Unit commitment acceleration method and system based on adaptive calling neighborhood search, and medium

Abstract

The invention discloses a unit commitment acceleration method and system based on adaptive calling neighborhood search and a medium. The method comprises the following steps: acquiring unit basic data in a power system; constructing a unit combinatorial optimization model based on the obtained unit basic data in the power system; when the unit commitment optimization model to be solved has the characteristic that the relaxation solution of the problem root node and the optimal solution of the problem meet constraint conditions, calling a relaxation enhanced neighborhood search algorithm; and searching a feasible solution based on a relaxation enhanced neighborhood search algorithm, and performing accelerated optimization on a unit combination problem based on the feasible solution to realize optimal scheduling of the power system. According to the method, the RENS is adaptively called, related nodes are fixedly calculated, and particularly expensive cutting planes are forbidden to be calculated when the RENS is used, so that the solving performance of the unit combination problem can be better improved, and stable operation of a power grid system is facilitated.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric power systems, and relates to a unit combination acceleration method, system and medium based on adaptive calling neighborhood search. Background Art

[0002] With the widespread application of new energy and the continuous deepening of power market reform, the unit combination problem of the power system, as a key issue in power optimization and dispatching, has received increasing attention. In today's era, the vigorous development of new energy has brought new opportunities and challenges to the energy field. On the one hand, the widespread access to new energy has brought about a major change in the energy structure of the power system, providing strong support for sustainable development; on the other hand, its intermittent and volatile characteristics have also brought many uncertainties to the stable operation of the power system. At the same time, the continuous advancement of power market reform has led to increasingly fierce competition in the power industry, and has put forward higher requirements for power optimization and dispatching.

[0003] The unit combination problem of the power system involves multiple aspects such as the start-stop decision-making and power allocation of the generator sets, which is directly related to the operating efficiency, reliability and economy of the power system. Due to the high complexity of the actual power system, it not only contains a large number of generator sets, transmission lines and load nodes, but is also affected by various external factors, such as weather changes and energy price fluctuations. Moreover, its uncertainty is strong. Factors such as the uncertainty of the output of new energy and the changes in load demand make it more difficult to efficiently solve the power optimization problem.

[0004] The Relaxed Enhanced Neighborhood Search (RENS) method is often used to find feasible solutions to the original problem to speed up the solution because it can effectively reduce the search space of the mixed integer linear programming problem. This method provides new ideas and approaches to solve complex power optimization problems to a certain extent. However, the solution effect of this method depends on the parameter setting. Different problems often require different parameter combinations to achieve better solution results. This means that when faced with complex and changeable power system problems, the RENS method cannot function stably and it is difficult to meet the needs of stable operation of the power system. Once the solution effect is not good, it may cause problems such as instability and low efficiency in the operation of the power system. Summary of the invention

[0005] The purpose of the present invention is to solve the problem that the relaxed enhanced neighborhood search method in the prior art cannot stably obtain a unit combination optimization solution, and to provide a unit combination acceleration method, system and medium based on adaptive calling neighborhood search.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] The present invention proposes a unit commitment acceleration method based on adaptive calling neighborhood search, comprising:

[0008] Obtain basic data of units in the power system;

[0009] Based on the basic data of units in the power system, a unit combination optimization model is constructed;

[0010] When the relaxed solution of the root node of the unit commitment optimization model to be solved and the optimal solution of the problem meet the constraint conditions, the relaxed enhanced neighborhood search algorithm is called;

[0011] A feasible solution is found based on the relaxed enhanced neighborhood search algorithm, and the unit commitment problem is accelerated based on the feasible solution to achieve optimal dispatch of the power system.

[0012] Preferably, the basic data of the unit includes: the operating cost of the unit, the output data of the unit, the power constraint data of the unit and the day-ahead load forecast data;

[0013] The unit's operating cost, unit output data, unit power constraint data and day-ahead load forecast data are all collected by the power system.

[0014] Preferably, the constructing of the unit commitment optimization model is specifically as follows:

[0015]

[0016] Among them, C x，u and C x，d are the startup cost and shutdown cost of unit x respectively; w x，y and z x，y are the startup state variable and shutdown state variable of unit x in period y, respectively. When unit x performs the startup action at time y, the startup state variable w of unit x in period y x，y is 1, otherwise it is 0; when unit x performs the shutdown action at time y, the shutdown state variable z of unit x in period y x，y is 1, otherwise it is 0; F x (P x，y ) is the cost of unit x in period y; P xy is the power generation of unit x in period y.

[0017] Preferably, if the relaxed solution of the root node of the problem of the unit commitment optimization model to be solved and the optimal solution of the problem do not satisfy the constraint conditions, a simulated annealing algorithm, a genetic algorithm, an ant colony algorithm or a neural network algorithm is called to find a feasible solution for the given optimization problem;

[0018] The constraint condition is that the absolute value of the difference between the optimal solution of the unit combination optimization model and the relaxed solution of the root node of the unit combination optimization model is less than a set threshold.

[0019] Preferably, the method of finding a feasible solution based on a relaxed enhanced neighborhood search algorithm comprises: setting parameters of an adaptively calling relaxed enhanced neighborhood search algorithm, and solving the unit combination optimization model based on the adaptively calling relaxed enhanced neighborhood search algorithm parameters; wherein, setting the parameters of an adaptively calling relaxed enhanced neighborhood search algorithm comprises: limiting the discreteness of sub-integer programming problems, limiting the relaxation scale of the total problem, the number of solution nodes and stagnant nodes, and limiting the cutting plane strength parameters.

[0020] Preferably, the solving of the unit commitment optimization model is specifically as follows: after setting the heuristic parameters, calculating the linear relaxation optimal solution If the integer variables of the original unit combination problem are in the optimal solution If the result is an integer, fix the value of the integer, otherwise set the upper and lower bounds of the integer variable to be decided to and The integer variables of the updated unit combination subproblem are converted to 0-1 variables, and the optimal solution is obtained by solving the subproblem after updating the upper and lower bounds. Output the optimal solution As the initial feasible solution to the original unit combination problem; It means rounding down, that is, the lower bound of the variable; It means rounding up, that is, the upper bound of the variable.

[0021] The present invention proposes a unit commitment acceleration system based on adaptive calling neighborhood search, comprising:

[0022] An acquisition module, wherein the acquisition module acquires basic data of units in the power system;

[0023] A construction module, wherein the construction module constructs a unit combination optimization model based on the acquired basic data of units in the power system;

[0024] A calling module, wherein the calling module calls a relaxed enhanced neighborhood search algorithm when a relaxed solution of a root node of a problem of a unit commitment optimization model to be solved and an optimal solution of the problem satisfy a constraint condition;

[0025] The solution module searches for a feasible solution based on a relaxed enhanced neighborhood search algorithm, and accelerates the optimization of the unit combination problem based on the feasible solution to achieve optimal dispatch of the power system.

[0026] Preferably, the constructing of the unit commitment optimization model is specifically as follows:

[0027]

[0028] Among them, C x，u and C x，dare the startup cost and shutdown cost of unit x respectively; w x，y and z x，y are the startup state variable and shutdown state variable of unit x in period y, respectively. When unit x performs the startup action at time y, the startup state variable w of unit x in period y x，y is 1, otherwise it is 0; when unit x performs the shutdown action at time y, the shutdown state variable z of unit x in period y x，y is 1, otherwise it is 0; F x (P x，y ) is the cost of unit x in period y; P xy is the power generation of unit x in period y.

[0029] Preferably, if the relaxed solution of the root node of the problem of the unit commitment optimization model to be solved and the optimal solution of the problem do not satisfy the constraint conditions, a simulated annealing algorithm, a genetic algorithm, an ant colony algorithm or a neural network algorithm is called to find a feasible solution for the given optimization problem;

[0030] The constraint condition is that the absolute value of the difference between the optimal solution of the unit combination optimization model and the relaxed solution of the root node of the unit combination optimization model is less than a set threshold.

[0031] Preferably, the method of finding a feasible solution based on a relaxed enhanced neighborhood search algorithm comprises: setting parameters of an adaptively calling relaxed enhanced neighborhood search algorithm, and solving the unit combination optimization model based on the adaptively calling relaxed enhanced neighborhood search algorithm parameters; wherein, setting the parameters of an adaptively calling relaxed enhanced neighborhood search algorithm comprises: limiting the discreteness of sub-integer programming problems, limiting the relaxation scale of the total problem, the number of solution nodes and stagnant nodes, and limiting the cutting plane strength parameters.

[0032] Preferably, the solving of the unit commitment optimization model is specifically as follows: after setting the heuristic parameters, calculating the linear relaxation optimal solution If the integer variables of the original unit combination problem are in the optimal solution If the result is an integer, fix the value of the integer, otherwise set the upper and lower bounds of the integer variable to be decided to and The integer variables of the updated unit combination subproblem are converted to 0-1 variables, and the optimal solution is obtained by solving the subproblem after updating the upper and lower bounds. Output the optimal solution As the initial feasible solution to the original unit combination problem; It means rounding down, that is, the lower bound of the variable; It means rounding up, that is, the upper bound of the variable.

[0033] A terminal device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of a unit combination acceleration method based on adaptive calling neighborhood search are implemented.

[0034] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a unit combination acceleration method based on adaptive calling neighborhood search.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The present invention proposes a unit combination acceleration method based on adaptive calling neighborhood search, which constructs a unit combination optimization model according to the basic data of the units in the power system; performs feature recognition on the unit combination optimization model to determine whether to call the relaxed enhanced neighborhood search algorithm; if the relaxed enhanced neighborhood search algorithm is called, the parameters of the adaptive calling relaxed enhanced neighborhood search algorithm are set to solve the unit combination optimization model and obtain a feasible solution to the unit combination problem; based on the feasible solution to the unit combination problem, the unit combination problem is accelerated to optimize. The adaptive calling of the relaxed enhanced neighborhood search algorithm and the use of cutting planes that are particularly expensive to calculate in the present invention can better improve the performance of solving the unit combination problem, which is beneficial to the stable operation of the power grid system.

[0037] The present invention proposes a unit commitment acceleration system based on adaptive calling neighborhood search, which divides the system into an acquisition module, a construction module, a solution module and a call module to obtain the optimization result of the power system unit commitment, thereby realizing unit commitment acceleration. The modularization concept is adopted to make each module independent of each other, which is convenient for unified management of each module. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 The present invention is a flow chart of the unit combination acceleration method based on adaptive calling neighborhood search.

[0040] Figure 2 The schematic diagram of the structure of the unit combination acceleration system based on adaptive calling neighborhood search of the present invention is shown in FIG.

[0041] Figure 3The figure is a schematic structural diagram of an electronic device of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0043] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0045] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0046] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0047] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0048] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0049] Example 1

[0050] The present invention proposes a unit commitment acceleration method based on adaptive calling neighborhood search, such as Figure 1 As shown, including:

[0051] S1: Obtain basic data of units in the power system;

[0052] The basic data of the unit includes: the operating cost of the unit, the output data of the unit, the power constraint data of the unit and the day-ahead load forecast data;

[0053] The unit's operating cost, unit output data, unit power constraint data and day-ahead load forecast data are all collected by the power system.

[0054] S2: Based on the basic data of units in the power system obtained, a unit combination optimization model is constructed;

[0055] The construction of the unit commitment optimization model is specifically as follows:

[0056]

[0057] Among them, C x，u and C x，d are the startup cost and shutdown cost of unit x respectively; w x，y and z x，y are the startup state variable and shutdown state variable of unit x in period y, respectively. When unit x performs the startup action at time y, the startup state variable w of unit x in period y x，y is 1, otherwise it is 0; when unit x performs the shutdown action at time y, the shutdown state variable z of unit x in period y x，y is 1, otherwise it is 0; F x (P x，y ) is the cost of unit x in period y; P xy is the power generation of unit x in period y.

[0058] S3: When the relaxed solution of the root node of the unit commitment optimization model to be solved and the optimal solution of the problem meet the constraint conditions, the relaxed enhanced neighborhood search algorithm is called;

[0059] If the relaxed solution of the root node of the unit combination optimization model to be solved and the optimal solution of the problem do not meet the constraint conditions, the simulated annealing algorithm, genetic algorithm, ant colony algorithm or neural network algorithm is called to find a feasible solution for the given optimization problem;

[0060] The constraint condition is that the absolute value of the difference between the optimal solution of the unit combination optimization model and the relaxed solution of the root node of the unit combination optimization model is less than a set threshold.

[0061] S4: Find feasible solutions based on the relaxed enhanced neighborhood search algorithm, accelerate the optimization of the unit combination problem based on the feasible solutions, and achieve optimal scheduling of the power system.

[0062] The method for finding a feasible solution based on a relaxed enhanced neighborhood search algorithm specifically comprises: setting parameters for adaptively calling the relaxed enhanced neighborhood search algorithm, and solving the unit combination optimization model based on the parameters for adaptively calling the relaxed enhanced neighborhood search algorithm; wherein, setting the parameters for adaptively calling the relaxed enhanced neighborhood search algorithm comprises: limiting the discreteness of the sub-integer programming problem, limiting the relaxation scale of the total problem, the number of solution nodes and stagnant nodes, and limiting the cutting plane strength parameters.

[0063] The unit combination optimization model is solved by: after setting the heuristic parameters, the linear relaxation optimal solution is calculated. If the integer variables of the original unit combination problem are in the optimal solution If the result is an integer, fix the value of the integer, otherwise set the upper and lower bounds of the integer variable to be decided to and The integer variables of the updated unit combination subproblem are converted to 0-1 variables, and the optimal solution is obtained by solving the subproblem after updating the upper and lower bounds. Output the optimal solution As the initial feasible solution to the original unit combination problem; It means rounding down, that is, the lower bound of the variable; It means rounding up, that is, the upper bound of the variable.

[0064] The present invention discloses a unit combination acceleration method based on adaptive calling neighborhood search, which improves the solution performance by combining the problem characteristics, adaptively calling RENS (calling level, number of times, etc.), fixing calculation-related nodes, and disabling cutting planes that are particularly expensive to calculate when using RENS.

[0065] The idea of ​​the RENS algorithm is to define a sub-MIP that optimizes the relaxed optimal solution This is done by fixing the This is done by rounding all integer variables in the solution to integer values. For the remaining integer variables, the bounds are tightened to the two nearest integer values. If a sub-MIP is solved using a linear outer approximation, its dual bound will usually be improved, since the reduced domain will produce a stronger linear relaxation and a tighter underestimation. Since the sub-MIP is solved entirely by the relaxation definition, so the process is called relaxed forced neighborhood search or rens for short.

[0066] In this process, a certain feature recognition function is performed for the problem examples to be solved. That is, when the root node is close to the actual MIP solution, the RENS method can be well referenced. At the same time, the intensity of the RENS algorithm is added, that is, for this type of example, it is determined whether to use the RENS algorithm, and certain parameters are set to adjust the intensity of using this algorithm, so as to better control the corresponding number of nodes and cutting plane intensity. Combined with other heuristic methods of COPT, a higher quality feasible solution can be output faster.

[0067] The examples used are extended from the examples of IEEE30, which respectively represent the unit commitment problems with different numbers of units. The experiment is set to MIPGap of 0.5%, the maximum stop time is set to 7200s, and the average test results of 12 examples using COPT are shown in the following table.

[0068] Table 1 Test results of adaptive relaxed enhanced neighborhood search for unit commitment

[0069]

[0070] This method can further improve the efficiency of large-scale SCUC solving in the engine. The adaptive RENS of the intermediate example COPT is more efficient than Gurobi. Basically, the adaptive RENS is 68% more efficient than the traditional RENS method. Compared with gurobi, the relative gap is basically less than 0.1%, and the solution quality is good. The red part is the result that is better than Gurobi. The advantage is that the advanced and effective RENS heuristic method inside the solver can be used with the optimal strategy. The disadvantage is that the built-in heuristic algorithm of the solver does not work in some examples. Even if the optimal strategy is used, more other heuristic methods are needed.

[0071] Example 2

[0072] The present invention proposes a unit commitment acceleration system based on adaptive calling neighborhood search, such as Figure 2 As shown, including:

[0073] An acquisition module, wherein the acquisition module acquires basic data of units in the power system;

[0074] The basic data of the unit includes: the operating cost of the unit, the output data of the unit, the power constraint data of the unit and the day-ahead load forecast data;

[0075] The unit's operating cost, unit output data, unit power constraint data and day-ahead load forecast data are all collected by the power system.

[0076] A construction module, wherein the construction module constructs a unit combination optimization model based on the acquired basic data of units in the power system;

[0077] The construction of the unit commitment optimization model is specifically as follows:

[0078]

[0079] Among them, C x，u and C x，d are the startup cost and shutdown cost of unit x respectively; w x，y and z x，y are the startup state variable and shutdown state variable of unit x in period y, respectively. When unit x performs the startup action at time y, the startup state variable w of unit x in period y x，y is 1, otherwise it is 0; when unit x performs the shutdown action at time y, the shutdown state variable z of unit x in period y x，y is 1, otherwise it is 0; F x (P x，y ) is the cost of unit x in period y; P xy is the power generation of unit x in period y.

[0080] A calling module, wherein the calling module calls a relaxed enhanced neighborhood search algorithm when a relaxed solution of a root node of a problem of a unit commitment optimization model to be solved and an optimal solution of the problem satisfy a constraint condition;

[0081] If the relaxed solution of the root node of the unit combination optimization model to be solved and the optimal solution of the problem do not meet the constraint conditions, the simulated annealing algorithm, genetic algorithm, ant colony algorithm or neural network algorithm is called to find a feasible solution for the given optimization problem;

[0082] The constraint condition is that the absolute value of the difference between the optimal solution of the unit combination optimization model and the relaxed solution of the root node of the unit combination optimization model is less than a set threshold.

[0083] The solution module searches for a feasible solution based on a relaxed enhanced neighborhood search algorithm, and accelerates the optimization of the unit combination problem based on the feasible solution to achieve optimal dispatch of the power system.

[0084] The method for finding a feasible solution based on a relaxed enhanced neighborhood search algorithm specifically comprises: setting parameters for adaptively calling the relaxed enhanced neighborhood search algorithm, and solving the unit combination optimization model based on the parameters for adaptively calling the relaxed enhanced neighborhood search algorithm; wherein, setting the parameters for adaptively calling the relaxed enhanced neighborhood search algorithm comprises: limiting the discreteness of the sub-integer programming problem, limiting the relaxation scale of the total problem, the number of solution nodes and stagnant nodes, and limiting the cutting plane strength parameters.

[0085] The unit combination optimization model is solved by: after setting the heuristic parameters, the linear relaxation optimal solution is calculated. If the integer variables of the original unit combination problem are in the optimal solution If the result is an integer, fix the value of the integer, otherwise set the upper and lower bounds of the integer variable to be decided to and The integer variables of the updated unit combination subproblem are converted to 0-1 variables, and the optimal solution is obtained by solving the subproblem after updating the upper and lower bounds. Output the optimal solution As the initial feasible solution to the original unit combination problem; It means rounding down, that is, the lower bound of the variable; It means rounding up, that is, the upper bound of the variable.

[0086] Example 3

[0087] See also Figure 3 As shown, the present invention also provides an electronic device 100 for a unit combination acceleration method based on adaptive calling neighborhood search; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0088] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the unit combination acceleration method based on adaptive calling neighborhood search described in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data (such as audio data) created according to the use of the electronic device 100, etc. In addition, the memory 101 can include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0089] The at least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and uses various interfaces and lines to connect various parts of the entire electronic device 100.

[0090] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a unit commitment acceleration method based on adaptive calling neighborhood search, and the processor 102 can execute the plurality of instructions to implement:

[0091] Obtain basic data of units in the power system;

[0092] Based on the basic data of units in the power system, a unit combination optimization model is constructed;

[0093] When the relaxed solution of the root node of the unit commitment optimization model to be solved and the optimal solution of the problem meet the constraint conditions, the relaxed enhanced neighborhood search algorithm is called;

[0094] A feasible solution is found based on the relaxed enhanced neighborhood search algorithm, and the unit commitment problem is accelerated based on the feasible solution to achieve optimal dispatch of the power system.

[0095] Example 4

[0096] If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0097] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0098] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0099] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0100] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A unit commitment acceleration method based on adaptive calling neighborhood search, characterized in that: include: Obtain basic data of units in the power system; Based on the basic data of units in the power system, a unit combination optimization model is constructed; When the relaxed solution of the root node of the unit commitment optimization model to be solved and the optimal solution of the problem meet the constraint conditions, the relaxed enhanced neighborhood search algorithm is called; A feasible solution is found based on the relaxed enhanced neighborhood search algorithm, and the unit commitment problem is accelerated based on the feasible solution to achieve optimal dispatch of the power system.

2. The unit commitment acceleration method based on adaptive calling neighborhood search according to claim 1 is characterized in that: The basic data of the unit include: the operating cost of the unit, the output data of the unit, the power constraint data of the unit and the day-ahead load forecast data; The unit's operating cost, unit output data, unit power constraint data and day-ahead load forecast data are all collected by the power system.

3. The unit commitment acceleration method based on adaptive calling neighborhood search according to claim 1, characterized in that: The construction of the unit commitment optimization model is specifically as follows: Among them, C x，u and C x，d are the startup cost and shutdown cost of unit x respectively; w x，y and z x，y are the startup state variable and shutdown state variable of unit x in period y, respectively. When unit x performs the startup action at time y, the startup state variable w of unit x in period y x，y is 1, otherwise it is 0; when unit x performs the shutdown action at time y, the shutdown state variable z of unit x in period y x，y is 1, otherwise it is 0; F x (P x，y ) is the cost of unit x in period y; P xy is the power generation of unit x in period y.

4. The unit commitment acceleration method based on adaptive calling neighborhood search according to claim 1, characterized in that: If the relaxed solution of the root node of the unit combination optimization model to be solved and the optimal solution of the problem do not meet the constraint conditions, the simulated annealing algorithm, genetic algorithm, ant colony algorithm or neural network algorithm is called to find a feasible solution for the given optimization problem; The constraint condition is that the absolute value of the difference between the optimal solution of the unit combination optimization model and the relaxed solution of the root node of the unit combination optimization model is less than a set threshold.

5. The unit commitment acceleration method based on adaptive calling neighborhood search according to claim 1, characterized in that: The method for finding a feasible solution based on a relaxed enhanced neighborhood search algorithm specifically comprises: setting parameters for adaptively calling the relaxed enhanced neighborhood search algorithm, and solving the unit combination optimization model based on the parameters for adaptively calling the relaxed enhanced neighborhood search algorithm; wherein, setting the parameters for adaptively calling the relaxed enhanced neighborhood search algorithm comprises: limiting the discreteness of the sub-integer programming problem, limiting the relaxation scale of the total problem, the number of solution nodes and stagnant nodes, and limiting the cutting plane strength parameters.

6. The unit commitment acceleration method based on adaptive calling neighborhood search according to claim 5, characterized in that: The unit combination optimization model is solved by: after setting the heuristic parameters, the linear relaxation optimal solution is calculated. If the integer variables of the original unit combination problem are in the optimal solution If the result is an integer, fix the value of the integer, otherwise set the upper and lower bounds of the integer variable to be decided to and The integer variables of the updated unit combination subproblem are converted to 0-1 variables, and the optimal solution is obtained by solving the subproblem after updating the upper and lower bounds. Output the optimal solution As the initial feasible solution to the original unit combination problem; It means rounding down, that is, the lower bound of the variable; It means rounding up, that is, the upper bound of the variable.

7. A unit commitment acceleration system based on adaptive calling neighborhood search, characterized in that: include: An acquisition module, wherein the acquisition module acquires basic data of units in the power system; A construction module, wherein the construction module constructs a unit combination optimization model based on the acquired basic data of units in the power system; A calling module, wherein the calling module calls a relaxed enhanced neighborhood search algorithm when a relaxed solution of a root node of a problem of a unit commitment optimization model to be solved and an optimal solution of the problem satisfy a constraint condition; The solution module searches for a feasible solution based on a relaxed enhanced neighborhood search algorithm, and accelerates the optimization of the unit combination problem based on the feasible solution to achieve optimal dispatch of the power system.

8. The unit commitment acceleration system based on adaptive calling neighborhood search according to claim 7, characterized in that: The construction of the unit commitment optimization model is specifically as follows: Among them, C x，u and C x，d are the startup cost and shutdown cost of unit x respectively; w x，y and z x，y are the startup state variable and shutdown state variable of unit x in period y, respectively. When unit x performs the startup action at time y, the startup state variable w of unit x in period y x，y is 1, otherwise it is 0; when unit x performs the shutdown action at time y, the shutdown state variable z of unit x in period y x，y is 1, otherwise it is 0; F x (P x，y ) is the cost of unit x in period y; P xy is the power generation of unit x in period y.

9. The unit commitment acceleration system based on adaptive calling neighborhood search according to claim 7, characterized in that: If the relaxed solution of the root node of the unit combination optimization model to be solved and the optimal solution of the problem do not meet the constraint conditions, the simulated annealing algorithm, genetic algorithm, ant colony algorithm or neural network algorithm is called to find a feasible solution for the given optimization problem; The constraint condition is that the absolute value of the difference between the optimal solution of the unit combination optimization model and the relaxed solution of the root node of the unit combination optimization model is less than a set threshold.

10. The unit commitment acceleration system based on adaptive calling neighborhood search according to claim 7, characterized in that: The method for finding a feasible solution based on a relaxed enhanced neighborhood search algorithm specifically comprises: setting parameters for adaptively calling the relaxed enhanced neighborhood search algorithm, and solving the unit combination optimization model based on the parameters for adaptively calling the relaxed enhanced neighborhood search algorithm; wherein, setting the parameters for adaptively calling the relaxed enhanced neighborhood search algorithm comprises: limiting the discreteness of the sub-integer programming problem, limiting the relaxation scale of the total problem, the number of solution nodes and stagnant nodes, and limiting the cutting plane strength parameters.

11. The unit commitment acceleration system based on adaptive calling neighborhood search according to claim 10, characterized in that: The unit combination optimization model is solved by: after setting the heuristic parameters, the linear relaxation optimal solution is calculated. If the integer variables of the original unit combination problem are in the optimal solution If the result is an integer, fix the value of the integer, otherwise set the upper and lower bounds of the integer variable to be decided to and The integer variables of the updated unit combination subproblem are converted to 0-1 variables, and the optimal solution is obtained by solving the subproblem after updating the upper and lower bounds. Output the optimal solution As the initial feasible solution to the original unit combination problem; It means rounding down, that is, the lower bound of the variable; It means rounding up, that is, the upper bound of the variable.

12. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the unit commitment acceleration method based on adaptive calling neighborhood search as described in any one of claims 1 to 6 are implemented.

13. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the unit commitment acceleration method based on adaptive calling neighborhood search as claimed in any one of claims 1 to 6 are implemented.

Images