CN118017562A - Frequency control method, device and equipment for distributed energy storage cluster control - Google Patents

Frequency control method, device and equipment for distributed energy storage cluster control Download PDF

Info

Publication number
CN118017562A
CN118017562A CN202410197747.4A CN202410197747A CN118017562A CN 118017562 A CN118017562 A CN 118017562A CN 202410197747 A CN202410197747 A CN 202410197747A CN 118017562 A CN118017562 A CN 118017562A
Authority
CN
China
Prior art keywords
energy storage
control
current control
frequency
storage cluster
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202410197747.4A
Other languages
Chinese (zh)
Inventor
钟加勇
稂龙亚
陈咏涛
王雪文
高晋
雍明超
崔秋实
刘礼
刘丁豪
郑迪文
张子谦
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Electric Power Research Institute of State Grid Chongqing Electric Power Co Ltd
State Grid Corp of China SGCC
Original Assignee
Electric Power Research Institute of State Grid Chongqing Electric Power Co Ltd
State Grid Corp of China SGCC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Electric Power Research Institute of State Grid Chongqing Electric Power Co Ltd, State Grid Corp of China SGCC filed Critical Electric Power Research Institute of State Grid Chongqing Electric Power Co Ltd
Priority to CN202410197747.4A priority Critical patent/CN118017562A/en
Publication of CN118017562A publication Critical patent/CN118017562A/en
Pending legal-status Critical Current

Links

Classifications

    • 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
    • G06N3/0499—Feedforward networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • H02J3/002—Flicker reduction, e.g. compensation of flicker introduced by non-linear load
    • 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
    • H02J3/241—The oscillation concerning frequency
    • 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
    • H02J3/28—Arrangements for balancing of the load in a network by storage of energy
    • H02J3/32—Arrangements for balancing of the load in a network by storage of energy using batteries with converting means
    • 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
    • H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
    • 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]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Power Engineering (AREA)
  • Data Mining & Analysis (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Nonlinear Science (AREA)
  • Feedback Control In General (AREA)

Abstract

The application discloses a frequency control method, a device and equipment for distributed energy storage cluster control, and relates to the field of power system frequency control; constructing a BP neural network model optimized by an improved particle swarm algorithm; and integrating the BP neural network model optimized by the improved particle swarm algorithm into the system frequency control architecture facing the distributed energy storage cluster to obtain an optimal control law, and completing the frequency control of the power grid system based on the optimal control law. Therefore, the energy storage cluster aggregation control center can comprehensively arrange all clusters so as to ensure the frequency modulation effect; the control law solving method integrated with the improved BP neural network can realize good frequency modulation performance, avoid overshoot, and improve the frequency modulation efficiency and the robustness of frequency control.

Description

Frequency control method, device and equipment for distributed energy storage cluster control
Technical Field
The invention relates to the field of frequency control of power systems, in particular to a frequency control method, a device and equipment for distributed energy storage cluster control.
Background
In order to build a high-efficiency energy system, a large amount of renewable energy sources are widely connected into a power grid. The intermittent and random nature of the new energy generation presents serious challenges to the frequency control of the grid. The distributed energy storage (Distributed Energy Storage, DES) has the advantages of being stable in performance, capable of rapidly responding to system frequency change, capable of solving the problems of long adjustment time consumption and the like of the traditional thermal power generating unit, and having obvious advantages in participating in power grid frequency modulation. Therefore, research on an efficient DES system is one of effective means for solving the problem of insufficient frequency support of a high-permeability new energy power grid.
Currently, research on the frequency modulation of the DES in a power system has a certain research result. The existing technical scheme provides a dynamic DES control strategy of primary frequency modulation, takes the behaviors of all system participants into consideration to construct a frequency control target, and selects an optimal user set by using a multi-armed robber method. According to the existing technical scheme, the energy storage distribution problem is researched by utilizing a combined optimization framework of an enhanced cross entropy method, and the frequency deviation is minimized when the system is in a transient state by solving the optimal distribution of storage units in a power grid. The prior art proposes a virtual synchronous control strategy taking into account the State of charge (SOC) of a battery, wherein a wide area SOC is realized by designing an additional controlled battery related to the SOC of other batteries, so as to further ensure the frequency supporting capability when the system is disturbed. The prior technical scheme provides a coordinated control strategy based on the added sagging control, and when the photovoltaic and the energy storage work simultaneously, the working state and the sagging coefficient of the energy storage unit can be dynamically adjusted to meet the frequency modulation requirement of the system. One existing solution proposes a plurality of DES aggregated primary frequency modulation power allocation strategies, in which a DES aggregate power allocation model is built based on model predictive control to minimize the overall frequency modulation cost of the system.
The method can realize system frequency control to a certain extent, but is limited by the construction cost of the energy storage power station and the imperfection of a control strategy, and the distributed energy storage cluster is still in an exploration stage in actual application. Therefore, how to implement frequency control by using distributed energy storage clusters is a current problem to be solved.
Disclosure of Invention
Accordingly, the present invention is directed to a frequency control method, apparatus and device for distributed energy storage cluster control, which can utilize the distributed energy storage clusters to realize frequency control, thereby improving frequency modulation efficiency and robustness of frequency control. The specific scheme is as follows:
In a first aspect, the application discloses a frequency control method for distributed energy storage cluster control, which comprises the following steps:
constructing a system frequency control architecture oriented to a distributed energy storage cluster;
Constructing a BP neural network model optimized by an improved particle swarm algorithm;
And integrating the BP neural network model optimized by the improved particle swarm algorithm into the system frequency control architecture facing the distributed energy storage cluster to obtain an optimal control law, and completing the frequency control of the power grid system based on the optimal control law.
Optionally, the system frequency control architecture for the distributed energy storage clusters includes a power system dispatching center, an energy storage cluster aggregation control center, a new energy electric field, a traditional electric field, a plurality of new energy generators and a plurality of energy storage clusters, wherein the energy storage cluster aggregation control center, the new energy electric field and the traditional electric field are respectively connected with the power system dispatching center, and the new energy generators and the energy storage clusters are respectively connected with the energy storage cluster aggregation control center.
Optionally, the expression of the hidden layer output of the BP neural network model optimized by the improved particle swarm optimization is:
wherein h i (k) is the output of the hidden layer ith input layer neuron; i is the number of the neuron of the input layer; k is the input sample; is an activation function; j is the hidden layer neuron number; m is the total number of hidden layer neurons; omega ij is the hidden layer weighting coefficient; x k-j is the input of the input sample k at the jth hidden layer neuron; x1 is a reference parameter.
Optionally, the expression of the output layer output of the BP neural network model optimized by the improved particle swarm optimization is:
Wherein o i1 (k) is the output of the i1 st output layer neuron of the output layer; i1 is the output layer neuron number; k is the input sample; g (·) is an activation function that takes a non-negative; Weighting coefficients for the output layer; q is the total number of neurons of the output layer; h i (k) is the output of the hidden layer i-th input layer neuron.
Optionally, the expression of the speed update and the position update of the improved particle swarm algorithm in the BP neural network model optimized by the improved particle swarm algorithm is:
Wherein, An updated value for speed; t is the current iteration number; gamma t is the scale factor; r is a [0,1] random number; Updated values for the locations; p g is the extremum; θ is the inertial weight.
Optionally, integrating the BP neural network model optimized by the improved particle swarm algorithm into the system frequency control architecture facing the distributed energy storage cluster to obtain an optimal control law, and completing the frequency control of the power grid system based on the optimal control law, including:
Integrating the BP neural network model optimized by the improved particle swarm optimization to the energy storage cluster aggregation control center;
Acquiring electric power data of each new energy generator and each energy storage cluster to obtain the mechanical power of the synchronous generator of the current control action;
obtaining disturbance power of the current control action generated based on new energy power of the new energy electric field from the power system dispatching center;
according to the mechanical power of the synchronous generator of the current control action and the disturbance power of the current control action, the energy storage cluster aggregation control center is utilized to obtain the optimal control law;
and realizing the frequency control of each new energy generator and each energy storage cluster according to the optimal control law, and completing the frequency control of the power grid system.
Optionally, the integrating the BP neural network model optimized by the improved particle swarm optimization to the energy storage cluster aggregation control center includes:
The expressions of the system frequency and the cost function of the energy storage cluster aggregation control center are respectively as follows:
f(t′)＝Cx(t′)；
Wherein, Is a system state; A. b and C are coefficient matrixes; x (t') is a state variable of the system; t' is time; u (t') is a state feedback control law; /(I)The energy storage power increment of the front and back control actions is adopted; /(I)A disturbance power increment for the current control action; f (t') is the system frequency; j (x (t')) is the cost function; /(I)Is the inverse of the weight matrix; phi 1 (x (t')) is the activation function; ε (x (t')) is the BP neural network approximation error.
Optionally, the obtaining the optimal control law by using the energy storage cluster aggregation control center according to the mechanical power of the synchronous generator of the current control action and the disturbance power of the current control action includes:
Acquiring the energy storage power of the current control action;
obtaining an estimated value of the frequency deviation of the current control action, an estimated value of the mechanical power increment of the synchronous generator of the current control action and an estimated value of the frequency deviation increment of the current control action by using an observer according to the mechanical power of the synchronous generator of the current control action, the disturbance power of the current control action and the energy storage power of the current control action;
And obtaining the optimal control law by utilizing the BP neural network model optimized by the improved particle swarm algorithm according to the estimated value of the frequency deviation of the current control action, the estimated value of the mechanical power increment of the synchronous generator of the current control action and the estimated value of the frequency deviation increment of the current control action.
Optionally, the obtaining, by using an observer, an estimated value of the frequency deviation of the current control action, an estimated value of the mechanical power increment of the synchronous generator of the current control action, and an estimated value of the frequency deviation increment of the current control action according to the mechanical power of the synchronous generator of the current control action, the disturbance power of the current control action, and the energy storage power of the current control action includes:
Obtaining the frequency deviation of the current control action according to the mechanical power of the synchronous generator of the current control action, the disturbance power of the current control action and the energy storage power of the current control action:
Wherein Δf is the frequency deviation of the current control action; Energy storage power for the current control action; p e is the disturbance power of the current control action; p m is the mechanical power of the synchronous generator of the current control action; h is the generator inertia time constant; s is a Laplace operator; d is a damping coefficient;
obtaining the energy storage power increment of the current control action according to the energy storage power of the current control action;
and obtaining an estimated value of the frequency deviation of the current control action, an estimated value of the mechanical power increment of the synchronous generator of the current control action and an estimated value of the frequency deviation increment of the current control action by using the observer according to the frequency deviation of the current control action and the energy storage power increment of the current control action.
Optionally, the obtaining the optimal control law by using the energy storage cluster aggregation control center includes:
determining the optimal control law based on the cost function of the energy storage cluster aggregation control center;
the expression of the optimal control law is as follows:
wherein u * (t') is the optimal control law; t' is time; r -1 is the inverse of the positive definite symmetry matrix; b T is the transpose of the coefficient matrix; Is a gradient operator; phi 1 T (x (t')) is the transpose of the activation function; x (t') is a state variable of the system; Is a weight matrix.
In a second aspect, the present application discloses a frequency control device for distributed energy storage cluster control, including:
the control architecture construction module is used for constructing a system frequency control architecture oriented to the distributed energy storage cluster;
The model construction module is used for constructing a BP neural network model optimized by the improved particle swarm optimization;
And the frequency control module is used for integrating the BP neural network model optimized by the improved particle swarm algorithm into the system frequency control architecture facing the distributed energy storage cluster to obtain an optimal control law, and completing the frequency control of the power grid system based on the optimal control law.
In a third aspect, the present application discloses an electronic device, comprising:
A memory for storing a computer program;
And the processor is used for executing the computer program to realize the frequency control method facing the distributed energy storage cluster control.
In a fourth aspect, the present application discloses a computer readable storage medium for storing a computer program, where the computer program when executed by a processor implements the foregoing frequency control method for distributed energy storage cluster control.
When the frequency control is carried out, a system frequency control architecture facing the distributed energy storage cluster is firstly constructed; then constructing a BP neural network model optimized by an improved particle swarm algorithm; and integrating the BP neural network model optimized by the improved particle swarm algorithm into the system frequency control architecture facing the distributed energy storage cluster to obtain an optimal control law, and completing the frequency control of the power grid system based on the optimal control law. Therefore, the system frequency control architecture oriented to the distributed energy storage clusters is constructed, and the energy storage clusters are regulated and controlled uniformly through the aggregation control center. Then, a reinforcement learning algorithm controller is designed, and the optimal energy storage power increment is controlled by utilizing the searching frequency of the BP neural network optimized by the improved particle swarm algorithm. And finally, realizing system frequency control by using the control quantity output by the controller. In this way, the energy storage cluster aggregation control center can comprehensively arrange all clusters so as to ensure the frequency modulation effect; the control law solving method integrated with the improved BP neural network can realize good frequency modulation performance, avoid overshoot, and improve the frequency modulation efficiency and the robustness of frequency control.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a system frequency control method for a distributed energy storage cluster according to the present disclosure;
fig. 2 is a schematic diagram of a system frequency control architecture for a distributed energy storage cluster according to the present disclosure;
fig. 3 is a schematic diagram of a distributed energy storage cluster frequency control structure for optimizing a BP neural network based on an improved particle swarm algorithm;
Fig. 4 is a schematic structural diagram of a system frequency control device for a distributed energy storage cluster according to the present disclosure;
Fig. 5 is a block diagram of an electronic device according to the present disclosure.
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.
At present, the existing methods can realize system frequency control to a certain extent, but are limited by the construction cost of the energy storage power station and the imperfection of a control strategy, and the distributed energy storage clusters are still in an exploration stage in actual application. In order to solve the technical problems, the application discloses a frequency control method for distributed energy storage cluster control, which can realize good frequency modulation performance, avoid overshoot and improve frequency modulation efficiency and robustness of frequency control.
Referring to fig. 1, the embodiment of the invention discloses a frequency control method for distributed energy storage cluster control, which comprises the following steps:
s11, constructing a system frequency control architecture oriented to a distributed energy storage cluster;
s12, constructing a BP neural network model optimized by an improved particle swarm algorithm;
and S13, integrating the BP neural network model optimized by the improved particle swarm algorithm into a system frequency control architecture oriented to the distributed energy storage cluster to obtain an optimal control law, and completing the frequency control of the power grid system.
In this embodiment, the system frequency control architecture for distributed energy storage clusters includes a power system dispatching center, an energy storage cluster aggregation control center, a new energy electric field, a traditional electric field, and a plurality of new energy generators and a plurality of energy storage clusters, which are respectively connected with the energy storage cluster aggregation control center.
In this embodiment, as shown in fig. 2, a large number of distributed energy storage clusters are integrated into the power System through the aggregator, and since different distributed energy storage clusters generally have different capacities, charging/discharging efficiencies, soC (System on Chip) levels, and other characteristics, the aggregation control center needs to set a corresponding frequency control method according to these characteristics. The power system dispatching center sends the frequency modulation requirement to a BESS (Battery Energy Storage System ) aggregator control center, and the aggregator center sends the frequency adjustment quantity and ACE (Area Control Error, regional control deviation) duration to the related distributed energy storage clusters, and finally, the power system frequency adjustment is achieved.
BP (Back Propagation) neural networks consist of three layers. The signal is propagated forward, the error is propagated backward, and the expression of the hidden layer output of the BP neural network model optimized by the improved particle swarm algorithm is as follows:
wherein h i (k) is the output of the hidden layer ith input layer neuron; i is the number of the neuron of the input layer; k is the input sample; is an activation function; j is the hidden layer neuron number; m is the total number of hidden layer neurons; omega ij is the hidden layer weighting coefficient; x k-j is the input of the input sample k at the jth hidden layer neuron; x1 is a reference parameter.
The expression of the output layer output of the BP neural network model optimized by the improved particle swarm optimization is as follows:
Wherein o il (k) is the output of the output layer il-th output layer neuron; i1 is the output layer neuron number; k is the input sample; g (·) is an activation function that takes a non-negative; Weighting coefficients for the output layer; q is the total number of neurons of the output layer; h i (k) is the output of the hidden layer i-th input layer neuron.
The BP neural network adopts a descending gradient method to carry out weight optimization and is easy to fall into local optimum, so that an improved particle swarm algorithm (IPSO, internet Protocol for Smart Objects) is adopted to obtain a weight optimum solution. Because PSO (PARTICLE SWARM Optimization ) algorithm has the defects of low search precision, easy premature convergence and the like, the variation thought of genetic algorithm is used for reference, and variation operation is introduced into PSO algorithm to improve the global optimizing capability of PSO. The expression of speed update and position update of the improved particle swarm algorithm in the BP neural network model optimized by the improved particle swarm algorithm is as follows:
Wherein, An updated value for speed; t is the current iteration number; gamma t is the scale factor; r is a [0,1] random number; Updated values for the locations; p g is the extremum; θ is the inertial weight.
In this embodiment, the BP neural network adopts a down gradient method to perform weight optimization, which is easy to fall into local optimization, so that the proposed method adopts an Improved Particle Swarm Optimization (IPSO) to obtain a weight optimal solution, so as to improve the global optimizing capability of the neural network.
In this embodiment, integrating the BP neural network model optimized by the improved particle swarm algorithm into the system frequency control architecture facing the distributed energy storage cluster to obtain an optimal control law, and completing the frequency control of the power grid system based on the optimal control law, including: integrating the BP neural network model optimized by the improved particle swarm optimization to the energy storage cluster aggregation control center; acquiring electric power data of each new energy generator and each energy storage cluster to obtain the mechanical power of the synchronous generator of the current control action; obtaining disturbance power of the current control action generated based on new energy power of the new energy electric field from the power system dispatching center; according to the mechanical power of the synchronous generator of the current control action and the disturbance power of the current control action, the energy storage cluster aggregation control center is utilized to obtain the optimal control law; and realizing the frequency control of each new energy generator and each energy storage cluster according to the optimal control law, and completing the frequency control of the power grid system.
The method for integrating the BP neural network model optimized by the improved particle swarm optimization to the energy storage cluster aggregation control center comprises the following steps: the expressions of the system frequency and the cost function of the energy storage cluster aggregation control center are respectively as follows:
f(t′)＝Cx(t′)；
Wherein, Is a system state; A. b and C are coefficient matrixes; x (t') is a state variable of the system; t' is time; u (t') is a state feedback control law; /(I)The energy storage power increment of the front and back control actions is adopted; /(I)The disturbance power increment of the front control action and the rear control action is adopted; f (t') is the system frequency; j (x (t')) is the cost function; /(I)Is the inverse of the weight matrix; phi 1 (x (t')) is the activation function; ε (x (t')) is the BP neural network approximation error.
In this embodiment, according to the mechanical power of the synchronous generator of the current control action and the disturbance power of the current control action, the energy storage cluster aggregation control center is utilized to obtain the optimal control law, which specifically includes: acquiring the energy storage power of the current control action; obtaining an estimated value of the frequency deviation of the current control action, an estimated value of the mechanical power increment of the synchronous generator of the current control action and an estimated value of the frequency deviation increment of the current control action by using an observer according to the mechanical power of the synchronous generator of the current control action, the disturbance power of the current control action and the energy storage power of the current control action; and obtaining the optimal control law by utilizing the BP neural network model optimized by the improved particle swarm algorithm according to the estimated value of the frequency deviation of the current control action, the estimated value of the mechanical power increment of the synchronous generator of the current control action and the estimated value of the frequency deviation increment of the current control action.
Specifically, according to the mechanical power of the synchronous generator in the current control action, the disturbance power in the current control action and the energy storage power in the current control action, an observer is utilized to obtain an estimated value of the frequency deviation of the current control action, an estimated value of the mechanical power increment of the synchronous generator in the current control action and an estimated value of the frequency deviation increment of the current control action, and the method comprises the following steps: obtaining the frequency deviation of the current control action according to the mechanical power of the synchronous generator of the current control action, the disturbance power of the current control action and the energy storage power of the current control action:
Wherein Δf is the frequency deviation of the current control action; Energy storage power for the current control action; p e is the disturbance power of the current control action; p m is the mechanical power of the synchronous generator of the current control action; h is the generator inertia time constant; s is a Laplace operator; d is a damping coefficient.
Obtaining the energy storage power increment of the current control action according to the energy storage power of the current control action; and obtaining an estimated value of the frequency deviation of the current control action, an estimated value of the mechanical power increment of the synchronous generator of the current control action and an estimated value of the frequency deviation increment of the current control action by using the observer according to the frequency deviation of the current control action and the energy storage power increment of the current control action.
Finally, determining the optimal control law based on the cost function of the energy storage cluster aggregation control center;
the expression of the optimal control law is as follows:
wherein u * (t') is the optimal control law; t' is time; r -1 is the inverse of the positive definite symmetry matrix; b T is the transpose of the coefficient matrix; Is a gradient operator; phi 1 T (x (t')) is the transpose of the activation function; x (t') is a state variable of the system; Is a weight matrix.
In this embodiment, the frequency control structure of the distributed energy storage cluster based on the IPSO-optimized BP neural network is shown in fig. 3, where the distributed energy storage cluster includes a plurality of DESSs (Distributed Energy Storage System ). Wherein the frequency deviation delta f and the energy storage power increment of the front control action and the rear control actionInput as input to an observer to obtain an estimated value f k of frequency deviation and an estimated value/>, of mechanical power increment of the synchronous generator between the front control action and the rear control actionAnd an estimate of the frequency deviation delta, Δf k. After the estimated value is input into the improved BP neural network model, the energy storage power increment which enables the frequency control to be optimal is obtained through optimization control, then the energy storage power reference value is obtained through an integrator, and finally the reference value is input into an energy storage control system, so that the purpose of frequency adjustment is achieved.
As can be seen from the above, when the application performs frequency control, a system frequency control architecture facing the distributed energy storage cluster is constructed first; then constructing a BP neural network model optimized by an improved particle swarm algorithm; and integrating the BP neural network model optimized by the improved particle swarm algorithm into the system frequency control architecture facing the distributed energy storage cluster to obtain an optimal control law, and completing the frequency control of the power grid system based on the optimal control law. Therefore, the system frequency control architecture oriented to the distributed energy storage clusters is constructed, and the energy storage clusters are regulated and controlled uniformly through the aggregation control center. Then, a reinforcement learning algorithm controller is designed, and the optimal energy storage power increment is controlled by utilizing the searching frequency of the BP neural network optimized by the improved particle swarm algorithm. And finally, realizing system frequency control by using the control quantity output by the controller. In this way, the energy storage cluster aggregation control center can comprehensively arrange all clusters so as to ensure the frequency modulation effect; the control law solving method integrated with the improved BP neural network can realize good frequency modulation performance, avoid overshoot, and improve the frequency modulation efficiency and the robustness of frequency control.
In this embodiment, for the frequency control of the power grid system including the distributed energy storage clusters, a state feedback control law u (t) is designed to regulate the power output of the new energy generator and DESCs. For frequency control, the system frequency dynamics is expressed as follows:
f(t′)＝Cx(t′)；
In the method, in the process of the invention, The energy storage power increment of the front and back control actions is adopted; /(I)Generating new energy power such as photovoltaic power, wind power and the like for disturbance power increment; f (t') is the system frequency; A. b, C is a coefficient matrix.
The control law u (t') was designed by minimizing the cost function, expressed as follows:
Wherein U (x (t '), U (t')) is a utility function; u (x (t '), U (t')) =x T(t′)Qx(t′)+uT (t ') Ru (t'), Q, R is a positive definite symmetric matrix with appropriate dimensions.
The optimal cost function is defined as:
Wherein u is a control law; omega c is the set of all control laws.
Based on the principle of the best of bellman, the following can be obtained:
the optimal control law u * (t') satisfies the hamilton-jacobian-bellman equation, namely:
where Θ c is the control set.
Then u * (t) of the system is:
in order to reduce the frequency deviation of the system in the power disturbance process and reduce the energy storage usage in the frequency adjustment process, the existence of weight is assumed So that J (x) is approximated by an improved BP neural network:
wherein epsilon (x) is the approximation error of the neural network; phi 1 (x) is the activation function.
The approximate optimal control law of the system can be obtained by using the BP neural network approximation method.
In this way, the application updates the weight through the IPSO algorithm to obtain the optimal weight, thereby providing a frequency control law for the system.
Referring to fig. 4, an embodiment of the present invention discloses a frequency control device for distributed energy storage cluster control, including:
the control architecture construction module 11 is used for constructing a system frequency control architecture facing the distributed energy storage cluster;
the model construction module 12 is used for constructing a BP neural network model optimized by an improved particle swarm algorithm;
And the frequency control module 13 is used for integrating the BP neural network model optimized by the improved particle swarm algorithm into the system frequency control architecture facing the distributed energy storage cluster to obtain an optimal control law, and completing the frequency control of the power grid system based on the optimal control law.
When the frequency control is carried out, a system frequency control architecture facing the distributed energy storage cluster is firstly constructed; then constructing a BP neural network model optimized by an improved particle swarm algorithm; and integrating the BP neural network model optimized by the improved particle swarm algorithm into the system frequency control architecture facing the distributed energy storage cluster to obtain an optimal control law, and completing the frequency control of the power grid system based on the optimal control law. Therefore, the system frequency control architecture oriented to the distributed energy storage clusters is constructed, and the energy storage clusters are regulated and controlled uniformly through the aggregation control center. Then, a reinforcement learning algorithm controller is designed, and the optimal energy storage power increment is controlled by utilizing the searching frequency of the BP neural network optimized by the improved particle swarm algorithm. And finally, realizing system frequency control by using the control quantity output by the controller. In this way, the energy storage cluster aggregation control center can comprehensively arrange all clusters so as to ensure the frequency modulation effect; the control law solving method integrated with the improved BP neural network can realize good frequency modulation performance, avoid overshoot, and improve the frequency modulation efficiency and the robustness of frequency control.
In some specific embodiments, the model building module 12, specifically for the improved particle swarm optimization, uses the expression of the hidden layer output of the BP neural network model as:
Wherein h i (k) is the output of the hidden layer ith input layer neuron; i is the number of the neuron of the input layer; k is the input sample; /(I) Is an activation function; j is the hidden layer neuron number; m is the total number of hidden layer neurons; omega ij is the hidden layer weighting coefficient; x k-j is the input of the input sample k at the jth hidden layer neuron; x1 is a reference parameter.
In some specific embodiments, the model building module 12, specifically for the output layer output of the BP neural network model optimized by the improved particle swarm algorithm, has the expression: wherein o i1 (k) is the output of the i1 st output layer neuron of the output layer; i1 is the output layer neuron number; k is the input sample; g (·) is an activation function that takes a non-negative; /(I) Weighting coefficients for the output layer; q is the total number of neurons of the output layer; h i (k) is the output of the hidden layer i-th input layer neuron.
In some specific embodiments, the model building module 12, specifically for the improved particle swarm algorithm in the BP neural network model optimized by the improved particle swarm algorithm, has the following expressions: Wherein/> An updated value for speed; t is the current iteration number; gamma t is the scale factor; r is a [0,1] random number; /(I)Updated values for the locations; p g is the extremum; θ is the inertial weight.
In some specific embodiments, the frequency control module 13 is specifically configured to integrate the BP neural network model optimized by the improved particle swarm algorithm into the energy storage cluster aggregation control center; acquiring electric power data of each new energy generator and each energy storage cluster to obtain the mechanical power of the synchronous generator of the current control action; obtaining disturbance power of the current control action generated based on new energy power of the new energy electric field from the power system dispatching center; according to the mechanical power of the synchronous generator of the current control action and the disturbance power of the current control action, the energy storage cluster aggregation control center is utilized to obtain the optimal control law; and realizing the frequency control of each new energy generator and each energy storage cluster according to the optimal control law, and completing the frequency control of the power grid system.
In some specific embodiments, the frequency control module 13 is specifically configured to integrate the expression of the system frequency and the cost function of the energy storage cluster aggregation control center as follows:
f(t′)＝Cx(t′)；
Wherein, Is a system state; A. b and C are coefficient matrixes; x (t') is a state variable of the system; t' is time; u (t') is a state feedback control law; /(I)The energy storage power increment of the front and back control actions is adopted; /(I)A disturbance power increment for the current control action; f (t') is the system frequency; j (x (t')) is the cost function; /(I)Is the inverse of the weight matrix; phi 1 (x (t')) is an activation function; ε (x (t')) is the BP neural network approximation error.
In some specific embodiments, the frequency control module 13 is specifically configured to obtain the stored energy power of the current control action; obtaining an estimated value of the frequency deviation of the current control action, an estimated value of the mechanical power increment of the synchronous generator of the current control action and an estimated value of the frequency deviation increment of the current control action by using an observer according to the mechanical power of the synchronous generator of the current control action, the disturbance power of the current control action and the energy storage power of the current control action; and obtaining the optimal control law by utilizing the BP neural network model optimized by the improved particle swarm algorithm according to the estimated value of the frequency deviation of the current control action, the estimated value of the mechanical power increment of the synchronous generator of the current control action and the estimated value of the frequency deviation increment of the current control action.
In some specific embodiments, the frequency control module 13 is specifically configured to obtain the frequency deviation of the current control action according to the mechanical power of the synchronous generator of the current control action, the disturbance power of the current control action, and the energy storage power of the current control action:
Wherein Δf is the frequency deviation of the current control action; Energy storage power for the current control action; p e is the disturbance power of the current control action; p m is the mechanical power of the synchronous generator of the current control action; h is the generator inertia time constant; s is a Laplace operator; d is a damping coefficient; obtaining the energy storage power increment of the current control action according to the energy storage power of the current control action; and obtaining an estimated value of the frequency deviation of the current control action, an estimated value of the mechanical power increment of the synchronous generator of the current control action and an estimated value of the frequency deviation increment of the current control action by using the observer according to the frequency deviation of the current control action and the energy storage power increment of the current control action.
In some specific embodiments, the frequency control module 13 is specifically configured to determine the optimal control law based on the cost function of the energy storage cluster aggregation control center; the expression of the optimal control law is as follows:
wherein u * (t') is the optimal control law; t' is time; r -1 is the inverse of the positive definite symmetry matrix; b T is the transpose of the coefficient matrix; Is a gradient operator; phi 1 T (x (t')) is the transpose of the activation function; x (t') is a state variable of the system; Is a weight matrix.
Further, the embodiment of the present application further discloses an electronic device, and fig. 5 is a block diagram of an electronic device 20 according to an exemplary embodiment, where the content of the figure is not to be considered as any limitation on the scope of use of the present application.
Fig. 5 is a schematic structural diagram of an electronic device 20 according to an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input output interface 25, and a communication bus 26. The memory 22 is configured to store a computer program, where the computer program is loaded and executed by the processor 21 to implement relevant steps in the frequency control method for distributed energy storage cluster control disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in the present embodiment may be specifically an electronic computer.
In this embodiment, the power supply 23 is configured to provide an operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and an external device, and the communication protocol to be followed is any communication protocol applicable to the technical solution of the present application, which is not specifically limited herein; the input/output interface 25 is used for acquiring external input data or outputting external output data, and the specific interface type thereof may be selected according to the specific application requirement, which is not limited herein.
The memory 22 may be a carrier for storing resources, such as a read-only memory, a random access memory, a magnetic disk, or an optical disk, and the resources stored thereon may include an operating system 221, a computer program 222, and the like, and the storage may be temporary storage or permanent storage.
The operating system 221 is used for managing and controlling various hardware devices on the electronic device 20 and the computer program 222, which may be Windows Server, netware, unix, linux, etc. The computer program 222 may further comprise a computer program capable of performing other specific tasks in addition to the computer program capable of performing the distributed energy storage cluster control oriented frequency control method performed by the electronic device 20 as disclosed in any of the previous embodiments.
Further, the application also discloses a computer readable storage medium for storing a computer program; the frequency control method for distributed energy storage cluster control is realized when the computer program is executed by a processor. For specific steps of the method, reference may be made to the corresponding contents disclosed in the foregoing embodiments, and no further description is given here.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing has outlined rather broadly the more detailed description of the application in order that the detailed description of the application that follows may be better understood, and in order that the present principles and embodiments may be better understood; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.

Claims (12)

1. The frequency control method for distributed energy storage cluster control is characterized by comprising the following steps of:
constructing a system frequency control architecture oriented to a distributed energy storage cluster;
Constructing a BP neural network model optimized by an improved particle swarm algorithm;
And integrating the BP neural network model optimized by the improved particle swarm algorithm into the system frequency control architecture facing the distributed energy storage cluster to obtain an optimal control law, and completing the frequency control of the power grid system based on the optimal control law.
2. The distributed energy storage cluster control-oriented frequency control method according to claim 1, wherein the distributed energy storage cluster-oriented system frequency control architecture comprises a power system dispatching center, an energy storage cluster aggregation control center, a new energy electric field and a traditional electric field, and a plurality of new energy generators and a plurality of energy storage clusters, wherein the energy storage cluster aggregation control center, the new energy electric field and the traditional electric field are respectively connected with the power system dispatching center, and the new energy generators and the energy storage clusters are respectively connected with the energy storage cluster aggregation control center.
3. The frequency control method for distributed energy storage cluster control according to claim 1, wherein the expression of the hidden layer output of the BP neural network model optimized by the improved particle swarm optimization is:
Wherein h i (k) is the output of the hidden layer ith input layer neuron; i is the number of the neuron of the input layer; k is the input sample: is an activation function; j is the hidden layer neuron number; m is the total number of hidden layer neurons; omega ij is the hidden layer weighting coefficient; x k-j is the input of the input sample k at the jth hidden layer neuron; x1 is a reference parameter.
4. The distributed energy storage cluster control-oriented frequency control method according to claim 3, wherein the expression of the output layer output of the BP neural network model optimized by the improved particle swarm optimization is:
Wherein o i1 (k) is the output of the output layer i1 st output layer neuron; i1 is the output layer neuron number; k is the input sample; g (·) is an activation function that takes a non-negative; Weighting coefficients for the output layer; q is the total number of neurons of the output layer; h i (k) is the output of the hidden layer i-th input layer neuron.
5. The method for controlling frequency of distributed energy storage cluster according to claim 4, wherein the expression of speed update and position update of the improved particle swarm algorithm in the BP neural network model optimized by the improved particle swarm algorithm is:
Wherein, An updated value for speed; t is the current iteration number; gamma t is the scale factor; r is a [0,1] random number; /(I)Updated values for the locations; p g is the extremum; θ is the inertial weight.
6. The distributed energy storage cluster control-oriented frequency control method according to claim 2, wherein integrating the BP neural network model optimized by the improved particle swarm algorithm into the distributed energy storage cluster-oriented system frequency control architecture to obtain an optimal control law, and completing the grid system frequency control based on the optimal control law, comprises:
Integrating the BP neural network model optimized by the improved particle swarm optimization to the energy storage cluster aggregation control center;
Acquiring electric power data of each new energy generator and each energy storage cluster to obtain the mechanical power of the synchronous generator of the current control action;
obtaining disturbance power of the current control action generated based on new energy power of the new energy electric field from the power system dispatching center;
according to the mechanical power of the synchronous generator of the current control action and the disturbance power of the current control action, the energy storage cluster aggregation control center is utilized to obtain the optimal control law;
and realizing the frequency control of each new energy generator and each energy storage cluster according to the optimal control law, and completing the frequency control of the power grid system.
7. The distributed energy storage cluster control-oriented frequency control method according to claim 6, wherein integrating the BP neural network model optimized by the improved particle swarm algorithm into the energy storage cluster aggregation control center comprises:
The expressions of the system frequency and the cost function of the energy storage cluster aggregation control center are respectively as follows:
f(t′)＝Cx(t′)；
Wherein, Is a system state; A. b and C are coefficient matrixes; x (t') is a state variable of the system; t' is time; u (t') is a state feedback control law; /(I)The energy storage power increment of the front and back control actions is adopted; /(I)A disturbance power increment for the current control action; f (t') is the system frequency; j (x (t')) is the cost function; /(I)Is the inverse of the weight matrix; phi 1 (x (t')) is the activation function; ε (x (t')) is the BP neural network approximation error.
8. The distributed energy storage cluster control-oriented frequency control method according to claim 6, wherein the obtaining the optimal control law by using the energy storage cluster aggregation control center according to the mechanical power of the synchronous generator of the current control action and the disturbance power of the current control action includes:
Acquiring the energy storage power of the current control action;
obtaining an estimated value of the frequency deviation of the current control action, an estimated value of the mechanical power increment of the synchronous generator of the current control action and an estimated value of the frequency deviation increment of the current control action by using an observer according to the mechanical power of the synchronous generator of the current control action, the disturbance power of the current control action and the energy storage power of the current control action;
And obtaining the optimal control law by utilizing the BP neural network model optimized by the improved particle swarm algorithm according to the estimated value of the frequency deviation of the current control action, the estimated value of the mechanical power increment of the synchronous generator of the current control action and the estimated value of the frequency deviation increment of the current control action.
9. The distributed energy storage cluster control-oriented frequency control method according to claim 8, wherein the obtaining, by using an observer, an estimated value of a frequency deviation of the current control action, an estimated value of a synchronous generator mechanical power increment of the current control action, and an estimated value of a frequency deviation increment of the current control action according to the synchronous generator mechanical power of the current control action, the disturbance power of the current control action, and the energy storage power of the current control action includes:
Obtaining the frequency deviation of the current control action according to the mechanical power of the synchronous generator of the current control action, the disturbance power of the current control action and the energy storage power of the current control action:
Wherein Δf is the frequency deviation of the current control action; Energy storage power for the current control action; p e is the disturbance power of the current control action; p m is the mechanical power of the synchronous generator of the current control action; h is the generator inertia time constant; s is a Laplace operator; d is a damping coefficient;
obtaining the energy storage power increment of the current control action according to the energy storage power of the current control action;
and obtaining an estimated value of the frequency deviation of the current control action, an estimated value of the mechanical power increment of the synchronous generator of the current control action and an estimated value of the frequency deviation increment of the current control action by using the observer according to the frequency deviation of the current control action and the energy storage power increment of the current control action.
10. The method for controlling frequencies for distributed energy storage cluster control according to claim 7, wherein the obtaining the optimal control law by using the energy storage cluster aggregation control center includes:
determining the optimal control law based on the cost function of the energy storage cluster aggregation control center;
the expression of the optimal control law is as follows:
wherein u * (t') is the optimal control law; t' is time; r -1 is the inverse of the positive definite symmetry matrix; b T is the transpose of the coefficient matrix; Is a gradient operator; phi 1 T (x (t')) is the transpose of the activation function; x (t') is a state variable of the system; /(I) Is a weight matrix.
11. A distributed energy storage cluster control oriented frequency control device, comprising:
the control architecture construction module is used for constructing a system frequency control architecture oriented to the distributed energy storage cluster;
The model construction module is used for constructing a BP neural network model optimized by the improved particle swarm optimization;
And the frequency control module is used for integrating the BP neural network model optimized by the improved particle swarm algorithm into the system frequency control architecture facing the distributed energy storage cluster to obtain an optimal control law, and completing the frequency control of the power grid system based on the optimal control law.
12. An electronic device, comprising:
A memory for storing a computer program;
A processor for executing the computer program to implement the distributed energy storage cluster control oriented frequency control method of any one of claims 1 to 10.
CN202410197747.4A 2024-02-22 2024-02-22 Frequency control method, device and equipment for distributed energy storage cluster control Pending CN118017562A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410197747.4A CN118017562A (en) 2024-02-22 2024-02-22 Frequency control method, device and equipment for distributed energy storage cluster control

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410197747.4A CN118017562A (en) 2024-02-22 2024-02-22 Frequency control method, device and equipment for distributed energy storage cluster control

Publications (1)

Publication Number Publication Date
CN118017562A true CN118017562A (en) 2024-05-10

Family

ID=90950112

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410197747.4A Pending CN118017562A (en) 2024-02-22 2024-02-22 Frequency control method, device and equipment for distributed energy storage cluster control

Country Status (1)

Country Link
CN (1) CN118017562A (en)

Similar Documents

Publication Publication Date Title
CN108964050A (en) Micro-capacitance sensor dual-layer optimization dispatching method based on Demand Side Response
CN107732960A (en) Micro-grid energy storage system capacity configuration optimizing method
WO2021242175A1 (en) Method and apparatus for controlling charging and discharging of user-side energy storage device, and storage medium thereof
CN109103912A (en) Consider the industrial park active distribution system method for optimizing scheduling of peaking demand of power grid
CN111144641B (en) Improved particle swarm algorithm-based microgrid optimization scheduling method
WO2022165914A1 (en) Cooperative control method for distributed voltage source converter, and alternating-current/direct-current hybrid microgrid
Zou Design of reactive power optimization control for electromechanical system based on fuzzy particle swarm optimization algorithm
CN111667109A (en) Output control method and device of virtual power plant
CN113595133A (en) Power distribution network-multi-microgrid system based on energy router and scheduling method thereof
CN112202205A (en) Multi-energy three-level autonomous cooperative control method and device
CN117674215A (en) Power distribution method, system, equipment and medium for hybrid energy storage system
Lv et al. Data-based optimal microgrid management for energy trading with integral Q-learning scheme
CN103580051B (en) Consider the wind storage system battery charge state Optimal Control System of part throttle characteristics
Ma et al. Coordinated control of micro-grid based on distributed moving horizon control
Buchibabu et al. Green energy management in DC microgrids enhanced with robust model predictive control and muddled tuna swarm MPPT
CN109687441A (en) A kind of independent micro-capacitance sensor flexibility resource capacity configuration method based on scene decomposition-coordination
Rezk et al. Hydrogen reduction-based energy management strategy of hybrid fuel cell/PV/battery/supercapacitor renewable energy system
CN116865270A (en) Optimal scheduling method and system for flexible interconnection power distribution network containing embedded direct current
CN118017562A (en) Frequency control method, device and equipment for distributed energy storage cluster control
CN116979611A (en) Hierarchical optimization scheduling method for source network load storage
US9742197B2 (en) Power distribution algorithm
US9600010B2 (en) Power distribution algorithm
Yu et al. A fuzzy Q-learning algorithm for storage optimization in islanding microgrid
Korada et al. Energy management strategy for photovoltaic powered hybrid energy storage systems in electric vehicles.
CN113673141A (en) Energy router modeling and optimization control method based on data driving

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