CN115660385B - Method and device for decomposing and parallelly solving economic operation domain of convex hull of power grid - Google Patents
Method and device for decomposing and parallelly solving economic operation domain of convex hull of power grid Download PDFInfo
- Publication number
- CN115660385B CN115660385B CN202211590666.8A CN202211590666A CN115660385B CN 115660385 B CN115660385 B CN 115660385B CN 202211590666 A CN202211590666 A CN 202211590666A CN 115660385 B CN115660385 B CN 115660385B
- Authority
- CN
- China
- Prior art keywords
- convex hull
- economic operation
- layer optimization
- power grid
- double
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power grid convex hull economic operation domain decomposition parallel solving method and device. Aiming at the problem of new energy consumption, the invention provides a method for solving the decomposition parallel of the convex hull economic operation domain for describing the influence of the uncertainty of the new energy output on the power grid dispatching plan. Firstly, constructing a first double-layer optimization model capable of being solved in parallel, and determining the dimension of the economic operation domain of the convex hull at each moment; then, initializing an initial convex hull containing initial economic operation points at each moment; and finally, constructing a second double-layer optimization model for expanding the top of the convex hull economic operation domain, and providing a double-layer iterative algorithm which can be executed in parallel to obtain the final convex hull economic operation domain. Compared with the traditional serial solving algorithm, the method has higher solving efficiency, and the obtained convex hull economic operation domain can be used for evaluating the safety and the economical efficiency of the operation of the power grid in real time on one hand, and can support intelligent fine scheduling of the power grid and support realization of an automatic cruising technology of the power grid on the other hand.
Description
Technical Field
The invention belongs to the technical field of large power grid refined intelligent scheduling, and particularly relates to a power grid convex hull economic operation domain decomposition parallel solving method and device.
Background
In recent years, excessive emission of greenhouse gases causes global climate change and extreme weather frequency. Therefore, in order to seek a sustainable development route, renewable energy sources need to be developed greatly, and carbon dioxide emission is reduced. However, the carbon emission of the energy industry in the current stage of China accounts for more than 80% of the total national quantity, wherein the carbon emission of the power industry accounts for more than 40% of the total national quantity. Therefore, the carbon emission of the power industry is reduced, the renewable energy consumption is improved, and the realization of the 'double carbon' target can be effectively supported.
In the process of implementing the present invention, the inventor finds that at least the following problems exist in the prior art:
in order to ensure safe and stable operation of the power grid, students in the field of power grid dispatching put forward a power grid security domain concept, but the power grid security domain only characterizes a power grid security operation boundary, and economy is not considered, so that carbon emission is not reduced.
Disclosure of Invention
Aiming at the defects of the prior art, the embodiment of the application aims to draw the economic operation boundary of the power grid on the basis of ensuring the safety of the power grid, and provides a decomposition parallel solving method and device of the economic operation domain of the convex hull of the power grid. On the basis of ensuring the safety of the power grid, new energy is maximally consumed, carbon emission is reduced, and realization of fine intelligent scheduling of a large power grid is supported.
According to a first aspect of an embodiment of the present application, there is provided a method for resolving and parallel solving an economic operation domain of a convex hull of a power grid, which is applied to the power grid, and includes:
constructing a first double-layer optimization model which can be decomposed and executed in parallel and is used for determining a generator number set of economic operation points of the power grid at all times along with the change of the output of the new energy based on a given power grid foundation optimization scheduling model and prediction information of the new energy and the load, and determining the economic operation domain dimension of the convex hull of the power grid at all times based on the constructed first double-layer optimization model;
generating a polyhedral convex hull which meets the calculation precision requirement as small as possible and contains the initial economic operation point at each moment based on a generator number set and a corresponding convex hull economic operation domain dimension of the economic operation point which changes along with the new energy output at each moment, and obtaining a hyperplane set corresponding to the polyhedral convex hull;
constructing a second double-layer optimization model for judging whether the current convex hull already contains all possible economic operation points or not based on a given power grid basic optimization scheduling model, prediction information of new energy and load, the polyhedral convex hull and a hyperplane set thereof, and converting the second double-layer optimization model into a corresponding second single-layer optimization model;
And constructing a double-layer iterative algorithm which can be decomposed and executed in parallel based on the second single-layer optimization model and the rapid convex hull algorithm, and gradually expanding the convex hulls in the polyhedral form at each moment until all economic operation points can be contained, so as to obtain a final convex hull economic operation domain.
Further, based on a given power grid basic optimization scheduling model and prediction information of new energy and load, a first double-layer optimization model which can be decomposed and executed in parallel and is used for determining a generator number set of economic operation points of the power grid at all times along with the change of new energy output is constructed, and the dimension of the convex hull economic operation domain of the power grid at all times is determined based on the constructed first double-layer optimization model, and the method comprises the following steps:
step S11: converting a given grid base optimization scheduling model into an equivalent compact form thereof;
step S12: according to a compact form equivalent to the power grid basic optimization scheduling model, constructing a first double-layer optimization model A and a second double-layer optimization model B which can be decomposed and executed in parallel and are used for determining a generator number set of economic operation points of the power grid at each moment along with the change of new energy output;
step S13: converting the lower layer optimization problem of the first double-layer optimization model into a KKT condition form thereof;
step S14: converting the nonlinear non-convex constraint in the KKT conditional form of the lower-layer optimization problem into a linear mixed integer equivalent form;
Step S15: converting the first double-layer optimization models A and B into first single-layer optimization models C and D according to the KKT conditional form of the lower-layer optimization problem and the linear mixed integer equivalent form of nonlinear non-convex constraint;
step S16: at the position ofTime of day for a generatorSolving the first single-layer optimization model C and the first single-layer optimization model C based on a solverD, numbering the corresponding generators which are not equal to the objective function value of the first single-layer optimization model C and DiAs a generator number set of economic operating points varying with the output of new energyWhereinWill beThe number of generators contained in (a)Is arranged as a power gridThe moment convex hull is economical in terms of the dimension of the run domain.
Further, based on the generator number set and the corresponding convex hull economic operation domain dimension of the economic operation point changing with the new energy output at each moment, generating a polyhedral convex hull containing the initial economic operation point as small as possible and meeting the calculation precision requirement at each moment, and obtaining a hyperplane set corresponding to the polyhedral convex hull, wherein the method comprises the following steps:
step S21: by means oftNew energy unit at momentjIs the predicted force of (2)Solving a power grid foundation optimization scheduling model to obtain the optimal output column vector of each generator at each moment WhereinIn the column vectorIn (3) take outGenerator numbering set with economic operating point changing along with new energy outputThe corresponding active output of the generator is used for obtaining the column vector;
Step S22: initializing a constant as small as possible under the condition of meeting the calculation accuracy requirementIn the followingAt the moment, in sequence in the column vectorAdding a constant to each dimension of (2)ObtainingColumn vectors of linear uncorrelatedWhereinIs atIs the first of (2)iAdding constants to dimensionsThe column vector obtained;
step S23: at the position ofAt the moment of time of day,individual operating pointsIs set of (a)Namely, a small enough polyhedral convex hull containing initial economic operation points is corresponding to the convex hull; obtaining the half-space representation form of the polyhedral convex hull by using a rapid convex hull algorithm, namely a hyperplane set。
Further, based on the given power grid basic optimization scheduling model, the prediction information of new energy and load, the polyhedral convex hull and the hyperplane set thereof, a second double-layer optimization model for judging whether the current convex hull already contains all possible economic operation points is constructed, and the second double-layer optimization model is converted into a corresponding second single-layer optimization model, which comprises the following steps:
s31: based on a given power grid basic optimization scheduling model, prediction information of new energy and load, the polyhedral convex hull and a hyperplane set thereof, a second double-layer optimization model for judging whether the current convex hull already contains all possible economic operation points is constructed as follows:
Objective function:
constraint conditions:
in the method, in the process of the invention,is thattMoment convex hull economic operation domainA hyperplane numbering set in the half-space representation;andrespectively istMoment convex hull economic operation domainNumbered under the half-space representation formIs a super plane of (a)Coefficient column vectors and intercepts of (i) i.e;Is thattTime of day, collectionThe column vector formed by the active power output of the generator,output for schedulable machine setA column vector of components;to output new energyA column vector of components;andrespectively charge power of the energy storage deviceAnd discharge powerA column vector of components;discarding electric power for new energyA column vector of components;to discard load powerA column vector of components;storing electrical energy for an energy storage deviceA column vector of components;、、、、、、anda corresponding coefficient matrix constrained by inequality;、、、、、、andcorresponding coefficient matrixes respectively constrained by equations; superscriptTRepresenting a transpose of the matrix;andcolumn vectors consisting of a lower limit and an upper limit of the predicted output error of the new energy unit are respectively formed;
s32: converting the second two-layer optimization model into a second equivalent single-layer optimization model according to steps S13, S14 and S15 as follows:
objective function:
constraint conditions:
in the method, in the process of the invention,representing the optimal solution result of the second single-layer optimization model, Andcolumn vectors consisting of lagrangian multipliers;representing diagonal elements asIs a diagonal matrix of the (a),i.e.Is a column vector consisting of 0 or 1; m is a sufficiently large constant.
Further, constructing a double-layer iterative algorithm which can be decomposed and executed in parallel based on the second single-layer optimization model and the rapid convex hull algorithm, gradually expanding the polyhedral convex hulls at all times until all economic operation points are contained, and obtaining a final convex hull economic operation domain, wherein the method comprises the following steps:
s41: initialization ofRelevant calculation parameters: setting convergence criterion delta, and inputting an economic operation domain of a convex hull to be solvedNumber of time periods of (a)Fluctuation range data of new energy active output predicted valueAndconvex hull economic operation domain at each momentDimension of (2)Corresponding generator number setHalf-space representation parameters of initial convex hull at each momentAndinitializing each timeIs a hyperplane set of (1)Initializing each timeVertex set of (a),;
S42: solving the expansion vertex of the current convex hull: based on the second monolayer optimization model, pairTime of dayHyperplane, solving and calculating optimization resultObtaining column vectorsAnd update;
S43: updating extended vertices meeting the condition: if it isThen updateThe method comprises the steps of carrying out a first treatment on the surface of the If it is Step S45 is performed;
s44: updating the half-space representation of the current convex hull: based on a fast convex hull algorithm, calculationTime vertex setIs obtained in the form of a half-space representation of (a)And returns to step S42;
s45: outputting a convex hull economic operation domain: output ofTime of dayForm parameters of the half-space representation of (a)Andthereby obtaining the final convex hull economic operation domain。
According to a second aspect of the embodiments of the present application, there is provided a decomposition parallel solving apparatus for a grid convex hull economic operation domain, applied to a grid, including:
the first construction module is used for constructing a first double-layer optimization model which can be decomposed and executed in parallel and is used for determining a generator number set of economic operation points of the power grid at all times along with the change of the output of the new energy based on a given power grid foundation optimization scheduling model and the prediction information of the new energy and the load, and determining the dimension of the economic operation domain of the convex hull of the power grid at all times based on the constructed first double-layer optimization model;
the generation module is used for generating a polyhedral convex hull which meets the calculation precision requirement as small as possible and comprises an initial economic operation point at each moment and obtaining a hyperplane set corresponding to the polyhedral convex hull based on a generator number set of which the economic operation point at each moment changes along with the new energy output and the dimension of the corresponding convex hull economic operation domain;
The second construction module is used for constructing a second double-layer optimization model for judging whether the current convex hull already contains all possible economic operation points or not based on a given power grid foundation optimization scheduling model, prediction information of new energy and load, the polyhedral convex hull and a hyperplane set thereof, and converting the second double-layer optimization model into a corresponding second single-layer optimization model;
and the third construction module is used for constructing a double-layer iterative algorithm which can be decomposed and executed in parallel based on the second single-layer optimization model and the rapid convex hull algorithm, and gradually expanding the polyhedral convex hulls at all times until all economic operation points are contained, so as to obtain a final convex hull economic operation domain.
According to a third aspect of embodiments of the present application, there is provided an electronic device, including:
one or more processors;
a memory for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of the first aspect.
According to a fourth aspect of embodiments of the present application, there is provided a computer readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the steps of the method according to the first aspect.
The technical scheme provided by the embodiment of the application can comprise the following beneficial effects:
according to the embodiment, the power grid convex hull economic operation domain decomposition parallel solving method can decompose the solving process into a plurality of optimization sub-problems which can be executed in parallel, and compared with the original algorithm which can only be solved in series, the algorithm has higher solving efficiency; secondly, the power grid convex hull economic operation domain obtained by the method can be used for evaluating the safety and the economical efficiency of power grid operation in real time; finally, the power grid convex hull economic operation domain obtained by the method is provided with a power grid optimal scheduling plan set, and the power grid convex hull economic operation domain can be combined with a real-time scheduling algorithm based on artificial intelligence to realize high-resolution fine scheduling of a large power grid, so that the method has a good application prospect.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
FIG. 1 is a flow chart illustrating a grid convex hull economic run-domain decomposition parallel solution method, according to an example embodiment.
FIG. 2 is a block diagram illustrating a grid convex hull economic run-domain decomposition parallel solver in accordance with an exemplary embodiment.
Fig. 3 is a schematic diagram of an electronic device, according to an example embodiment.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application.
The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first message may also be referred to as a second message, and similarly, a second message may also be referred to as a first message, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.
FIG. 1 is a flow chart illustrating a method of decomposition parallel solution of a grid convex hull economic run domain, as shown in FIG. 1, according to an exemplary embodiment, the method may include the steps of:
step S1: constructing a first double-layer optimization model which can be decomposed and executed in parallel and is used for determining a generator number set of economic operation points of the power grid at all times along with the change of the output of the new energy based on a given power grid foundation optimization scheduling model and prediction information of the new energy and the load, and determining the economic operation domain dimension of the convex hull of the power grid at all times based on the constructed first double-layer optimization model;
step S2: generating a polyhedral convex hull which meets the calculation precision requirement as small as possible and contains the initial economic operation point at each moment based on a generator number set and a corresponding convex hull economic operation domain dimension of the economic operation point which changes along with the new energy output at each moment, and obtaining a hyperplane set corresponding to the polyhedral convex hull;
step S3: constructing a second double-layer optimization model for judging whether the current convex hull already contains all possible economic operation points or not by utilizing the polyhedral convex hull and the hyperplane set thereof based on a given power grid foundation optimization scheduling model and prediction information of new energy and load, and converting the second double-layer optimization model into a corresponding second single-layer optimization model;
Step S4: and constructing a double-layer iterative algorithm which can be decomposed and executed in parallel based on the second single-layer optimization model and the rapid convex hull algorithm, and gradually expanding the convex hulls in the polyhedral form at each moment until all economic operation points can be contained, so as to obtain a final convex hull economic operation domain.
According to the embodiment, the power grid convex hull economic operation domain decomposition parallel solving method can decompose the solving process into a plurality of optimization sub-problems which can be executed in parallel, and compared with the original algorithm which can only be solved in series, the algorithm has higher solving efficiency; secondly, the power grid convex hull economic operation domain obtained by the method can be used for evaluating the safety and the economical efficiency of power grid operation in real time; finally, the power grid convex hull economic operation domain obtained by the method is provided with a power grid optimal scheduling plan set, and the power grid convex hull economic operation domain can be combined with a real-time scheduling algorithm based on artificial intelligence to realize high-resolution fine scheduling of a large power grid, so that the method has a good application prospect.
In the specific implementation of step S1, based on the given power grid basic optimization scheduling model and the prediction information of the new energy and the load, a first double-layer optimization model which can be decomposed and executed in parallel and is used for determining a generator number set of economic operation points of the power grid varying with the output of the new energy is constructed, and based on the constructed first double-layer optimization model, the dimension of the economic operation domain of the convex hull of the power grid at each moment is determined, including:
Specifically, "economy" in the economic operation domain refers to generalized economy and can generally refer to any given scheduling target such as lowest power generation cost, highest new energy consumption, lowest carbon emission, etc., in the application, the scheduling target function needs to keep the grid base optimization scheduling model convex, and the target function also enables the charge and discharge variables to be [ + ]) On the basis of which the person skilled in the art can set the objective function according to the actual situation. This step may comprise the sub-steps of:
step S11: converting a given grid base optimization scheduling model into an equivalent compact form thereof;
in one embodiment, the grid-based optimal scheduling model is,
objective function:
constraint conditions:
in the method, in the process of the invention,for the number of time periods to be optimally calculated,the number of the schedulable generators;the number of the energy storage devices;is a new energy machineGroup number;is the number of loads;numbering a set for the generator;is thatA set of time periods;is thatA set of time periods;a line numbering set;numbering the new energy unit set;numbering a set for the energy storage device;numbering a set for a load;、andrespectively, generatorsiIs a coefficient of power generation cost; Is thattTime generatoriIs an active force of (a);andrespectively are energy storage devicessCharging and discharging cost coefficients of (a);is thattTime energy storage devicesIs set to the charging power of (a);is thattTime energy storage devicesIs set in the above range;is a new energy unitjA penalty coefficient of the electric power is abandoned;is thattNew energy unit at momentjIs not used for the power supply;is the loadrIs a load rejection penalty coefficient of (1);is thattTime loadrIs used for discarding the load power;andrespectively, generatorsiMinimum and maximum active force of (2);andrespectively, generatorsiMaximum landslide and climbing rate of (a);andrespectively the lineslAn upper transmission power limit of (2);、、andthe power transfer factors of the node branches corresponding to the generator, the new energy, the energy storage and the load are respectively;is thattNew energy unit at momentjIs an active force of (a);is thattTime loadrIs set to be a power demand of the engine;is thattTime energy storage devicesIs used for storing electric quantity;andrespectively are energy storage devicessIs provided;is an energy storage devicesMaximum stored power of (2);is an energy storage devicesIs set to the maximum operating power of (a).
It should be noted that, the objective function (1 a) is an embodiment that uses as much new energy consumed by the lowest possible power generation cost as a scheduling objective, and in a specific implementation, a person skilled in the art may set a corresponding objective function according to an actual scheduling objective requirement, which is not described herein.
For convenience of description, the model is converted into its equivalent compact form, as follows:
objective function:
constraint conditions:
in the method, in the process of the invention,output for schedulable machine setA column vector of components;to output new energyA column vector of components;andrespectively charge power of the energy storage deviceAnd discharge powerA column vector of components;discarding electric power for new energyA column vector of components;to discard load powerA column vector of components;storing electrical energy for an energy storage deviceA column vector of components;、、、、、、anda corresponding coefficient matrix constrained by inequality;、、、、、、andcorresponding coefficient matrixes respectively constrained by equations; superscriptTRepresenting the transpose of the matrix.
Step S12: according to a compact form equivalent to the power grid basic optimization scheduling model, constructing a first double-layer optimization model A and a second double-layer optimization model B which can be decomposed and executed in parallel and are used for determining a generator number set of economic operation points of the power grid at each moment along with the change of new energy output;
specifically, i.e. by judgingAt the position ofWhether the maximum and minimum values of the moment are equal or not is further judged whether the economic operation point of the moment is changed along with the fluctuation of the new energy output, and the first double-layer optimization models A and B are respectively shown as the following (3 a) - (3 d) and (4 a) - (4 d):
objective function:
Constraint conditions:
in the formula, subscript in objective function ""means a collectionAny of (3)iSum setAny of (3)tLater similar subscripts all refer to the same combination meaning;andand respectively predicting column vectors consisting of a lower limit and an upper limit of the output error of the new energy unit.
Objective function:
constraint conditions:
step S13: converting the lower layer optimization problem of the first double-layer optimization model into a KKT condition form thereof;
specifically, since the double-layer optimization problem is a "NP" hard problem and is difficult to solve directly, for the convenience of solving, the lower-layer optimization problems of the double-layer optimization models a and B (corresponding to (3 c), (3 d) and (4 c), (4 d), respectively) are converted into their KKT conditional forms, as shown in (5 a) - (5 i).
In the method, in the process of the invention,andcolumn vectors consisting of lagrangian multipliers;representing diagonal elements asIs a diagonal matrix of (a).
Step S14: converting the nonlinear non-convex constraint in the KKT conditional form of the underlying optimization problem into a linear mixed integer equivalent form:
in the method, in the process of the invention,i.e.Is a column vector consisting of 0 or 1; m is a sufficiently large constant, which is generally preferred。
This step can eliminate the difficult-to-solve nonlinear constraints.
Step S15: the first two-layer optimization models A and B can be converted into first single-layer optimization models C and D according to the KKT conditional form of the lower-layer optimization problem and the linear mixed integer equivalent form of nonlinear non-convex constraint, specifically as (7 a) - (7C) and (8 a) - (8C) respectively,
Objective function:
constraint conditions:
(5a),(5c)~(5i),(6a)~(6b) (7c)
objective function:
constraint conditions:
(5a),(5c)~(5i),(6a)~(6b) (8c)
it should be noted that the first single-layer optimization models C and D are each required to beSolving once, namely all that is needed to be solved respectivelySince each solution does not affect each other, the solution can be decomposed to the following timeAnd the calculation nodes are solved in parallel, so that the solving efficiency is improved.
Step S16: at the position ofTime of day for a generatorSolving the first single-layer optimization models C and D based on a solver respectively, and numbering corresponding generators unequal to objective function values of the first single-layer optimization models C and DiAs a generator number set of economic operating points varying with the output of new energyWhereinWill beThe number of generators contained in (a)Is arranged as electricityNetDimension of economic operation domain of moment convex hull;
in particular, determining an electrical gridThe moment convex hull economic run domain dimension. At the position ofTime of day for a generatorSolving the models C and D based on solvers (gurobi, cplex, etc.), respectively, and numbering the corresponding generators with unequal objective function values of the models C and DiIs denoted as a collection of (2)Wherein. Thus, it can be considered thattTime of day collectionThe economic operating point of the generator can be along with the output of new energy Changes by changes in (a) and (b) a collectionThe economic operation point of the generator is not output along with new energyIs changed by a change in (a). So that the number of the parts to be processed,tonly the set needs to be considered in the moment power grid convex hull economic operation domainThe generator in the inner part can be used for generating electricity,the number of generators contained in (a)Namely, the electric networkThe moment convex hull is economical in terms of the dimension of the run domain.
It should be noted that the number of the substrates,the moment of time of the power grid convex hull economic operation domain is characterized by aggregationIn the power generator. For convenience of description,tsymbol for moment power grid convex hull economic operation domainTo express%Representing both the convex hull economic operation domain in the solving process and the finally obtained convex hull economic operation domain), and introducing a column vectorTo represent convex hull economic run-time domainIs numbered inkEconomical operation point [ ]The economic operation points in the system are innumerable, and the serial numbers are introducedkFor convenience in describing the solution process), column vectorsThe dimension elements are setThe active power output of the generator.
In the specific implementation of the step S2, based on the generator number set of economic operation points at each moment along with the change of new energy output and the dimension of the corresponding convex hull economic operation domain, generating a polyhedron convex hull containing initial economic operation points as small as possible and meeting the calculation precision requirement at each moment, and obtaining a hyperplane set corresponding to the polyhedron convex hull;
In particular, this step may comprise the sub-steps of:
step S21: by means oftNew energy unit at momentjIs the predicted force of (2)Solving the power grid basic optimization scheduling model to obtain the optimal output column vector of each generator at each momentWhereinIn the column vectorIn the process, the generator number set of which the economic operation point is changed along with the output of new energy is taken outThe corresponding active output of the generator is used for obtaining the column vector;
Specifically, an initial operating point for generating an economic operating domain for solving the convex hull is specified, new energy output is specified, a model is solved, and as can be easily seen,namely, the convex hull economic operation domainAn economic operating point in the systemAs a solutiontMoment convex hull economic operation domainIs a starting point of the (c).
Step S22: initializing a constant as small as possible under the condition of meeting the calculation accuracy requirementIn the followingAt the moment, in sequence in the column vectorAdding a constant to each dimension of (2)ObtainingColumn vectors of linear uncorrelatedWhereinIs atIs the first of (2)iAdding constants to dimensionsThe resulting column vector.
Specifically, to generate an initial convex hull at each moment, the column vectors are vertices of the initial convex hull, each vector corresponds to a vertex, and the vertices directly form an initial convex hull, which is one of the representation forms of the convex hulls, namely, the vertex representation.
Step S23: at the position ofAt the moment of time of day,individual operating pointsIs set of (a)Namely, a small enough polyhedral convex hull containing initial economic operation points is corresponding to the convex hull; obtaining the half-space representation form of the polyhedral convex hull by using a rapid convex hull algorithm, namely a hyperplane set。
In particular, with the fast convex hull algorithm, it is these column vectors that are taken as input, another representation of the initial convex hull, i.e. a half-space representation, is obtained. Both representations correspond to the same convex hull.
The solving process of the initial convex hull at each moment is independent and can be decomposed toAnd executing in parallel on the computing nodes.
In the implementation of step S3, based on the given grid basic optimization scheduling model, the prediction information of the new energy and the load, the polyhedral convex hull and the hyperplane set thereof, a second double-layer optimization model for judging whether the current convex hull already contains all possible economic operation points is constructed, and the second double-layer optimization model is converted into a corresponding second single-layer optimization model, which includes:
s31: based on the given power grid basic optimization scheduling model, the prediction information of new energy and load, the polyhedral convex hull and the hyperplane set thereof, a second double-layer optimization model for judging whether the current convex hull already contains all possible economic operation points is constructed,
Specifically, the double-layer optimization model is a criterion for expanding the vertexes of the convex hull economic operation domain, and whether calculation is stopped is judged by judging whether the returned vertexes are close enough to the corresponding hyperplane or not; if the distance from the corresponding hyperplane is far, the vertex is used as an expansion vertex; otherwise, if the distance from the corresponding hyperplane is sufficiently close, the iterative process is stopped. The double-layer optimization model is specifically as follows:
objective function:
constraint conditions:
in the method, in the process of the invention,is thattMoment convex hull economic operation domainHyperplane in a half-space representationA numbering set;andrespectively istMoment convex hull economic operation domainNumbered under the half-space representation formIs a super plane of (a)Coefficient column vectors and intercepts of (i) i.e;Is thattTime of day, collectionThe column vector is composed of the active power output of the generator.
S32: converting the second two-layer optimization model into a second equivalent single-layer optimization model according to steps S13, S14 and S15 as follows:
in particular, the second two-layer optimization model is a "NP" hard problem that is difficult to solve directly. Thus, for ease of solution, the second two-layer optimization model can be converted to an equivalent second single-layer optimization model according to steps S13, S14 and S15, as follows:
Objective function:
constraint conditions:
(5a),(5c)~(5i),(6a)~(6b) (10c)
in the method, in the process of the invention,and representing the optimized solution result of the second single-layer optimization model.
The second single-layer optimization model is described asAll or part of the combinations of (a) are solved, but the solutions of the combinations are relatively independent and can be decomposed to at mostThe solutions are performed in parallel on the individual compute nodes,is thattTime of dayThe number of hyperplanes contained.
In the specific implementation of the step S4, constructing a decomposable parallel-executed double-layer iterative algorithm based on the second single-layer optimization model and the rapid convex hull algorithm, and gradually expanding the polyhedral convex hulls at all times until all economic operation points can be contained, so as to obtain a final convex hull economic operation domain;
in particular, the double-layer iterative algorithm may comprise the sub-steps of:
s41: initializing relevant calculation parameters: setting convergence criterion delta, and inputting an economic operation domain of a convex hull to be solvedNumber of time periods of (a)New energyFluctuation range data of source active output predicted valueAndconvex hull economic operation domain at each momentDimension of (2)Corresponding generator number setHalf-space representation parameters of initial convex hull at each momentAndinitializing each timeIs a hyperplane set of (1)Initializing each time Vertex set of (a),;
S42: solving the expansion vertex of the current convex hull: based on the second monolayer optimization model, pairTime of dayHyperplane, calculation of optimization resultsObtaining column vectorsAnd update;
S43: updating extended vertices meeting the condition: if it isThen updateThe method comprises the steps of carrying out a first treatment on the surface of the If it isStep S45 is performed;
s44: updating the half-space representation of the current convex hull: based on a fast convex hull algorithm, calculationTime vertex setIs obtained in the form of a half-space representation of (a)And returns to step S42;
s45: outputting a convex hull economic operation domain: output ofTime of dayForm parameters of the half-space representation of (a)Andthereby obtaining the final convex hull economic operation domain。
Corresponding to the embodiment of the power grid convex hull economic operation domain decomposition parallel solving method, the application also provides an embodiment of the power grid convex hull economic operation domain decomposition parallel solving device.
FIG. 2 is a block diagram illustrating a grid convex hull economic run-domain decomposition parallel solver according to an exemplary embodiment. Referring to fig. 2, the apparatus may include:
the first construction module 21 is configured to construct a first double-layer optimization model of a generator number set, which is executed in parallel and can be used to determine the economic operation points of the power grid at each moment and changes with the output of the new energy, based on a given power grid base optimization scheduling model and the prediction information of the new energy and the load, and determine the economic operation domain dimension of the convex hull at each moment of the power grid based on the constructed first double-layer optimization model;
The generating module 22 is configured to generate, at each moment, a polyhedral convex hull containing an initial economic operation point as small as possible and that meets a calculation accuracy requirement, based on a generator number set and a corresponding convex hull economic operation domain dimension, where economic operation points at each moment change with new energy output, and obtain a hyperplane set corresponding to the polyhedral convex hull;
the second construction module 23 is configured to construct a second double-layer optimization model for judging whether the current convex hull already contains all possible economic operation points based on the given power grid basic optimization scheduling model, the prediction information of new energy and load, the polyhedral convex hull and the hyperplane set thereof, and convert the second double-layer optimization model into a corresponding second single-layer optimization model;
and a third construction module 24, configured to construct a decomposable parallel-executed double-layer iterative algorithm based on the second single-layer optimization model and the fast convex hull algorithm, and gradually expand the polyhedral convex hulls at each moment until all economic operation points are included, so as to obtain a final convex hull economic operation domain.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purposes of the present application. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
Correspondingly, the application also provides electronic equipment, which comprises: one or more processors; a memory for storing one or more programs; and when the one or more programs are executed by the one or more processors, the one or more processors are enabled to realize the grid convex hull economic operation domain decomposition parallel solving method. As shown in fig. 3, a hardware structure diagram of an apparatus with data processing capability, where the method for resolving and parallel solving a convex hull economic operation domain of a power grid is provided in an embodiment of the present invention, except for a processor, a memory and a network interface shown in fig. 3, the apparatus with data processing capability in the embodiment is generally according to an actual function of the apparatus with data processing capability, and may further include other hardware, which is not described herein.
Correspondingly, the application also provides a computer readable storage medium, wherein computer instructions are stored on the computer readable storage medium, and the instructions realize the grid convex hull economic operation domain decomposition parallel solving method when being executed by a processor. The computer readable storage medium may be an internal storage unit, such as a hard disk or a memory, of any of the data processing enabled devices described in any of the previous embodiments. The computer readable storage medium may also be an external storage device, such as a plug-in hard disk, a Smart Media Card (SMC), an SD Card, a Flash memory Card (Flash Card), or the like, provided on the device. Further, the computer readable storage medium may include both internal storage units and external storage devices of any device having data processing capabilities. The computer readable storage medium is used for storing the computer program and other programs and data required by the arbitrary data processing apparatus, and may also be used for temporarily storing data that has been output or is to be output.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains.
It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof.
Claims (8)
1. The utility model provides a parallel solving method of power grid convex hull economic operation domain decomposition, which is characterized in that the method is applied to a power grid and comprises the following steps:
constructing a first double-layer optimization model which can be decomposed and executed in parallel and is used for determining a generator number set of economic operation points of the power grid at all times along with the change of the output of the new energy based on a given power grid foundation optimization scheduling model and prediction information of the new energy and the load, and determining the economic operation domain dimension of the convex hull of the power grid at all times based on the constructed first double-layer optimization model;
generating a polyhedral convex hull which meets the calculation precision requirement as small as possible and contains the initial economic operation point at each moment based on a generator number set and a corresponding convex hull economic operation domain dimension of the economic operation point which changes along with the new energy output at each moment, and obtaining a hyperplane set corresponding to the polyhedral convex hull;
constructing a second double-layer optimization model for judging whether the current convex hull already contains all possible economic operation points or not based on a given power grid basic optimization scheduling model, prediction information of new energy and load, the polyhedral convex hull and a hyperplane set thereof, and converting the second double-layer optimization model into a corresponding second single-layer optimization model;
And constructing a double-layer iterative algorithm which can be decomposed and executed in parallel based on the second single-layer optimization model and the rapid convex hull algorithm, and gradually expanding the convex hulls in the polyhedral form at each moment until all economic operation points can be contained, so as to obtain a final convex hull economic operation domain.
2. The method of claim 1, wherein constructing a first double-layer optimization model of a generator number set that can be performed in parallel and that is used to determine a change in economic operating point of the grid with the output of the new energy, based on a given grid base optimization scheduling model and prediction information of the new energy and the load, and determining the economic operating domain dimension of the convex hull of the grid at each moment based on the constructed first double-layer optimization model, comprises:
step S11: converting a given grid base optimization scheduling model into an equivalent compact form thereof;
step S12: according to a compact form equivalent to the power grid basic optimization scheduling model, constructing a first double-layer optimization model A and a second double-layer optimization model B which can be decomposed and executed in parallel and are used for determining a generator number set of economic operation points of the power grid at each moment along with the change of new energy output;
step S13: converting the lower layer optimization problem of the first double-layer optimization model into a KKT condition form thereof;
Step S14: converting the nonlinear non-convex constraint in the KKT conditional form of the lower-layer optimization problem into a linear mixed integer equivalent form;
step S15: converting the first double-layer optimization models A and B into first single-layer optimization models C and D according to the KKT conditional form of the lower-layer optimization problem and the linear mixed integer equivalent form of nonlinear non-convex constraint;
step S16: at the position ofTime of day for a generatorSolving the first single-layer optimization models C and D based on a solver respectively, and numbering corresponding generators unequal to objective function values of the first single-layer optimization models C and DiAs a generator number set of economic operating points varying with the output of new energyWhereinWill beThe number of generators contained in (a)Is arranged as a power gridThe moment convex hull is economical in terms of the dimension of the run domain.
3. The method of claim 1, wherein generating as small as possible a polyhedral convex hull containing initial economic operating points at each moment and obtaining a hyperplane set corresponding thereto that meets the calculation accuracy requirement based on the generator number set and the corresponding convex hull economic operating domain dimension of the economic operating points as a function of new energy output at each moment, comprises:
Step S21: by means oftNew energy unit at momentjIs the predicted force of (2)Solving a power grid foundation optimization scheduling model to obtain the optimal output column vector of each generator at each momentWhereinIn the column vectorIn the process, the generator number set of which the economic operation point is changed along with the output of new energy is taken outThe corresponding active output of the generator is used for obtaining the column vector;
Step S22: initializing a constant as small as possible under the condition of meeting the calculation accuracy requirementIn the followingAt the moment, in sequence in the column vectorAdding a constant to each dimension of (2)ObtainingColumn vectors of linear uncorrelatedWhereinIs atIs the first of (2)iAdding constants to dimensionsThe column vector obtained;
step S23: at the position ofAt the moment of time of day,individual operating pointsIs set of (a)Namely, a small enough polyhedral convex hull containing initial economic operation points is corresponding to the convex hull; obtaining the half-space representation form of the polyhedral convex hull by using a rapid convex hull algorithm, namely a hyperplane set。
4. The method of claim 2, wherein constructing a second double-layer optimization model for determining whether the current convex hull already contains all possible economic operating points based on the given grid-based optimization scheduling model, the prediction information of new energy and load, the polyhedral convex hull and the hyperplane set thereof, and converting the second double-layer optimization model into a corresponding second single-layer optimization model, comprises:
S31: based on a given power grid basic optimization scheduling model, prediction information of new energy and load, the polyhedral convex hull and a hyperplane set thereof, a second double-layer optimization model for judging whether the current convex hull already contains all possible economic operation points is constructed as follows:
objective function:
constraint conditions:
in the method, in the process of the invention,is thattMoment convex hull economic operation domainA hyperplane numbering set in the half-space representation;andrespectively istMoment convex hull economic operation domainNumbered under the half-space representation formIs a super plane of (a)Coefficient column vectors and intercepts of (i) i.e;Is thattTime of day, collectionThe column vector formed by the active power output of the generator,output for schedulable machine setA column vector of components;to output new energyA column vector of components;andrespectively charge power of the energy storage deviceAnd discharge powerA column vector of components;discarding electric power for new energyA column vector of components;to discard load powerA column vector of components;storing electrical energy for an energy storage deviceA column vector of components;、、、、、、anda corresponding coefficient matrix constrained by inequality;、、、、、、andcorresponding coefficient matrixes respectively constrained by equations; superscriptTRepresenting a transpose of the matrix;andcolumn vectors consisting of a lower limit and an upper limit of the predicted output error of the new energy unit are respectively formed;
S32: converting the second two-layer optimization model into a second equivalent single-layer optimization model according to steps S13, S14 and S15 as follows:
objective function:
constraint conditions:
in the method, in the process of the invention,representing the optimal solution result of the second single-layer optimization model,andcolumn vectors consisting of lagrangian multipliers;representing diagonal elements asIs a diagonal matrix of the (a),i.e.Is a column vector consisting of 0 or 1; m is a sufficiently large constant.
5. The method of claim 1, wherein constructing a decomposable parallel-executed double-layer iterative algorithm based on the second single-layer optimization model and the fast convex hull algorithm, gradually expanding the polyhedral convex hulls at each moment until all economic operation points can be included, and obtaining a final convex hull economic operation domain, comprises:
s41: initializing relevant calculation parameters: setting convergence criterion delta, and inputting an economic operation domain of a convex hull to be solvedNumber of time periods of (a)Fluctuation range data of new energy active output predicted valueAndconvex hull economic operation domain at each momentDimension of (2)Corresponding generator number setHalf-space representation parameters of initial convex hull at each momentAndinitializing each timeIs a hyperplane set of (1)Initializing each time Vertex set of (a),;
S42: solving the expansion vertex of the current convex hull: based on the second monolayer optimization model, pairTime of dayHyperplane, solving and calculating optimization resultObtaining column vectorsAnd update;
S43: updating extended vertices meeting the condition: if it isThen updateThe method comprises the steps of carrying out a first treatment on the surface of the If it isStep S45 is performed;
s44: updatingHalf-space representation of the current convex hull: based on a fast convex hull algorithm, calculationTime vertex setIs obtained in the form of a half-space representation of (a)And returns to step S42;
6. The utility model provides a power grid convex hull economic operation domain decomposes parallel solution device which characterized in that is applied to in the electric wire netting, includes:
the first construction module is used for constructing a first double-layer optimization model which can be decomposed and executed in parallel and is used for determining a generator number set of economic operation points of the power grid at all times along with the change of the output of the new energy based on a given power grid foundation optimization scheduling model and the prediction information of the new energy and the load, and determining the dimension of the economic operation domain of the convex hull of the power grid at all times based on the constructed first double-layer optimization model;
The generation module is used for generating a polyhedral convex hull which meets the calculation precision requirement as small as possible and comprises an initial economic operation point at each moment and obtaining a hyperplane set corresponding to the polyhedral convex hull based on a generator number set of which the economic operation point at each moment changes along with the new energy output and the dimension of the corresponding convex hull economic operation domain;
the second construction module is used for constructing a second double-layer optimization model for judging whether the current convex hull already contains all possible economic operation points or not based on a given power grid foundation optimization scheduling model, prediction information of new energy and load, the polyhedral convex hull and a hyperplane set thereof, and converting the second double-layer optimization model into a corresponding second single-layer optimization model;
and the third construction module is used for constructing a double-layer iterative algorithm which can be decomposed and executed in parallel based on the second single-layer optimization model and the rapid convex hull algorithm, and gradually expanding the polyhedral convex hulls at all times until all economic operation points are contained, so as to obtain a final convex hull economic operation domain.
7. An electronic device, comprising:
one or more processors;
a memory for storing one or more programs;
The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-5.
8. A computer readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the steps of the method according to any of claims 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211590666.8A CN115660385B (en) | 2022-12-12 | 2022-12-12 | Method and device for decomposing and parallelly solving economic operation domain of convex hull of power grid |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211590666.8A CN115660385B (en) | 2022-12-12 | 2022-12-12 | Method and device for decomposing and parallelly solving economic operation domain of convex hull of power grid |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115660385A CN115660385A (en) | 2023-01-31 |
CN115660385B true CN115660385B (en) | 2023-07-07 |
Family
ID=85019604
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211590666.8A Active CN115660385B (en) | 2022-12-12 | 2022-12-12 | Method and device for decomposing and parallelly solving economic operation domain of convex hull of power grid |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115660385B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116029464B (en) * | 2023-03-28 | 2023-07-18 | 浙江大学 | Acceleration solving method for accurate box-type economic operation domain of power grid |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112381375A (en) * | 2020-11-09 | 2021-02-19 | 浙江大学 | Power grid economic operation domain rapid generation method based on power flow distribution matrix |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020235049A1 (en) * | 2019-05-22 | 2020-11-26 | 日本電気株式会社 | Optimization device, optimization method, and optimization program |
CN113488987B (en) * | 2021-05-17 | 2023-07-14 | 国网浙江杭州市余杭区供电有限公司 | Power grid flexibility operation domain evaluation index calculation method considering source load fluctuation |
CN114662798B (en) * | 2022-05-17 | 2022-09-06 | 浙江大学 | Scheduling method and device based on power grid economic operation domain and electronic equipment |
CN114640138B (en) * | 2022-05-18 | 2022-09-02 | 浙江大学 | Method and device for solving convex hull economic operation domain and electronic equipment |
-
2022
- 2022-12-12 CN CN202211590666.8A patent/CN115660385B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112381375A (en) * | 2020-11-09 | 2021-02-19 | 浙江大学 | Power grid economic operation domain rapid generation method based on power flow distribution matrix |
Also Published As
Publication number | Publication date |
---|---|
CN115660385A (en) | 2023-01-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Alhussan et al. | Green hydrogen production ensemble forecasting based on hybrid dynamic optimization algorithm | |
Khan et al. | Optimal sizing of a stand-alone photovoltaic, wind turbine and fuel cell systems | |
Kumar Khadanga et al. | Frequency control in hybrid distributed power systems via type‐2 fuzzy PID controller | |
CN113890023B (en) | Comprehensive energy micro-grid distributed economic dispatch optimization method and system | |
Zhang et al. | Robust optimization for dynamic economic dispatch under wind power uncertainty with different levels of uncertainty budget | |
Dong et al. | Machine-learning-based real-time economic dispatch in islanding microgrids in a cloud-edge computing environment | |
Chen et al. | Effective load carrying capability evaluation of renewable energy via stochastic long-term hourly based SCUC | |
Zhao et al. | Deep learning based model-free robust load restoration to enhance bulk system resilience with wind power penetration | |
Bornapour et al. | An efficient scenario-based stochastic programming for optimal planning of combined heat, power, and hydrogen production of molten carbonate fuel cell power plants | |
CN113285490B (en) | Power system scheduling method, device, computer equipment and storage medium | |
Song et al. | Optimal parameter extraction of the proton exchange membrane fuel cells based on a new Harris Hawks Optimization algorithm | |
Deepanraj et al. | Intelligent wild geese algorithm with deep learning driven short term load forecasting for sustainable energy management in microgrids | |
Sahoo et al. | Modified Harris Hawks optimization-based fractional-order fuzzy PID controller for frequency regulation of multi-micro-grid | |
Miao et al. | Metamodel based design optimization approach in promoting the performance of proton exchange membrane fuel cells | |
CN115660385B (en) | Method and device for decomposing and parallelly solving economic operation domain of convex hull of power grid | |
CN109687448A (en) | A kind of active power distribution network flexibility appraisal procedure based on uncertain domain | |
CN111509784B (en) | Uncertainty-considered virtual power plant robust output feasible region identification method and device | |
Mumtaz et al. | Adaptive control paradigm for photovoltaic and solid oxide fuel cell in a grid-integrated hybrid renewable energy system | |
Chen et al. | Optimal control strategy for solid oxide fuel cell‐based hybrid energy system using deep reinforcement learning | |
CN117833285A (en) | Micro-grid energy storage optimization scheduling method based on deep reinforcement learning | |
Zhang et al. | Physical-model-free intelligent energy management for a grid-connected hybrid wind-microturbine-PV-EV energy system via deep reinforcement learning approach | |
Zhao et al. | A data‐driven scheduling approach for integrated electricity‐hydrogen system based on improved DDPG | |
Liu et al. | More efficient energy management for hybrid ac/dc microgrids with hard constrained neural network-based conversion loss surrogate models | |
Shi et al. | Day‐ahead optimal dispatching of hybrid power system based on deep reinforcement learning | |
Sun et al. | Optimal Scheduling of Wind-Photovoltaic-Pumped Storage Joint Complementary Power Generation System Based on Improved Firefly Algorithm |
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 |