CN112600244B - Photovoltaic power station voltage control method based on neural network - Google Patents

Photovoltaic power station voltage control method based on neural network Download PDF

Info

Publication number
CN112600244B
CN112600244B CN202011434418.5A CN202011434418A CN112600244B CN 112600244 B CN112600244 B CN 112600244B CN 202011434418 A CN202011434418 A CN 202011434418A CN 112600244 B CN112600244 B CN 112600244B
Authority
CN
China
Prior art keywords
voltage
photovoltaic
power
bus
neural network
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011434418.5A
Other languages
Chinese (zh)
Other versions
CN112600244A (en
Inventor
陈之轩
窦春霞
赵昕
马建川
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.)
Jiangsu Paiergao Intelligent Technology Co ltd
Original Assignee
Jiangsu Paiergao Intelligent Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangsu Paiergao Intelligent Technology Co ltd filed Critical Jiangsu Paiergao Intelligent Technology Co ltd
Priority to CN202011434418.5A priority Critical patent/CN112600244B/en
Publication of CN112600244A publication Critical patent/CN112600244A/en
Application granted granted Critical
Publication of CN112600244B publication Critical patent/CN112600244B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • H02J3/381—Dispersed generators
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/12—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network 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
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
    • H02J3/466—Scheduling the operation of the generators, e.g. connecting or disconnecting generators to meet a given demand
    • 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
    • H02J3/38—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
    • H02J3/50—Controlling the sharing of the out-of-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
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/20—The dispersed energy generation being of renewable origin
    • H02J2300/22—The renewable source being solar energy
    • H02J2300/24—The renewable source being solar energy of photovoltaic origin
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/40—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation wherein a plurality of decentralised, dispersed or local energy generation technologies are operated simultaneously
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E10/00—Energy generation through renewable energy sources
    • Y02E10/50—Photovoltaic [PV] energy
    • Y02E10/56—Power conversion systems, e.g. maximum power point trackers

Abstract

The invention discloses a voltage control method of a photovoltaic power station based on a neural network, which comprises the following specific steps: step one: the bus voltage active power neural network and the bus voltage reactive power neural network respectively output sensitivity coefficients of corresponding bus voltage active power and bus voltage reactive power to the model predictive controller; step two: the model predictive controller builds a mathematical model of bus voltage and node injection active power and reactive power through sensitivity coefficients of bus voltage active power and bus voltage reactive power issued by an upper control architecture. The photovoltaic power station voltage control method based on the neural network can solve the overvoltage and undervoltage problems of the photovoltaic power station bus, effectively improves the practicability and expandability of the method based on sensitivity analysis, has important significance for safe operation of a power distribution network, and has important significance for building a boosting energy Internet, improving the power service quality and optimizing and utilizing various resources.

Description

Photovoltaic power station voltage control method based on neural network
Technical Field
The invention relates to the field of voltage regulation of photovoltaic power stations of power distribution networks, in particular to a voltage control method of a photovoltaic power station based on a neural network.
Background
Along with the continuous permeation of new energy in a power distribution network, the traditional power distribution network is gradually developed into an active power distribution network, so that the problems of gradual exhaustion of fossil energy and improvement of environmental friendliness are solved, and meanwhile, a lot of challenges are provided for smooth operation and planning of the power distribution network, a large number of distributed photovoltaics are aggregated in a photovoltaic power station, so that the photovoltaic power station is an important component element in the power distribution network, and has an irreplaceable effect on the stable operation of supporting the load storage of the whole power distribution network, the intermittence and randomness of the distributed photovoltaics can cause fluctuation of the bus voltage of the whole photovoltaic power station, the safety of the whole power distribution network is endangered even the disconnection of the power grid is caused, and the problem of excessive and insufficient voltage of the bus voltage of the photovoltaic power station is effectively solved, so that the photovoltaic power distribution network is an important research direction in the field of the power distribution network;
in the existing photovoltaic power station voltage control method based on the neural network, the topology and network parameters of the system are not easy to obtain in the actual operation of the photovoltaic power station, so that the actual application of the method based on sensitivity analysis has a plurality of difficulties, and the overvoltage and undervoltage problems of the bus of the photovoltaic power station cannot be treated.
Disclosure of Invention
The invention aims to provide a photovoltaic power station voltage control method based on a neural network, which aims to solve the problems that in the prior art, the topology and network parameters of a system are not easy to obtain in the actual operation of a photovoltaic power station, so that the actual application of the method based on sensitivity analysis has a plurality of difficulties and the overvoltage and undervoltage problems of a bus of the photovoltaic power station cannot be processed.
In order to achieve the above purpose, the present invention provides the following technical solutions: a voltage control method of a photovoltaic power station based on a neural network comprises the following specific steps:
step one: the bus voltage active power neural network and the bus voltage reactive power neural network respectively output sensitivity coefficients of corresponding bus voltage active power and bus voltage reactive power to the model predictive controller;
step two: the model predictive controller builds a mathematical model of bus voltage and node injection active power and reactive power through sensitivity coefficients of bus voltage active power and bus voltage reactive power issued by an upper control architecture.
Further, the bus voltage active power neural network and the bus voltage reactive power neural network form an upper control architecture, and the model predictive controller is a component of a lower control architecture;
the bus voltage active power neural network consists of an input layer, a hidden layer and an output layer, wherein the input data of the bus voltage active power neural network input layer comprises active power data of nodes and voltage deviation data of buses, and the output data of the bus voltage active power neural network output layer is a sensitivity coefficient of bus voltage active power of photovoltaic nodes;
further, the active power data of the node may be obtained by the formula (1):
Figure GDA0004131151390000021
in the formula (1), U j And I j The voltage and the current of the jth photovoltaic node are respectively obtained by conjugate operation, re is the real part operation, and the voltage deviation data of the bus can be obtained by the formula (2):
Figure GDA0004131151390000031
in the formula (2), the amino acid sequence of the compound,
Figure GDA0004131151390000032
and->
Figure GDA0004131151390000033
The voltage and the reference voltage value of the ith photovoltaic power station bus are respectively;
further, the reactive power data of the node can be obtained by the formula (3):
Figure GDA0004131151390000034
in formula (3), U j And I j The voltage and the current of the jth photovoltaic node are respectively calculated by conjugate operation and imaginary operation.
Further, the specific steps of obtaining the sensitivity coefficient of the bus voltage active power and the sensitivity coefficient of the bus voltage reactive power are as follows:
step one: the active power data of the photovoltaic node, the voltage deviation data of the bus and the reactive power data of the photovoltaic node obtained through calculation are preprocessed, and the preprocessing modes are respectively shown in formulas (4), (5) and (6):
Figure GDA0004131151390000035
Figure GDA0004131151390000036
Figure GDA0004131151390000037
in the formula (4), P' j And
Figure GDA0004131151390000038
respectively normalizing the active power of the jth photovoltaic node and rated active power; in the formula (5), ->
Figure GDA0004131151390000039
And->
Figure GDA00041311513900000310
Respectively obtaining a voltage deviation normalized value and a maximum value of the voltage deviation of the ith bus; in the formula (6), Q' j And->
Figure GDA00041311513900000311
The reactive power normalized value and the reactive power rated value of the jth photovoltaic node are respectively;
step two: after the active power data of the photovoltaic node, the voltage deviation data of the bus and the reactive power data of the photovoltaic node are preprocessed, the active power data of the photovoltaic node and the voltage deviation data of the bus are used as the input of a bus voltage active power neural network, the reactive power data of the photovoltaic node and the voltage deviation data of the bus are used as the input of the bus voltage reactive power neural network, the active power data of the photovoltaic node, the voltage deviation data of the bus and the voltage deviation data of the bus are respectively input into the corresponding neural network for training, and the weight of the corresponding neural network is corrected according to the formula (7):
Figure GDA0004131151390000041
in the formula (7), E p (k)、w p (k)、Δw p (k) Output error value, weight matrix and weight updating amount in kth weight updating of bus voltage/active power neural network respectively, E q (k)、w q (k)、Δw q (k) Output error value, weight matrix and weight update amount at the kth weight update of the bus voltage/reactive power neural network are respectively:
Figure GDA0004131151390000042
in the formula (8), Y p (k)、Y' p (k) The real value and the actual value of the output quantity during the kth weight updating of the bus voltage/active power neural network are respectively, Y q (k)、Y' q (k) The real value and the actual value of the output quantity are respectively obtained when the kth weight of the busbar voltage/reactive power neural network is updated;
step three: when the errors respectively meet the corresponding conditions, stopping updating the weight matrix, sending the final output quantity to a model prediction controller at the lower layer,
Figure GDA0004131151390000043
in the formula (9), gamma p And gamma q The error threshold values preset for the bus voltage/active power neural network and the bus voltage/reactive power neural network respectively are:
Figure GDA0004131151390000051
further, the model predictive controller solves the corresponding optimal control quantity through real-time rolling optimization, and the objective function of the model predictive controller is composed of a multi-objective optimization function, wherein the multi-objective optimization function specifically comprises two groups of objective functions, one group is to minimize the busbar voltage deviation value of the photovoltaic power station, the other group is to minimize the active control cost of the photovoltaic node, and the first term of the multi-objective optimization function is as shown in a formula (11):
Figure GDA0004131151390000052
in the formula (11), the amino acid sequence of the compound,
Figure GDA0004131151390000053
n is the voltage deviation value of the kth step of the ith bus predicted based on the current moment p And N b Respectively the length of the prediction domain and the total number of the photovoltaic power station buses;
the second term of the objective function of the lower model predictive controller is shown in the formula (12):
Figure GDA0004131151390000054
in the formula (12), F j (k) N for the active control cost of the kth step of the jth photovoltaic node predicted based on the current moment p And N pv Respectively the length of a prediction domain and the total number of photovoltaic nodes of a photovoltaic power station, F j (k) As a quadratic function, as shown in equation (13):
Figure GDA0004131151390000055
in the formula (13), a j 、b j 、c j Active control cost coefficients, Δp, for the jth photovoltaic node, respectively j (k) The active control quantity of the kth step of the jth photovoltaic node predicted based on the current moment;
the objective function of the lower model predictive controller is formed by weighting the objective functions in the formula (11) and the formula (12), specifically shown as the formula (14), and the constraint of the objective function is shown as the formulas (15) - (20):
min(λ 1 ·Obj1+λ 2 ·Obj2) (14)
Figure GDA0004131151390000061
Figure GDA0004131151390000062
Figure GDA0004131151390000063
Figure GDA0004131151390000064
/>
Figure GDA0004131151390000065
Figure GDA0004131151390000066
in the formula (14), lambda 1 、λ 2 Respectively corresponding weight matrix, N c To control domain length; equation (15) and equation (16) represent the climbing constraints of the active power and reactive power of the jth photovoltaic node, respectively, wherein,
Figure GDA0004131151390000067
the method comprises the steps of respectively carrying out climbing upper limit constraint, climbing lower limit constraint, climbing upper limit constraint and climbing lower limit constraint on active power of a jth photovoltaic node; formulae (17) and (18) represent upper and lower output limit constraints of active power and reactive power, respectively, of the jth photovoltaic node, wherein +.>
Figure GDA0004131151390000068
The upper limit constraint, the lower limit constraint, the upper limit constraint and the lower limit constraint of the active power and the reactive power of the jth photovoltaic node are respectively, and P j (t 0 )、Q j (t 0 ) Respectively outputting active power and reactive power of the jth photovoltaic node at the current moment; the formula (19) is the relation between the voltage change of the bus node and the injection of active power and reactive power into each photovoltaic node, wherein ∈>
Figure GDA0004131151390000069
Sensitivity coefficient of active power injection for bus node voltage variation/photovoltaic node, final output from bus voltage/active power neural network in upper control +.>
Figure GDA00041311513900000610
Sensitivity coefficient of reactive power injection for busbar node voltage variation/photovoltaic node, final output from busbar voltage/reactive power neural network in upper control +.>
Figure GDA0004131151390000071
(from formula (10)); formula (20) represents the output active power constraint of the whole photovoltaic power plant, wherein +.>
Figure GDA0004131151390000072
The active power reference output value of the whole photovoltaic power station is from a power grid dispatching center.
Further, the weight matrix of the objective function of the model predictive controller can be changed by the actual value of the photovoltaic power station busbar voltage, and a multi-objective model is controlled by a multi-mode, wherein the multi-mode refers to whether the photovoltaic busbar voltage is in a normal operation range or not.
The multi-mode refers to whether the voltage of the photovoltaic bus is in a normal operation range, and the specific judging method is as follows:
Figure GDA0004131151390000073
in the formula (21), the amino acid sequence of the amino acid,
Figure GDA0004131151390000074
u is the reference voltage value of the ith bus of the photovoltaic power station i (t 0 ) For the actual voltage value of the ith bus of the photovoltaic power station at the current moment, epsilon is the safety margin coefficient of the bus voltage, sig (t 0 ) The mode indication function of the photovoltaic power station is represented by the over/under voltage phenomenon of the photovoltaic power station when the value of the mode indication function is 1, and the normal operation of the photovoltaic power station is represented by the value of the mode indication function is 0. Lambda (lambda) 1 And lambda (lambda) 2 The value of (2) satisfies the following formula:
Figure GDA0004131151390000075
λ 2 ＝I (23)
formula (22) represents that the greater the extent to which the busbar voltage of the photovoltaic power plant exceeds its normal operating range, the corresponding diagonal matrix lambda 1 The larger the element value of (2), the corresponding diagonal matrix lambda if the photovoltaic power plant is operating normally 1 The objective function of the lower model predictive controller is degenerated from multiple objective functions to a single objective function, namely, the optimization objective is to minimize the active output cost of the photovoltaic power station under the normal operation condition, wherein lambda 1 (m) is a diagonal matrix lambda 1 N, N λ1 As a diagonal matrix lambda 1 Is lambda of the dimension of ε Is a weight coefficient; in the formula (23), I is an identity matrix, and the model predicts the objective function of the controller and the constrained passing particle swarm thereofAlgorithm solving and optimizing control quantity of active power and reactive power
Figure GDA0004131151390000081
And->
Figure GDA0004131151390000082
Respectively issued to the corresponding inverter terminal controllers.
Compared with the prior art, the invention has the beneficial effects that: according to the photovoltaic power station voltage control method based on the neural network, rolling optimization is carried out by designing a corresponding objective function, the output reference values of active power and reactive power of the optimal inverter can be solved in real time, the output reference values are further transmitted to the corresponding optical Fu Jiedian inverter, the solved optimal control amounts of the active power and the reactive power are respectively transmitted to the corresponding inverter terminal controller, so that the overvoltage and undervoltage problems of a bus of the photovoltaic power station can be solved, meanwhile, the relation between the voltage change of a photovoltaic node and the injection power is obtained in a data driving mode, the neural network is trained according to historical operation data, the active and reactive sensitivity coefficients of the photovoltaic power station can be obtained, the bus voltage control of the photovoltaic power station is realized, the practicability and the expandability of the method based on sensitivity analysis are effectively improved, and the method has important significance for safe operation of a power distribution network;
the photovoltaic power station voltage control method based on the neural network is characterized in that the neural network for acquiring the sensitivity coefficient is respectively designed based on the data driving thought, the problem that the sensitivity coefficient is difficult to acquire due to difficult measurement of parameters such as impedance in an actual power grid for sensitivity analysis is solved, meanwhile, a model prediction controller under multi-mode switching is designed, multi-objective optimization of the photovoltaic power station under different running conditions is realized, integrated design of safety control-steady state control of the photovoltaic power station is realized, a novel method is provided for busbar voltage regulation of the photovoltaic power station, and the control method has important significance in the aspects of boosting energy Internet construction, realizing national energy development strategy, improving power service quality, optimizing and utilizing various resources and the like.
Drawings
FIG. 1 is a diagram of a bus voltage active power neural network of the present invention;
FIG. 2 is a block diagram of a bus voltage reactive power neural network of the present invention;
fig. 3 is a photovoltaic power plant busbar voltage hierarchical control architecture of the present invention.
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.
Referring to fig. 1-3, the present invention provides a technical solution: a voltage control method of a photovoltaic power station based on a neural network comprises the following specific steps:
step one: the bus voltage active power neural network and the bus voltage reactive power neural network respectively output sensitivity coefficients of corresponding bus voltage active power and bus voltage reactive power to the model predictive controller;
step two: the model predictive controller builds a mathematical model of bus voltage and node injection active power and reactive power through sensitivity coefficients of bus voltage active power and bus voltage reactive power issued by an upper control architecture.
The bus voltage active power neural network and the bus voltage reactive power neural network form an upper control framework, and the model predictive controller is a component part of a lower control framework;
the bus voltage active power neural network consists of an input layer, a hidden layer and an output layer, wherein input data of the bus voltage active power neural network input layer comprises active power data of a node and voltage deviation data of a bus, output data of the bus voltage active power neural network output layer is a sensitivity coefficient of bus voltage active power of a photovoltaic node, and active power data of the node can be obtained through the following steps:
Figure GDA0004131151390000101
in formula (24), U j And I j The voltage and the current of the jth photovoltaic node are respectively represented by the superscript x, the conjugate operation and Re, the real part calculation. The voltage deviation data of the bus bar can be obtained by the formula (2):
Figure GDA0004131151390000102
in the formula (25), the amino acid sequence of the amino acid,
Figure GDA0004131151390000103
and->
Figure GDA0004131151390000104
The voltage of the ith photovoltaic power station bus and the reference voltage value are respectively.
The output data of the bus voltage active power neural network output layer is the sensitivity coefficient of the bus voltage active power of the photovoltaic node.
As shown in fig. 2, the bus voltage reactive power neural network in the upper control architecture is composed of an input layer, a hidden layer and an output layer, the input data of the bus voltage reactive power neural network input layer includes the reactive power data of the node and the voltage deviation data of the bus, and the reactive power data of the node can be obtained by the formula (3):
Figure GDA0004131151390000105
in formula (3), U j And I j The voltage and the current of the jth photovoltaic node are respectively calculated by conjugate operation and imaginary operation.
The output data of the bus voltage reactive power neural network output layer is the sensitivity coefficient of the bus voltage reactive power of the photovoltaic node.
The method comprises the following three steps of:
step one: preprocessing the active power data of the photovoltaic node, the voltage deviation data of the bus and the reactive power data of the photovoltaic node, which are obtained through calculation in the formulas (1), (2) and (3), wherein the preprocessing modes are respectively shown in the formulas (4), (5) and (6):
Figure GDA0004131151390000111
Figure GDA0004131151390000112
Figure GDA0004131151390000113
in the formula (4), P' j And
Figure GDA0004131151390000114
respectively normalizing the active power of the jth photovoltaic node and rated active power; in the formula (5), ->
Figure GDA0004131151390000115
And->
Figure GDA0004131151390000116
Respectively obtaining a voltage deviation normalized value and a maximum value of the voltage deviation of the ith bus; in the formula (6), Q' j And->
Figure GDA0004131151390000117
The reactive power normalized value and the reactive power rated value of the j-th photovoltaic node are respectively.
Step two: after the active power data of the photovoltaic node, the voltage deviation data of the bus and the reactive power data of the photovoltaic node are preprocessed, the active power data of the photovoltaic node and the voltage deviation data of the bus are used as the input of a bus voltage active power neural network, the reactive power data of the photovoltaic node and the voltage deviation data of the bus are used as the input of the bus voltage reactive power neural network, the active power data of the photovoltaic node, the voltage deviation data of the bus and the voltage deviation data of the bus are respectively input into the corresponding neural network for training, and the weight of the corresponding neural network is corrected according to the formula (7):
Figure GDA0004131151390000118
in the formula (7), E p (k)、w p (k)、Δw p (k) Respectively, the output error value, the weight matrix and the weight updating amount in the kth weight updating of the bus voltage active power neural network, E q (k)、w q (k)、Δw q (k) Output error value, weight matrix and weight updating amount when the kth weight of the bus voltage reactive power neural network is updated are respectively:
Figure GDA0004131151390000121
in the formula (8), Y p (k)、Y' p (k) The real value and the actual value of the output quantity when the kth weight of the bus voltage active power neural network is updated are respectively, Y q (k)、Y' q (k) And the real value and the actual value of the output quantity are respectively obtained when the kth weight of the bus voltage reactive power neural network is updated.
Step three: when error E p (k)、E q (k) When the conditions (9) are satisfied, the updating of the weight matrix w is stopped p (k) And w q (k) And the final output quantity
Figure GDA0004131151390000122
And->
Figure GDA0004131151390000123
And sending the data to a model predictive controller.
Figure GDA0004131151390000124
In the formula (10), gamma p And gamma q The error threshold values preset for the bus voltage active power neural network and the bus voltage reactive power neural network respectively are:
Figure GDA0004131151390000125
as shown in fig. 3, the model predictive controller solves the corresponding optimal control quantity through real-time rolling optimization, and the objective function of the model predictive controller is composed of a multi-objective optimization function, wherein the multi-objective optimization function specifically comprises two groups of objective functions, one group is to minimize the busbar voltage deviation value of the photovoltaic power station, the other group is to minimize the active control cost of the photovoltaic node, and as shown in formula (11), the objective function is the first term of the multi-objective optimization function:
Figure GDA0004131151390000131
in the formula (11), the amino acid sequence of the compound,
Figure GDA0004131151390000132
n is the voltage deviation value of the kth step of the ith bus predicted based on the current moment p And N b The predicted domain length and the total number of photovoltaic power plant bus bars, respectively.
The second term of the objective function of the model predictive controller is shown as equation (12):
Figure GDA0004131151390000133
in the formula (12), F j (k) N for the active control cost of the kth step of the jth photovoltaic node predicted based on the current moment p And N pv Respectively the length of a prediction domain and the total number of photovoltaic nodes of a photovoltaic power station, F j (k) Is a secondary letterThe number is shown as a formula (13):
Figure GDA0004131151390000134
in the formula (13), a j 、b j 、c j Active control cost coefficients, Δp, for the jth photovoltaic node, respectively j (k) The active control quantity of the kth step of the jth photovoltaic node predicted based on the current moment.
The objective function of the model predictive controller is formed by weighting the objective functions in the formula (11) and the formula (12), specifically shown in the formula (14), and the constraint is shown in the formulas (15) - (20):
min(λ 1 ·Obj1+λ 2 ·Obj2) (14)
s.t.
Figure GDA0004131151390000135
Figure GDA0004131151390000136
Figure GDA0004131151390000137
Figure GDA0004131151390000138
Figure GDA0004131151390000141
Figure GDA0004131151390000142
in the formula (14), lambda 1 、λ 2 Respectively corresponding weight matrix, N c To control domain length; equation (15) and equation (16) represent the climbing constraints of the active power and reactive power of the jth photovoltaic node, respectively, wherein,
Figure GDA0004131151390000143
the upper limit constraint of the climbing of the active power, the lower limit constraint of the climbing, the upper limit constraint of the climbing of the reactive power and the lower limit constraint of the climbing of the active power of the jth photovoltaic node are respectively shown in the formulas (17) and (18), wherein the formulas (17) and (18) respectively represent the upper limit constraint and the lower limit constraint of the output of the active power and the reactive power of the jth photovoltaic node, and the formula (18) is used for limiting the upper limit and the lower limit constraint of the output of the active power and the reactive power of the jth photovoltaic node, wherein the formula (iii) is used for limiting the upper limit constraint of the climbing of the active power and the lower limit constraint of the reactive power of the jth photovoltaic node>
Figure GDA0004131151390000144
The upper limit constraint, the lower limit constraint, the upper limit constraint and the lower limit constraint of the active power and the reactive power of the jth photovoltaic node are respectively, and P j (t 0 )、Q j (t 0 ) Respectively outputting active power and reactive power of the jth photovoltaic node at the current moment, wherein the formula (19) is the relation between the voltage change of the bus node and the injection of the active power and the reactive power of each photovoltaic node, and the formula (19) is that>
Figure GDA0004131151390000145
Sensitivity coefficient of active power injection for bus node voltage variation photovoltaic node from final output of bus voltage active power neural network in upper control architecture
Figure GDA0004131151390000146
The sensitivity coefficient of injecting reactive power into the photovoltaic node for bus node voltage change comes from the final output quantity of the bus voltage reactive power neural network in the upper control architecture +.>
Figure GDA0004131151390000147
As can be seen from equation (10), equation (20) represents the output active power constraint of the entire photovoltaic power plant, wherein +.>
Figure GDA0004131151390000148
Active power reference transmission for whole photovoltaic power stationAnd outputting the value from a power grid dispatching center.
Weight matrix lambda of objective function of model predictive controller 1 And lambda (lambda) 2 The method can change according to the actual value of the bus voltage of the photovoltaic power station so as to realize multi-target model prediction control under multi-mode switching, wherein the multi-mode refers to whether the voltage of the photovoltaic bus is in a normal operation range or not, and the specific judging method is as follows:
Figure GDA0004131151390000151
in the formula (21), the amino acid sequence of the amino acid,
Figure GDA0004131151390000152
u is the reference voltage value of the ith bus of the photovoltaic power station i (t 0 ) For the actual voltage value of the ith bus of the photovoltaic power station at the current moment, epsilon is the safety margin coefficient of the bus voltage, sig (t 0 ) Is a mode indication function of the photovoltaic power station, when the value is 1, the mode indication function represents that the photovoltaic power station generates an over-under voltage phenomenon, when the value is 0, the mode indication function represents that the photovoltaic power station normally operates, lambda 1 And lambda (lambda) 2 The value of (2) satisfies the following formula:
Figure GDA0004131151390000153
λ 2 ＝I (23)
formula (22) represents that the greater the extent to which the busbar voltage of the photovoltaic power plant exceeds its normal operating range, the corresponding diagonal matrix lambda 1 The larger the element value of (2), the corresponding diagonal matrix lambda if the photovoltaic power plant is operating normally 1 Is an all-zero matrix, the objective function of the model predictive controller is degenerated from a plurality of objective functions to a single objective function, namely, the optimization objective is to minimize the active output cost of the photovoltaic power station under the normal operation condition, wherein lambda 1 (m) is a diagonal matrix lambda 1 Is selected from the group consisting of the m-th element of (c),
Figure GDA0004131151390000154
as a diagonal matrix lambda 1 Is lambda of the dimension of ε Is a weight coefficient; in the formula (23), I is an identity matrix.
The objective function of the model predictive controller and the constraint thereof are solved by a particle swarm algorithm, and the optimal control quantity of the solved active power and reactive power is calculated
Figure GDA0004131151390000155
And->
Figure GDA0004131151390000156
Respectively issued to the corresponding inverter terminal controllers, thereby solving the problem of over-under voltage of the bus of the photovoltaic power station.
Working principle: for the photovoltaic power station voltage control method based on the neural network, firstly, a network model of photovoltaic node voltage change and injection of active and reactive is respectively constructed by utilizing a deep neural network in a data driving mode, the corresponding quantitative relation is excavated, the impedance parameter of a system is not required to be actually measured, the problem that the reactive sensitivity in an actual power grid is difficult to acquire is effectively solved, secondly, a bus voltage control scheme based on model predictive control is designed based on the obtained active and reactive sensitivity coefficients, the optimal inverter is solved in real time through online rolling optimization to output active power and reactive power reference values, thereby providing a feasible, effective and accurate control method for the bus voltage control problem of the photovoltaic power station, and the active power data of the photovoltaic node, the voltage deviation data of the bus and the reactive power data of the photovoltaic node are preprocessed through calculation, preprocessing active power data of a photovoltaic node, voltage deviation data of a bus and reactive power data of the photovoltaic node, taking the active power data of the photovoltaic node and the voltage deviation data of the bus as input of a bus voltage active power neural network, taking the reactive power data of the photovoltaic node and the voltage deviation data of the bus as input of the bus voltage reactive power neural network, respectively inputting the active power data of the photovoltaic node and the voltage deviation data of the bus into corresponding neural networks for training, stopping updating a weight matrix when errors respectively meet corresponding conditions, sending final output quantity to a model predictive controller at the lower layer, obtaining a sensitivity coefficient of active power of line voltage and a sensitivity coefficient of reactive power of bus voltage, solving an objective function of the model predictive controller and constraint of the objective function by a particle swarm algorithm, and the solved optimal control amounts of active power and reactive power are respectively issued to corresponding inverter terminal controllers, so that the overvoltage and undervoltage problems of the photovoltaic power station bus are solved.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (8)

1. A photovoltaic power station voltage control method based on a neural network is characterized by comprising the following steps of: the control method comprises the following specific steps:
step one: the bus voltage active power neural network and the bus voltage reactive power neural network respectively output sensitivity coefficients of corresponding bus voltage active power and bus voltage reactive power to the model predictive controller;
step two: the model prediction controller builds a mathematical model of bus voltage and node injection active power and reactive power through sensitivity coefficients of bus voltage active power and bus voltage reactive power issued by an upper control architecture;
the specific steps of obtaining the sensitivity coefficient of the bus voltage active power and the sensitivity coefficient of the bus voltage reactive power are as follows:
step one: the active power data of the photovoltaic node, the voltage deviation data of the bus and the reactive power data of the photovoltaic node obtained through calculation are preprocessed, and the preprocessing modes are respectively shown in formulas (4), (5) and (6):
Figure FDA0004136113940000011
Figure FDA0004136113940000012
Figure FDA0004136113940000013
in the formula (4), P' j And
Figure FDA0004136113940000014
respectively normalizing the active power of the jth photovoltaic node and rated active power; in the formula (5), ->
Figure FDA0004136113940000015
And->
Figure FDA0004136113940000016
Respectively obtaining a voltage deviation normalized value and a maximum value of the voltage deviation of the ith bus; in the formula (6), Q' j And->
Figure FDA0004136113940000017
The reactive power normalized value and the reactive power rated value of the jth photovoltaic node are respectively;
step two: after the active power data of the photovoltaic node, the voltage deviation data of the bus and the reactive power data of the photovoltaic node are preprocessed, the active power data of the photovoltaic node and the voltage deviation data of the bus are used as the input of a bus voltage active power neural network, the reactive power data of the photovoltaic node and the voltage deviation data of the bus are used as the input of the bus voltage reactive power neural network, the active power data of the photovoltaic node, the voltage deviation data of the bus and the voltage deviation data of the bus are respectively input into the corresponding neural network for training, and the weight of the corresponding neural network is corrected according to the formula (7):
Figure FDA0004136113940000021
in the formula (7), E p (k)、w p (k)、Δw p (k) Output error value, weight matrix and weight updating amount in kth weight updating of bus voltage/active power neural network respectively, E q (k)、w q (k)、Δw q (k) Output error value, weight matrix and weight update amount at the kth weight update of the bus voltage/reactive power neural network are respectively:
Figure FDA0004136113940000022
in the formula (8), Y p (k)、Y′ p (k) The real value and the actual value of the output quantity during the kth weight updating of the bus voltage/active power neural network are respectively, Y q (k)、Y′ q (k) The real value and the actual value of the output quantity are respectively obtained when the kth weight of the busbar voltage/reactive power neural network is updated;
step three: when the errors respectively meet the corresponding conditions, stopping updating the weight matrix, sending the final output quantity to a model prediction controller at the lower layer,
Figure FDA0004136113940000023
in the formula (9), gamma p And gamma q The error threshold values preset for the bus voltage/active power neural network and the bus voltage/reactive power neural network respectively are:
Figure FDA0004136113940000024
2. the photovoltaic power station voltage control method based on the neural network according to claim 1, wherein the method comprises the following steps: the bus voltage active power neural network and the bus voltage reactive power neural network form an upper control architecture, and the model predictive controller is a component part of a lower control architecture;
the bus voltage active power neural network comprises an input layer, a hidden layer and an output layer, wherein input data of the bus voltage active power neural network input layer comprises active power data of nodes and voltage deviation data of buses, and output data of the bus voltage active power neural network output layer is a sensitivity coefficient of bus voltage active power of photovoltaic nodes.
3. The photovoltaic power station voltage control method based on the neural network according to claim 2, wherein: the active power data of the node can be obtained by the formula (1):
Figure FDA0004136113940000025
in the formula (1), U j And I j The voltage and the current of the jth photovoltaic node are respectively obtained by conjugate operation, re is the real part operation, and the voltage deviation data of the bus can be obtained by the formula (2):
Figure FDA0004136113940000031
in the formula (2), the amino acid sequence of the compound,
Figure FDA0004136113940000032
and->
Figure FDA0004136113940000033
The voltage of the ith photovoltaic power station bus and the reference voltage value are respectively.
4. The photovoltaic power station voltage control method based on the neural network according to claim 2, wherein: the reactive power data of the node can be obtained by formula (3):
Figure FDA0004136113940000034
in formula (3), U j And I j The voltage and the current of the jth photovoltaic node are respectively calculated by conjugate operation and imaginary operation.
5. The photovoltaic power station voltage control method based on the neural network according to claim 1, wherein the method comprises the following steps: the model prediction controller solves the corresponding optimal control quantity through real-time rolling optimization, the objective function of the model prediction controller is composed of a multi-objective optimization function, the multi-objective optimization function specifically comprises two groups of objective functions, one group is to minimize the busbar voltage deviation value of the photovoltaic power station, the other group is to minimize the active control cost of the photovoltaic node, and the first term of the multi-objective optimization function is shown as a formula (11):
Figure FDA0004136113940000035
in the formula (11), the amino acid sequence of the compound,
Figure FDA0004136113940000036
n is the voltage deviation value of the kth step of the ith bus predicted based on the current moment p And N b Respectively the length of the prediction domain and the total number of the photovoltaic power station buses; />
The second term of the objective function of the lower model predictive controller is shown in the formula (12):
Figure FDA0004136113940000037
in the formula (12), F j (k) N for the active control cost of the kth step of the jth photovoltaic node predicted based on the current moment p And N pv Respectively the length of a prediction domain and the total number of photovoltaic nodes of a photovoltaic power station, F j (k) As a quadratic function, as shown in equation (13):
Figure FDA0004136113940000038
in the formula (13), a j 、b j 、c j Active control cost coefficients, Δp, for the jth photovoltaic node, respectively j (k) The active control quantity of the kth step of the jth photovoltaic node predicted based on the current moment.
6. The photovoltaic power station voltage control method based on the neural network according to claim 5, wherein the method comprises the following steps: the objective function of the lower model predictive controller is formed by weighting the objective functions in the formula (11) and the formula (12), specifically shown as the formula (14), and the constraint of the objective function is shown as the formulas (15) - (20):
min(λ 1 ·Obj1+λ 2 ·Obj2) (14)
Figure FDA0004136113940000041
Figure FDA0004136113940000042
Figure FDA0004136113940000043
Figure FDA0004136113940000044
Figure FDA0004136113940000045
Figure FDA0004136113940000046
in the formula (14), lambda 1 、λ 2 Respectively corresponding weight matrix, N c To control domain length; equation (15) and equation (16) represent the climbing constraints of the active power and reactive power of the jth photovoltaic node, respectively, wherein,
Figure FDA0004136113940000047
Figure FDA0004136113940000048
the method comprises the steps of respectively carrying out climbing upper limit constraint, climbing lower limit constraint, climbing upper limit constraint and climbing lower limit constraint on active power of a jth photovoltaic node; formulae (17) and (18) represent upper and lower output limit constraints of active power and reactive power, respectively, of the jth photovoltaic node, wherein +.>
Figure FDA0004136113940000049
Figure FDA00041361139400000410
The upper limit constraint, the lower limit constraint, the upper limit constraint and the lower limit constraint of the active power and the reactive power of the jth photovoltaic node are respectively, and P j (t 0 )、Q j (t 0 ) Respectively outputting active power and reactive power of the jth photovoltaic node at the current moment; the formula (19) is the relation between the voltage change of the bus node and the injection of active power and reactive power into each photovoltaic node, wherein ∈>
Figure FDA00041361139400000411
Sensitivity coefficient of active power injection for bus node voltage variation/photovoltaic node, final output from bus voltage/active power neural network in upper control +.>
Figure FDA0004136113940000051
Sensitivity coefficient of reactive power injection for busbar node voltage variation/photovoltaic node, final output from busbar voltage/reactive power neural network in upper control +.>
Figure FDA0004136113940000052
(from formula (10)); formula (20) represents the output active power constraint of the whole photovoltaic power plant, wherein +.>
Figure FDA0004136113940000053
The active power reference output value of the whole photovoltaic power station is from a power grid dispatching center.
7. The photovoltaic power station voltage control method based on the neural network according to claim 1, wherein the method comprises the following steps: the weight matrix of the objective function of the model predictive controller can be changed through the actual value of the photovoltaic power station bus voltage, and a multi-mode control multi-objective model is adopted, wherein the multi-mode refers to whether the photovoltaic bus voltage is in a normal operation range or not.
8. The photovoltaic power station voltage control method based on the neural network according to claim 7, wherein: the multi-mode refers to whether the voltage of the photovoltaic bus is in a normal operation range, and the specific judging method is as follows:
Figure FDA0004136113940000054
in the formula (21), the amino acid sequence of the amino acid,
Figure FDA0004136113940000055
u is the reference voltage value of the ith bus of the photovoltaic power station i (t 0 ) The actual voltage value of the ith bus of the photovoltaic power station at the current moment is epsilon which is the voltage of the busFull margin coefficient, sig (t 0 ) Is a mode indication function of the photovoltaic power station, when the value is 1, the mode indication function represents that the photovoltaic power station generates over/under voltage phenomenon, when the value is 0, the mode indication function represents that the photovoltaic power station normally operates, lambda 1 And lambda (lambda) 2 The value of (2) satisfies the following formula:
Figure FDA0004136113940000056
λ 2 ＝I (23)
formula (22) represents that the greater the extent to which the busbar voltage of the photovoltaic power plant exceeds its normal operating range, the corresponding diagonal matrix lambda 1 The larger the element value of (2), the corresponding diagonal matrix lambda if the photovoltaic power plant is operating normally 1 Is an all-zero matrix, the objective function of the lower model predictive controller is degenerated from multiple objective functions to a single objective function, namely, the optimization objective is to minimize the active output cost of the photovoltaic power station under the normal operation condition, wherein lambda 1 (m) is a diagonal matrix lambda 1 N, N λ1 As a diagonal matrix lambda 1 Is lambda of the dimension of ε Is a weight coefficient; in the formula (23), I is an identity matrix, the objective function of the model predictive controller and the constraint thereof are solved by a particle swarm algorithm, and the optimal control quantity of the solved active power and reactive power is calculated
Figure FDA0004136113940000061
And
Figure FDA0004136113940000062
respectively issued to the corresponding inverter terminal controllers. />
CN202011434418.5A 2020-12-10 2020-12-10 Photovoltaic power station voltage control method based on neural network Active CN112600244B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011434418.5A CN112600244B (en) 2020-12-10 2020-12-10 Photovoltaic power station voltage control method based on neural network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011434418.5A CN112600244B (en) 2020-12-10 2020-12-10 Photovoltaic power station voltage control method based on neural network

Publications (2)

Publication Number Publication Date
CN112600244A CN112600244A (en) 2021-04-02
CN112600244B true CN112600244B (en) 2023-04-28

Family

ID=75191424

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011434418.5A Active CN112600244B (en) 2020-12-10 2020-12-10 Photovoltaic power station voltage control method based on neural network

Country Status (1)

Country Link
CN (1) CN112600244B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114123200B (en) * 2022-01-24 2022-04-12 国网山西省电力公司晋城供电公司 Photovoltaic power station dynamic modeling method based on data driving and storage device
CN115912372B (en) * 2022-11-30 2023-10-03 国网四川省电力公司电力科学研究院 Voltage control method and system for high-proportion distributed photovoltaic access distribution network

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0643948A (en) * 1992-07-27 1994-02-18 Tohoku Electric Power Co Inc Voltage reactive power controller
WO2015081771A1 (en) * 2013-12-06 2015-06-11 国家电网公司 Adaptive emergency control method for voltage security and stability based on synchronous measurement information
CN105281360A (en) * 2015-09-14 2016-01-27 国家电网公司 Distributed photovoltaic automatic generating control method based on sensitivity
CN109462254A (en) * 2018-11-16 2019-03-12 国网辽宁省电力有限公司电力科学研究院 A method of photovoltaic digestion capability is promoted based on voltage sensibility
CN110601252A (en) * 2019-06-18 2019-12-20 武汉大学 MPC-based feeder-level rapid voltage control method for distribution-type photovoltaic power distribution network
CN112018755A (en) * 2020-07-03 2020-12-01 国网浙江省电力有限公司电力科学研究院 Photovoltaic power distribution network reactive voltage prediction method and system based on cyclic neural network

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0643948A (en) * 1992-07-27 1994-02-18 Tohoku Electric Power Co Inc Voltage reactive power controller
WO2015081771A1 (en) * 2013-12-06 2015-06-11 国家电网公司 Adaptive emergency control method for voltage security and stability based on synchronous measurement information
CN105281360A (en) * 2015-09-14 2016-01-27 国家电网公司 Distributed photovoltaic automatic generating control method based on sensitivity
CN109462254A (en) * 2018-11-16 2019-03-12 国网辽宁省电力有限公司电力科学研究院 A method of photovoltaic digestion capability is promoted based on voltage sensibility
CN110601252A (en) * 2019-06-18 2019-12-20 武汉大学 MPC-based feeder-level rapid voltage control method for distribution-type photovoltaic power distribution network
CN112018755A (en) * 2020-07-03 2020-12-01 国网浙江省电力有限公司电力科学研究院 Photovoltaic power distribution network reactive voltage prediction method and system based on cyclic neural network

Also Published As

Publication number Publication date
CN112600244A (en) 2021-04-02

Similar Documents

Publication Publication Date Title
CN106505635B (en) Active scheduling model and scheduling system with minimum wind abandon
CN110782363A (en) AC/DC power distribution network scheduling method considering wind power uncertainty
CN110581571A (en) dynamic optimization scheduling method for active power distribution network
CN112600244B (en) Photovoltaic power station voltage control method based on neural network
CN113313613B (en) Power distribution network modularized movable battery energy storage MMBES optimal configuration method
CN107147146B (en) A kind of distributed energy management solutions optimization method and device based on the more microgrids of joint
CN106058914B (en) The voltage optimization method of distribution power generation Predicting Technique based on Elman algorithms
CN105826944A (en) Method and system for predicting power of microgrid group
CN106026113A (en) Micro-grid system monitoring method having reactive automatic compensation function
CN108711868A (en) It is a kind of meter and islet operation voltage security GA for reactive power optimization planing method
CN111130121A (en) Fuzzy coordination control calculation method for reactive power compensation system of power distribution network in DG and EV environments
Sreejith et al. Optimal location of interline power flow controller in a power system network using ABC algorithm
CN113962159A (en) Method for evaluating maximum photovoltaic access capacity of power distribution network based on reasonable light abandonment
Elgamal et al. Robust multi‐agent system for efficient online energy management and security enforcement in a grid‐connected microgrid with hybrid resources
Reddy et al. Placement of distributed generator, capacitor and DG and capacitor in distribution system for loss reduction and reliability improvement
Chen et al. Real-time volt/var optimization for distribution systems with photovoltaic integration
Akbari-Zadeh et al. Dstatcom allocation in the distribution system considering load uncertainty
Krishnan et al. An efficient DLN2-CRSO approach based dynamic stability enhancement in micro-grid system
CN115133540A (en) Power distribution network model-free real-time voltage control method
Alzaareer et al. Voltage and congestion control in active distribution networks using fast sensitivity analysis
CN113241793A (en) Prevention control method for power system with IPFC (intelligent power flow controller) considering wind power scene
CN112182952A (en) Multi-objective optimization scheduling method for improving elasticity of power system
Arouna et al. Optimal placement of an unified power flow controller in a transmission network by unified non dominated sorting genetic algorithm-III and differential evolution algorithm
CN105811423A (en) Reactive automatic compensation method for microgrid system
Shu et al. A control strategy for battery energy storage smoothing short-term wind power fluctuation based on ANN

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant