | |
| CN115000994A (en) | Multi-energy storage unit grouping consistency power distribution method | |
| CN115459310A (en) | Hybrid energy storage capacity optimization method and system based on improved variational modal decomposition | |
| CN116454920A (en) | Power distribution network frequency modulation method, device, equipment and storage medium | |
| CN116645089A (en) | Energy storage system double-layer optimal configuration method considering capacity degradation of retired battery | |
| CN117117906B (en) | Hybrid energy storage system participation power grid frequency modulation control method and system | |
| CN111311032B (en) | Micro-grid system capacity optimal configuration method based on sector radar map model | |
| CN112910016A (en) | Frequency modulation control method for power distribution network | |
| CN110266059B (en) | Novel energy supply system optimal configuration method based on triangular comprehensive evaluation | |
| CN115238992B (en) | Coordination optimization method and device for power system source load storage and electronic equipment | |
| CN110729759B (en) | Method and device for determining distributed power supply configuration scheme in micro-grid | |
| CN108233426B (en) | Micro-grid energy control method and device | |
| CN117375026B (en) | Micro-grid frequency modulation system and method with cooperation of super capacitor and battery energy storage | |
| CN111934312B (en) | Cascade utilization reconstruction energy storage system capacity configuration method based on risk defense | |
| CN118228982A (en) | Comprehensive energy system optimization method and device based on market-resource multiple coupling | |
| CN114977338A (en) | Capacity configuration method, device, medium and equipment | |
| CN117039856A (en) | Control method and system of power distribution network, electronic equipment and storage medium |
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: 20200602 |