Light-water cluster time-sharing-grouping conditional objective optimization scheduling method and light-water cluster time-sharing-grouping conditional objective optimization scheduling system

Abstract

The invention discloses a light-water cluster time-sharing-grouping condition target optimization scheduling method and system, and the method comprises the steps: constructing a first day-ahead prediction model and a first day-intra prediction model of photovoltaic power generation power based on the historical data of a photovoltaic power generation system and the historical data of a load, and a second day-ahead prediction model and a second day-intra prediction model of the load electric power. According to the first day-ahead prediction model and the second day-ahead prediction model, constructing a day-ahead prediction scheduling optimization model of the basic group hydropower station cluster, and adopting a two-stage condition optimization mode to form a first scheduling scheme of the basic group hydropower station cluster; and according to the first intra-day prediction model and the second intra-day prediction model, constructing an intra-day prediction scheduling optimization model of the adjustment group hydropower station cluster, and adopting a two-stage condition optimization mode to form a second scheduling scheme of the adjustment group hydropower station cluster. And the overall energy utilization rate of the power generation cluster and the stability of load power supply are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of hydropower cluster control under distributed photovoltaic access, and in particular relates to a time-sharing and group-based conditional target optimization scheduling method and system for a photovoltaic and hydropower cluster. Background Art

[0002] Photovoltaic power generation systems, which are random and volatile, are an unstable type of power source. Their penetration rate in the power system has increased, bringing great challenges to the balance of power supply and demand in the power system. Although energy storage systems with both power supply and load characteristics can effectively balance the contradiction between power supply and load demand, the economic, energy consumption and safety issues of energy storage systems have always been the key to restricting their development. Using existing controllable and stable power sources, such as small hydropower, to quickly and efficiently cooperate with photovoltaic power generation systems to achieve reliable supply of electricity demand will be another effective means to promote the further application of photovoltaic power generation systems. Therefore, how to establish a coordinated control strategy for distributed hydropower clusters, improve the utilization rate of new energy, reduce the adverse effects of photovoltaic power generation system uncertainty on power transmission and distribution, and ensure the quality of load power consumption has become an issue worthy of study.

[0003] In the current practical application of distributed hydropower and photovoltaic power generation systems, most distributed hydropower and photovoltaic clusters operate independently and lack unified optimization and scheduling management. This extensive operation mode may lead to idle waste of some distributed resources or low power supply performance. Therefore, it is necessary to establish a unified management optimization scheduling strategy and system for distributed resources. In existing studies, some studies consider transforming small hydropower stations into micro pumped storage systems, and then establish optimization models and intraday rolling optimization strategies to improve photovoltaic consumption. This method requires appropriate transformation of hydropower stations to have dual characteristics of power supply and load, ignoring the complementarity of hydropower and photovoltaic power generation and the ability to cooperate with photovoltaic power generation. Some studies have discovered the complementary characteristics of small hydropower stations and photovoltaic power generation, and calculated the output power of the hydropower station cluster according to the power system transmission end, or realized the coordinated control of small hydropower clusters by optimizing the complementary consumption model of distributed water / photovoltaic power generation clusters. However, related studies have ignored the differences between hydropower stations in small hydropower clusters, especially in terms of response speed, regulation energy and energy loss, which will result in low dynamic response and high energy consumption in coordinated control. On the other hand, related studies have ignored the advantages of day-ahead and intraday forecasts in predicting and dispatching strategies for small hydropower clusters at different time scales. Summary of the invention

[0004] The present invention provides a time-sharing and grouping conditional target optimization scheduling method and system for a light-water cluster, which are used to solve the technical problems of low dynamic response and high energy consumption of coordinated control of a small hydropower cluster.

[0005] In a first aspect, the present invention provides a time-sharing and group-sharing conditional target optimization scheduling method for optical-water clusters, comprising: The technical parameters of each hydropower station in the hydropower station cluster in the distribution network are used to construct a feature vector that represents the operating capacity of the hydropower station, and the machine learning method is used to divide each hydropower station into a basic group hydropower station cluster and a regulation group hydropower station cluster; Based on the historical data of the photovoltaic power generation system and the historical data of the load, a one-day-ahead forecast model and a one-day-intraday forecast model for photovoltaic power generation, as well as a two-day-ahead forecast model and a two-day-intraday forecast model for load power consumption are constructed; A day-ahead forecasting and dispatching optimization model for the basic group of hydropower station clusters is constructed according to the first day-ahead forecasting model and the second day-ahead forecasting model, and a first dispatching plan for the basic group of hydropower station clusters is formed by adopting a two-stage conditional optimization method; An intraday forecasting scheduling optimization model for the hydropower station cluster of the regulation group is constructed based on the first intraday forecasting model and the second intraday forecasting model, and a two-stage conditional optimization method is adopted to form a second scheduling plan for the hydropower station cluster of the regulation group.

[0006] In a second aspect, the present invention provides a time-sharing and group-sharing conditional target optimization scheduling system for optical and water clusters, comprising: a partitioning module configured to use technical parameters of each hydropower station in the hydropower station cluster in the distribution network to construct a feature vector representing the operating capacity of the hydropower station, and to use a machine learning method to partition each hydropower station into a basic group hydropower station cluster and a regulation group hydropower station cluster; A first construction module is configured to construct a first-day-ahead prediction model and a first-day-intraday prediction model for photovoltaic power generation, and a second-day-ahead prediction model and a second-day-intraday prediction model for load power based on photovoltaic power generation system historical data and load historical data; a second construction module configured to construct a day-ahead forecasting and dispatching optimization model for the basic group of hydropower station clusters according to the first day-ahead forecasting model and the second day-ahead forecasting model, and to form a first dispatching plan for the basic group of hydropower station clusters by adopting a two-stage conditional optimization method; The third construction module is configured to construct an intraday forecasting scheduling optimization model for the hydropower station cluster of the regulation group according to the first intraday forecasting model and the second intraday forecasting model, and adopt a two-stage conditional optimization method to form a second scheduling plan for the hydropower station cluster of the regulation group.

[0007] According to a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the steps of the conditional target optimization scheduling method for time-sharing and grouping of optical-water clusters according to any embodiment of the present invention.

[0008] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor executes the steps of the conditional objective optimization scheduling method for time-sharing and grouping of optical-water clusters according to any embodiment of the present invention.

[0009] The time-sharing and grouping conditional target optimization scheduling method and system of the photovoltaic and hydropower cluster of the present application take into account the global and low time resolution characteristics of the day-ahead prediction and the accuracy and high time resolution characteristics of the intraday rolling prediction, and establish a time-sharing and grouping scheduling strategy for the small hydropower station cluster. In addition, the water consumption, switching and other factors of small hydropower are considered in the scheduling strategy, and a two-stage conditional target optimization method is established. While cooperating with photovoltaic power generation to supply load electricity, the operating performance of the small hydropower cluster is improved, which is conducive to promoting the matching degree of the coordinated operation of distributed small hydropower clusters and distributed photovoltaic power generation systems, and improving the overall energy utilization rate of the power generation cluster and the stability of load power supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A flow chart of a time-sharing and group-sharing conditional target optimization scheduling method for an optical-water cluster provided by an embodiment of the present invention; Figure 2 A structural block diagram of a time-sharing and group-based conditional target optimization scheduling system for optical-water clusters provided by an embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0012] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution 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. 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.

[0013] See also Figure 1 , which shows a flow chart of a time-sharing and group-based conditional target optimization scheduling method for optical-water clusters of the present application.

[0014] like Figure 1 As shown, the time-sharing and group-sharing conditional target optimization scheduling method of the optical-water cluster specifically includes the following steps: Step S101, using the technical parameters of each hydropower station in the hydropower station cluster in the distribution network, constructing a feature vector representing the operating capacity of the hydropower station, and using a machine learning method to divide each hydropower station into a basic group hydropower station cluster and a regulation group hydropower station cluster.

[0015] In this step, the indicators that characterize the regulation speed and regulation range of the hydropower station are defined as the characteristic variables for the hydropower station grouping, and the importance of different characteristic variables is defined by expert experience. The indicators that characterize the regulation speed of the hydropower station include response speed, climbing rate, etc.; the indicators that characterize the regulation range of the hydropower station include installed capacity, rated head, etc. In the feature vector, the characteristics that characterize the regulation speed (such as response speed, climbing rate, etc.) are more important to the grouping than the characteristics that characterize the size of the hydropower station (such as installed capacity, rated head, etc.).

[0016] Based on the feature vectors of each hydropower station in the hydropower station cluster and the importance of the features, the clustering method in machine learning is used to divide each hydropower station into a basic group hydropower station cluster and a regulation group hydropower station cluster. The basic group hydropower station cluster is a hydropower station cluster with slow regulation speed and large regulation range; the regulation group hydropower station cluster is a hydropower station cluster with fast regulation speed and small regulation range.

[0017] Step S102, constructing a first-day-ahead prediction model and a first-day-intraday prediction model for photovoltaic power generation, and a second-day-ahead prediction model and a second-day-intraday prediction model for load power based on photovoltaic power generation system historical data and load historical data.

[0018] In this step, based on the historical hourly power generation data and meteorological data of the photovoltaic power generation system, a one-day-ahead prediction model for photovoltaic power generation is established using a machine learning method, wherein the output of the one-day-ahead prediction model is the power generation of the photovoltaic power generation system on the second day, and the input of the one-day-ahead prediction model is the photovoltaic power generation and meteorological data of the same date as the second day in history, and the prediction error of the photovoltaic power generation system on each day is statistically analyzed to form a prediction value for the minimum power generation of the photovoltaic power generation system on the second day; Based on the hourly power consumption of the load in history, a two-day-ahead prediction model for the load power consumption is established using a neural network. The output of the two-day-ahead prediction model is the power consumption of the load on the next day. The input of the two-day-ahead prediction model is the power consumption of the load on the same date as the next day in history. The prediction error of the load power consumption on each day is statistically analyzed to form a prediction value for the minimum power consumption of the load. Based on the minute-level power generation data and meteorological data in the history of photovoltaic power generation, the first-day prediction model of photovoltaic power generation is established by using the autoregressive prediction method. The output of the first-day prediction model is the photovoltaic power generation active power in the future period after the current moment, and the input of the first-day prediction model is the photovoltaic power generation active power in the period before the current moment. Based on the historical minute-level electric power consumption of the load, the autoregressive prediction method is used to establish a second-day prediction model for the load electric power consumption. The output of the second-day prediction model is the load electric power consumption in the future period after the current moment, and the input of the second-day prediction model is the load electric power consumption in the period before the current moment.

[0019] Step S103, constructing a day-ahead forecasting and scheduling optimization model for the basic group of hydropower station clusters according to the first day-ahead forecasting model and the second day-ahead forecasting model, and adopting a two-stage conditional optimization method to form a first scheduling plan for the basic group of hydropower station clusters.

[0020] In this step, the minimum power generation forecast value of the photovoltaic power generation system on the second day is defined as And the minimum power consumption forecast value of the load on the second day is , The end time of the second day, is the predicted power generation value of the photovoltaic power generation system at the Tth moment, is the predicted value of load power consumption at the Tth moment; Assume that the number of hydropower stations in the hydropower station cluster of the regulation group used for scheduling on the second day is , the first in the hydropower station cluster of the regulation group The installed capacity of the hydropower station is , then the maximum regulation capacity of the hydropower station cluster of the regulation group is According to the predicted value of the minimum power generation of the photovoltaic power generation system on the second day and the predicted value of the minimum power consumption of the load on the second day, the output power range of the basic group hydropower station cluster at each moment on the second day is calculated as ; Taking the minimum water consumption of each hydropower station in the basic group hydropower station cluster as the objective function, the first-stage optimization scheduling model of each hydropower station in the basic group hydropower station cluster is established, and the minimum water consumption of the basic group hydropower station cluster is solved by using the classical optimization method; Taking the minimum water consumption of the basic group hydropower station cluster as the condition and the minimum switching of each hydropower station in the basic group hydropower station cluster as the objective function, the second-stage optimization scheduling model of each hydropower station in the basic group hydropower station cluster is established, and the first scheduling plan of the basic group hydropower station cluster is solved using the classical optimization method.

[0021] It should be noted that the optimization variables in the first-stage optimization scheduling model of each hydropower station in the basic group of hydropower station clusters are determined, where the optimization variables are the operating power of each hydropower station in the basic group of hydropower station clusters at each moment on the second day, and the first Hydropower stations in The output power at the moment is ; Determine the optimization objective function that represents the overall water consumption of the hydropower plants in the basic group of hydropower plants , the expression is: , In the formula, is the number of hydropower stations in the basic group of hydropower station clusters, is the water head of the kth hydropower station in the basic group of hydropower stations, The end time of the second day, It is the functional relationship between water consumption, hydraulic head and operating power of each hydropower station; Determine the operating constraints of each hydropower station in the basic group hydropower station cluster, expressed as: , , , In the formula, is the maximum ramp rate of the kth hydropower station in the basic group of hydropower stations, is the installed capacity of the kth hydropower station in the basic group of hydropower station clusters, For load The predicted power consumption at the time, Photovoltaic power generation system The predicted power generation value at the time, The first hydropower station in the basic group Hydropower stations in Output power at the moment; The optimization objective function is solved by using the classical optimization method to obtain the minimum water consumption of the basic group of hydropower station clusters. .

[0022] Specifically, the optimization variables in the second-stage optimization scheduling model of each hydropower station in the basic group of hydropower station clusters are determined, wherein the optimization variables include the operating power and operating status of each hydropower station in the basic group of hydropower station clusters at each moment on the second day, Hydropower stations in The output power and operating status at the moment are and , is a binary optimization variable between 0 and 1. =1, indicating the first Hydropower stations in Always in the start-up state, =0, indicating the first Hydropower stations in Always in shutdown state; Determine the conditional objective function that represents the minimum number of state switching times of the hydropower stations in the basic group of hydropower station clusters under the condition of minimum overall water consumption , the expression is: , In the formula, The first hydropower station in the basic group Hydropower stations in The operating status at the moment, is the minimum water consumption of the basic group of hydropower station clusters, The optimization objective function for the overall water consumption of hydropower stations in the basic group of hydropower station clusters; Determine the operating constraints of each hydropower station in the basic group hydropower station cluster, expressed as: , , , In the formula, is the maximum ramp rate of the kth hydropower station in the basic group of hydropower stations, is the installed capacity of the kth hydropower station in the basic group of hydropower station clusters, For load The predicted power consumption at the time, Photovoltaic power generation system The predicted power generation value at the time, The first hydropower station in the basic group Hydropower stations in Output power at the moment; The conditional objective function is solved using a classical optimization method, and the operating power and operating status of each hydropower station in the basic group hydropower station cluster at each moment of the second day are obtained to form a first dispatching plan for the basic group hydropower station cluster.

[0023] Step S104, constructing an intraday forecasting scheduling optimization model for the hydropower station cluster of the regulation group according to the first intraday forecasting model and the second intraday forecasting model, and adopting a two-stage conditional optimization method to form a second scheduling plan for the hydropower station cluster of the regulation group.

[0024] In this step, define The predicted power generation value of the photovoltaic power generation system at the moment is and in The predicted power consumption of the load at the moment is , is the intraday forecast length, For photovoltaic power generation systems The predicted power generation value at the time, For load The predicted value of power consumption at the moment; Assume that During the period, the hydropower station cluster of the regulation group is The number of hydropower stations is , the first in the hydropower station cluster of the regulation group At any given moment, The power generation is , the basic group of hydropower station cluster as a whole at any time The power generation is , is the number of hydropower stations in the basic group of hydropower station clusters, The first hydropower station in the basic group At any given moment, The output power of the hydropower station cluster is regulated by the constraint condition of the power generation power of the hydropower station cluster: , In the formula, For at any time The load power consumption forecast value, For at any time The predicted power generation value of the photovoltaic power generation system, It is the permissible threshold value for the imbalance between load power consumption and power generation; Taking the minimum water consumption of each hydropower station in the regulating group hydropower station cluster as the objective function, the third-stage optimization dispatching model of each hydropower station in the regulating group hydropower station cluster is established, and the minimum water consumption of the regulating group hydropower station cluster is solved by using the classical optimization method; Taking the minimum water consumption of the regulating group hydropower station cluster as a condition and the minimum switching of each hydropower station in the regulating group hydropower station cluster as the objective function, a fourth-stage optimal scheduling model of each hydropower station in the regulating group hydropower station cluster is established, and the classical optimization method is used to solve the optimal scheduling sequence of each hydropower station in the regulating group hydropower station cluster in the future at the current moment, wherein the scheduling plan of each hydropower station in the regulating group hydropower station cluster at the first predicted moment in the optimal scheduling sequence is the second scheduling plan of the regulating group hydropower station cluster.

[0025] It should be noted that the optimization variables in the third-stage optimization dispatching model of each hydropower station in the hydropower station cluster of the regulation group are determined. The optimization variables are the operating power of each hydropower station in the hydropower station cluster of the regulation group at the current moment in the future, which are defined in Any time during the period The regulation group under the hydropower station cluster The output power of a hydropower station is ; Determine the optimization objective function that represents the overall water consumption of the hydropower plants in the regulation group hydropower plant cluster , the expression is: , In the formula, is the water head of the kth hydropower station in the hydropower station cluster of the regulation group, It is the functional relationship between water consumption, hydraulic head and operating power of each hydropower station; Determine the operation constraints of each hydropower station in the hydropower station cluster of the regulation group, and the expression is: , , In the formula, It is the first in the hydropower station cluster of the regulation group. The maximum ramp rate of a hydropower station, It is the first in the hydropower station cluster of the regulation group. The installed capacity of the hydropower station, It is the first in the hydropower station cluster of the regulation group. Hydropower stations in The power generation at the moment; Solve the optimization objective function using classical optimization methods , get the minimum water consumption of the hydropower station cluster of the regulation group .

[0026] Specifically, the optimization variables in the fourth stage optimization scheduling model of each hydropower station in the hydropower station cluster of the regulation group are determined, wherein the optimization variables include the operating power and operating status of each hydropower station in the hydropower station cluster of the regulation group in the future period of time. Any time during the period The regulation group under the hydropower station cluster The output power of a hydropower station is and the operating status is , is a binary optimization variable between 0 and 1. =1, indicating that the first At any given moment, In operation, when =0, indicating the first At any given moment, In shutdown state; Determine the conditional objective function that represents the minimum number of state switching times of the hydropower stations in the regulation group under the condition of minimum overall water consumption , the expression is: , In the formula, To optimize the overall water consumption of hydropower stations in the hydropower station cluster, To regulate the minimum water consumption of the hydropower station cluster, The jth hydropower station in the basic group hydropower station cluster is The operating status at the moment; Determine the operation constraints of each hydropower station in the hydropower station cluster of the regulation group, and the expression is: , , In the formula, It is the first in the hydropower station cluster of the regulation group. The maximum ramp rate of a hydropower station, It is the first in the hydropower station cluster of the regulation group. The installed capacity of the hydropower stations; Solve the conditional objective function using classical optimization methods , and obtain the operating power and operating status of each hydropower station in the hydropower station cluster of the regulation group in the future period, forming an optimized scheduling sequence for each hydropower station in the hydropower station cluster of the regulation group in the future period.

[0027] In a specific embodiment, it is determined whether to perform the day-ahead forecasting and scheduling optimization of the small hydropower cluster. If the day-ahead forecasting and scheduling optimization of the small hydropower cluster is performed, the first scheduling scheme is performed; if not, it is determined whether to continue to perform the intraday forecasting and scheduling optimization of the small hydropower cluster; If the intraday forecast scheduling optimization of the small hydropower cluster is executed, the second scheduling plan is carried out; if not, the scheduling of the small hydropower cluster is completed and the restart instruction is waited.

[0028] In summary, in the current practical application of distributed hydropower and photovoltaic power generation systems, most distributed hydropower and photovoltaic clusters operate independently and lack unified optimization and scheduling management. Existing studies consider unified management of distributed resources, and some studies consider transforming small hydropower stations into micro pumped storage systems, establishing optimization models and intraday rolling optimization strategies to improve photovoltaic consumption. This method enables the transformed pumped storage power station to have both power supply and load characteristics, but increases the cost of transformation, while ignoring the complementarity of hydropower and photovoltaic power generation and the ability to cooperate with photovoltaic power generation. Based on the complementary characteristics of small hydropower stations and photovoltaic power generation, some studies calculate the output power of the hydropower station cluster according to the power system transmission end, or optimize the complementary consumption model of distributed hydro / photovoltaic power generation clusters to achieve coordinated control of small hydropower clusters. However, on the one hand, related studies ignore the differences between hydropower stations in small hydropower clusters, especially in terms of response speed, regulation energy and energy loss, which will result in unsatisfactory performance in the coordinated control process. On the other hand, related studies ignore the differences in prediction and scheduling strategies of hydropower stations with different performance in small hydropower clusters at different time scales. To this end, the present invention proposes a time-sharing and grouping conditional target optimization scheduling method for distributed photovoltaic and hydropower clusters. Compared with the prior art, the technical solution of the present application takes into account the global and low time resolution characteristics of the day-ahead prediction and the accuracy and high time resolution characteristics of the intraday rolling prediction, effectively groups the small hydropower clusters in the distribution network, and establishes a small hydropower station cluster scheduling strategy with different time scales. In addition, factors such as water consumption and switching of small hydropower are considered in the scheduling strategy, and a two-stage conditional target optimization method is established to improve the operating performance of small hydropower clusters while cooperating with photovoltaic power generation to supply load electricity. The present application will be conducive to promoting the matching degree of the coordinated operation of distributed small hydropower clusters and distributed photovoltaic power generation systems, and improving the overall energy utilization rate of the power generation cluster and the stability of load power supply.

[0029] See also Figure 2 , which shows a structural block diagram of a light-water cluster time-sharing and group-based conditional target optimization scheduling system of the present application.

[0030] like Figure 2As shown, the conditional target optimization scheduling system 200 includes a partitioning module 210 , a first building module 220 , a second building module 230 and a third building module 240 .

[0031] Among them, the division module 210 is configured to use the technical parameters of each hydropower station in the hydropower station cluster in the distribution network to construct a feature vector that characterizes the operating capacity of the hydropower station, and use a machine learning method to divide each hydropower station into a basic group hydropower station cluster and a regulation group hydropower station cluster; the first construction module 220 is configured to construct a first-day-ahead prediction model and a first-day-intraday prediction model for photovoltaic power generation power, as well as a second-day-ahead prediction model and a second-day-intraday prediction model for load power based on historical data of the photovoltaic power generation system and historical load data; the second construction module 230 is configured to construct a day-ahead prediction and scheduling optimization model for the basic group hydropower station cluster based on the first day-ahead prediction model and the second day-ahead prediction model, and adopt a two-stage conditional optimization method to form a first scheduling plan for the basic group hydropower station cluster; the third construction module 240 is configured to construct an intraday prediction and scheduling optimization model for the regulation group hydropower station cluster based on the first intraday prediction model and the second intraday prediction model, and adopt a two-stage conditional optimization method to form a second scheduling plan for the regulation group hydropower station cluster.

[0032] It should be understood that Figure 2 Modules and references documented in Figure 1 Therefore, the operations and features described above for the method and the corresponding technical effects are also applicable to Figure 2 The modules in it will not be described in detail here.

[0033] In some other embodiments, the embodiments of the present invention further provide a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor is caused to execute the conditional target optimization scheduling method for time-sharing and grouping of optical-water clusters in any of the above method embodiments; As an implementation mode, the computer-readable storage medium of the present invention stores computer-executable instructions, and the computer-executable instructions are configured as follows: The technical parameters of each hydropower station in the hydropower station cluster in the distribution network are used to construct a feature vector that represents the operating capacity of the hydropower station, and the machine learning method is used to divide each hydropower station into a basic group hydropower station cluster and a regulation group hydropower station cluster; Based on the historical data of the photovoltaic power generation system and the historical data of the load, a one-day-ahead forecast model and a one-day-intraday forecast model for photovoltaic power generation, as well as a two-day-ahead forecast model and a two-day-intraday forecast model for load power consumption are constructed; A day-ahead forecasting and dispatching optimization model for the basic group of hydropower station clusters is constructed according to the first day-ahead forecasting model and the second day-ahead forecasting model, and a first dispatching plan for the basic group of hydropower station clusters is formed by adopting a two-stage conditional optimization method; An intraday forecasting scheduling optimization model for the hydropower station cluster of the regulation group is constructed based on the first intraday forecasting model and the second intraday forecasting model, and a two-stage conditional optimization method is adopted to form a second scheduling plan for the hydropower station cluster of the regulation group.

[0034] The computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the light-water cluster time-sharing-grouping conditional target optimization scheduling system, etc. In addition, the computer-readable storage medium may include a high-speed random access memory, and may also include a memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the light-water cluster time-sharing-grouping conditional target optimization scheduling system via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0035] Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, the device includes: a processor 310 and a memory 320. The electronic device may also include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330 and the output device 340 may be connected via a bus or other means. Figure 3 In the example, the bus connection is used. The memory 320 is the above-mentioned computer-readable storage medium. The processor 310 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 320, that is, the conditional target optimization scheduling method of the light-water cluster time-sharing-grouping in the above-mentioned method embodiment is realized. The input device 330 can receive input digital or character information, and generate key signal input related to user settings and function control of the conditional target optimization scheduling system of the light-water cluster time-sharing-grouping. The output device 340 may include display devices such as display screens.

[0036] The electronic device can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0037] As an implementation mode, the electronic device is applied to a time-sharing and grouping conditional target optimization scheduling system of an optical-water cluster, and is used for a client, and includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: The technical parameters of each hydropower station in the hydropower station cluster in the distribution network are used to construct a feature vector that represents the operating capacity of the hydropower station, and the machine learning method is used to divide each hydropower station into a basic group hydropower station cluster and a regulation group hydropower station cluster; Based on the historical data of the photovoltaic power generation system and the historical data of the load, a one-day-ahead forecast model and a one-day-intraday forecast model for photovoltaic power generation, as well as a two-day-ahead forecast model and a two-day-intraday forecast model for load power consumption are constructed; A day-ahead forecasting and dispatching optimization model for the basic group of hydropower station clusters is constructed according to the first day-ahead forecasting model and the second day-ahead forecasting model, and a first dispatching plan for the basic group of hydropower station clusters is formed by adopting a two-stage conditional optimization method; An intraday forecasting scheduling optimization model for the hydropower station cluster of the regulation group is constructed based on the first intraday forecasting model and the second intraday forecasting model, and a two-stage conditional optimization method is adopted to form a second scheduling plan for the hydropower station cluster of the regulation group.

[0038] Through the description of the above implementation modes, those skilled in the art can clearly understand that each implementation mode can be implemented by means of software plus a necessary general hardware platform, or of course by hardware. Based on such an understanding, the above technical solution can essentially or in other words be embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0039] 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A time-sharing and grouping conditional target optimization scheduling method for optical-water clusters, characterized in that: include: The technical parameters of each hydropower station in the hydropower station cluster in the distribution network are used to construct a feature vector that represents the operating capacity of the hydropower station, and the machine learning method is used to divide each hydropower station into a basic group hydropower station cluster and a regulation group hydropower station cluster; Based on the historical data of the photovoltaic power generation system and the historical data of the load, a one-day-ahead forecast model and a one-day-intraday forecast model for photovoltaic power generation, as well as a two-day-ahead forecast model and a two-day-intraday forecast model for load power consumption are constructed; A day-ahead forecasting and dispatching optimization model for the basic group of hydropower station clusters is constructed according to the first day-ahead forecasting model and the second day-ahead forecasting model, and a first dispatching plan for the basic group of hydropower station clusters is formed by adopting a two-stage conditional optimization method; An intraday forecasting scheduling optimization model for the hydropower station cluster of the regulation group is constructed based on the first intraday forecasting model and the second intraday forecasting model, and a two-stage conditional optimization method is adopted to form a second scheduling plan for the hydropower station cluster of the regulation group.

2. According to claim 1, a time-sharing and grouping conditional target optimization scheduling method for optical-water clusters is characterized in that: The technical parameters of each hydropower station in the hydropower station cluster in the distribution network are used to construct a feature vector representing the operating capacity of the hydropower station, and the machine learning method is used to divide each hydropower station into a basic group hydropower station cluster and a regulation group hydropower station cluster, including: Define the indicators that characterize the regulation speed and regulation range of the hydropower station as the characteristic variables for grouping the hydropower stations, and use expert experience to define the importance of different characteristic variables; Based on the feature vectors of each hydropower station in the hydropower station cluster and the importance of the features, the clustering method in machine learning is used to divide the hydropower stations into a basic group hydropower station cluster and a regulation group hydropower station cluster.

3. The method for optimizing the scheduling of light-water cluster time-sharing and grouping conditional objectives according to claim 1, characterized in that: The method of constructing a one-day-ahead prediction model and a one-day-intraday prediction model for photovoltaic power generation based on photovoltaic power generation system historical data and load historical data, as well as a two-day-ahead prediction model and a two-day-intraday prediction model for load power consumption includes: Based on the historical hourly power generation data and meteorological data of the photovoltaic power generation system, a one-day-ahead prediction model for photovoltaic power generation is established using machine learning methods. The output of the one-day-ahead prediction model is the power generation of the photovoltaic power generation system on the second day. The input of the one-day-ahead prediction model is the photovoltaic power generation and meteorological data of the same date as the second day in history. The prediction error of the photovoltaic power generation system on each day is statistically analyzed to form a prediction value for the minimum power generation of the photovoltaic power generation system on the second day. Based on the hourly power consumption of the load in history, a two-day-ahead prediction model for the load power consumption is established using a neural network. The output of the two-day-ahead prediction model is the power consumption of the load on the next day. The input of the two-day-ahead prediction model is the power consumption of the load on the same date as the next day in history. The prediction error of the load power consumption on each day is statistically analyzed to form a prediction value for the minimum power consumption of the load. Based on the minute-level power generation data and meteorological data in the history of photovoltaic power generation, the first-day prediction model of photovoltaic power generation is established by using the autoregressive prediction method. The output of the first-day prediction model is the photovoltaic power generation active power in the future period after the current moment, and the input of the first-day prediction model is the photovoltaic power generation active power in the period before the current moment. Based on the historical minute-level electric power consumption of the load, the autoregressive prediction method is used to establish a second-day prediction model for the load electric power consumption. The output of the second-day prediction model is the load electric power consumption in the future period after the current moment, and the input of the second-day prediction model is the load electric power consumption in the period before the current moment.

4. The method for optimizing the scheduling of light-water cluster time-sharing and grouping conditional objectives according to claim 1, characterized in that: The step of constructing a day-ahead forecasting and dispatching optimization model for the basic group of hydropower station clusters according to the first day-ahead forecasting model and the second day-ahead forecasting model, and adopting a two-stage conditional optimization method to form a first dispatching scheme for the basic group of hydropower station clusters includes: The minimum power generation forecast value of the photovoltaic power generation system on the second day is defined as And the minimum power consumption forecast value of the load on the second day is , The end time of the second day, is the predicted power generation value of the photovoltaic power generation system at the Tth moment, is the predicted value of load power consumption at the Tth moment; Assume that the number of hydropower stations in the hydropower station cluster of the regulation group used for scheduling on the second day is , the first in the hydropower station cluster of the regulation group The installed capacity of the hydropower station is , then the maximum regulation capacity of the hydropower station cluster of the regulation group is According to the predicted value of the minimum power generation of the photovoltaic power generation system on the second day and the predicted value of the minimum power consumption of the load on the second day, the output power range of the basic group hydropower station cluster at each moment on the second day is calculated as ; Taking the minimum water consumption of each hydropower station in the basic group hydropower station cluster as the objective function, the first-stage optimization scheduling model of each hydropower station in the basic group hydropower station cluster is established, and the minimum water consumption of the basic group hydropower station cluster is solved by using the classical optimization method; Taking the minimum water consumption of the basic group hydropower station cluster as the condition and the minimum switching of each hydropower station in the basic group hydropower station cluster as the objective function, the second-stage optimization scheduling model of each hydropower station in the basic group hydropower station cluster is established, and the first scheduling plan of the basic group hydropower station cluster is solved using the classical optimization method.

5. The method for optimizing the scheduling of light-water cluster time-sharing and grouping conditional objectives according to claim 4, characterized in that: The first-stage optimization scheduling model of each hydropower station in the basic group hydropower station cluster is established by taking the minimum water consumption of each hydropower station in the basic group hydropower station cluster as the objective function, and solving the minimum water consumption of the basic group hydropower station cluster by using the classical optimization method, including: Determine the optimization variables in the first phase optimization scheduling model of each hydropower station in the basic group of hydropower station clusters, where the optimization variables are the operating power of each hydropower station in the basic group of hydropower station clusters at each time on the second day, and define the first phase optimization scheduling model of each hydropower station in the basic group of hydropower station clusters. Hydropower stations in The output power at the moment is ; Determine the optimization objective function that represents the overall water consumption of the hydropower plants in the basic group of hydropower plants , the expression is: ， In the formula, is the number of hydropower stations in the basic group of hydropower station clusters, is the water head of the kth hydropower station in the basic group of hydropower stations, The end time of the second day, It is the functional relationship between water consumption, hydraulic head and operating power of each hydropower station; Determine the operating constraints of each hydropower station in the basic group hydropower station cluster, expressed as: ， ， ， In the formula, is the maximum ramp rate of the kth hydropower station in the basic group of hydropower stations, is the installed capacity of the kth hydropower station in the basic group of hydropower station clusters, For load The predicted power consumption at the time, Photovoltaic power generation system The predicted power generation value at the time, The first hydropower station in the basic group Hydropower stations in Output power at the moment; The optimization objective function is solved by using the classical optimization method to obtain the minimum water consumption of the basic group of hydropower station clusters. .

6. The method for optimizing the scheduling of light-water cluster time-sharing and grouping conditional objectives according to claim 4, characterized in that: The method takes the minimum water consumption of the basic group hydropower station cluster as a condition and the minimum switching of each hydropower station in the basic group hydropower station cluster as an objective function, establishes a second-stage optimization scheduling model for each hydropower station in the basic group hydropower station cluster, and uses a classical optimization method to solve the first scheduling plan of the basic group hydropower station cluster, including: Determine the optimization variables in the second-stage optimization scheduling model of each hydropower station in the basic group of hydropower station clusters, where the optimization variables include the operating power and operating status of each hydropower station in the basic group of hydropower station clusters at each time on the second day, the first Hydropower stations in The output power and operating status at the moment are and , is a binary optimization variable between 0 and 1. =1, indicating the first Hydropower stations in Always in the start-up state, =0, indicating the first Hydropower stations in Always in shutdown state; Determine the conditional objective function that represents the minimum number of state switching times of the hydropower stations in the basic group of hydropower station clusters under the condition of minimum overall water consumption , the expression is: ， In the formula, The first hydropower station in the basic group Hydropower stations in The operating status at the moment, is the minimum water consumption of the basic group of hydropower station clusters, The optimization objective function for the overall water consumption of hydropower stations in the basic group of hydropower station clusters; Determine the operating constraints of each hydropower station in the basic group hydropower station cluster, expressed as: ， ， ， In the formula, is the maximum ramp rate of the kth hydropower station in the basic group of hydropower stations, is the installed capacity of the kth hydropower station in the basic group of hydropower station clusters, For load The predicted power consumption at the time, Photovoltaic power generation system The predicted power generation value at the time, The first hydropower station in the basic group Hydropower stations in Output power at the moment; The conditional objective function is solved using a classical optimization method, and the operating power and operating status of each hydropower station in the basic group hydropower station cluster at each moment of the second day are obtained to form a first dispatching plan for the basic group hydropower station cluster.

7. The method for optimizing the scheduling of light-water cluster time-sharing and grouping conditional objectives according to claim 1, characterized in that: The intraday forecasting scheduling optimization model of the hydropower station cluster of the regulating group is constructed according to the first intraday forecasting model and the second intraday forecasting model, and a two-stage conditional optimization method is adopted to form a second scheduling scheme for the hydropower station cluster of the regulating group, including: Defined in The predicted power generation value of the photovoltaic power generation system at the moment is and in The predicted power consumption of the load at the moment is , is the intraday forecast length, For photovoltaic power generation systems The predicted power generation value at the time, For load The predicted value of power consumption at the moment; Assume that During the period, the hydropower station cluster of the regulation group is The number of hydropower stations is , the first in the hydropower station cluster of the regulation group At any given moment, The power generation is , the basic group of hydropower station cluster as a whole at any time The power generation is , is the number of hydropower stations in the basic group of hydropower station clusters, The first hydropower station in the basic group At any given moment, The output power of the hydropower station cluster is regulated by the constraint condition of the power generation power of the hydropower station cluster: , In the formula, For at any time The load power consumption forecast value, For at any time The predicted power generation value of the photovoltaic power generation system, It is the permissible threshold value for the imbalance between load power consumption and power generation; Taking the minimum water consumption of each hydropower station in the regulating group hydropower station cluster as the objective function, the third-stage optimization dispatching model of each hydropower station in the regulating group hydropower station cluster is established, and the minimum water consumption of the regulating group hydropower station cluster is solved by using the classical optimization method; Taking the minimum water consumption of the regulating group hydropower station cluster as a condition and the minimum switching of each hydropower station in the regulating group hydropower station cluster as the objective function, a fourth-stage optimal scheduling model of each hydropower station in the regulating group hydropower station cluster is established, and the classical optimization method is used to solve the optimal scheduling sequence of each hydropower station in the regulating group hydropower station cluster in the future at the current moment, wherein the scheduling plan of each hydropower station in the regulating group hydropower station cluster at the first predicted moment in the optimal scheduling sequence is the second scheduling plan of the regulating group hydropower station cluster.

8. The method for optimizing the scheduling of light and water clusters by time-sharing and grouping conditions according to claim 7, characterized in that: The third-stage optimization scheduling model of each hydropower station in the regulating group hydropower station cluster is established by taking the minimum water consumption of each hydropower station in the regulating group hydropower station cluster as the objective function, and solving the minimum water consumption of the regulating group hydropower station cluster by using the classical optimization method includes: Determine the optimization variables in the third-stage optimization dispatch model of each hydropower station in the hydropower station cluster of the regulation group. The optimization variables are the operating power of each hydropower station in the hydropower station cluster of the regulation group at the current moment in the future, which are defined in Any time during the period The regulation group under the hydropower station cluster The output power of a hydropower station is ; Determine the optimization objective function that represents the overall water consumption of the hydropower plants in the regulation group hydropower plant cluster , the expression is: ， In the formula, is the head of the kth hydropower station in the hydropower station cluster of the regulation group, It is the functional relationship between water consumption, hydraulic head and operating power of each hydropower station; Determine the operation constraints of each hydropower station in the hydropower station cluster of the regulation group, and the expression is: ， ， In the formula, It is the first in the hydropower station cluster of the regulation group. The maximum ramp rate of a hydropower station, It is the first in the hydropower station cluster of the regulation group. The installed capacity of the hydropower station, It is the first in the hydropower station cluster of the regulation group. Hydropower stations in The power generation at the time; Solve the optimization objective function using classical optimization methods , get the minimum water consumption of the hydropower station cluster of the regulation group .

9. The method for optimizing the scheduling of light and water clusters by time-sharing and grouping conditions according to claim 7, characterized in that: The fourth-stage optimization dispatching model of each hydropower station in the regulating group hydropower station cluster is established based on the minimum water consumption of the regulating group hydropower station cluster and the minimum switching of each hydropower station in the regulating group hydropower station cluster as the objective function, and the optimal dispatching sequence of each hydropower station in the regulating group hydropower station cluster in the future at the current moment is solved by using the classical optimization method, including: Determine the optimization variables in the fourth stage optimization dispatch model of each hydropower station in the hydropower station cluster of the regulation group, where the optimization variables include the operating power and operating status of each hydropower station in the hydropower station cluster of the regulation group in the future period of time. Any time during the period The regulation group under the hydropower station cluster The output power of a hydropower station is and the operating status is , is a binary optimization variable between 0 and 1. =1, indicating that the first At any given moment, In operation, when =0, indicating the first At any given moment, In shutdown state; Determine the conditional objective function that represents the minimum number of state switching times of the hydropower stations in the regulation group under the condition of minimum overall water consumption , the expression is: ， In the formula, To optimize the overall water consumption of hydropower stations in the hydropower station cluster, To regulate the minimum water consumption of the hydropower station cluster, The jth hydropower station in the basic group hydropower station cluster is The operating status at the moment; Determine the operation constraints of each hydropower station in the hydropower station cluster of the regulation group, and the expression is: ， ， In the formula, It is the first in the hydropower station cluster of the regulation group. The maximum ramp rate of a hydropower station, It is the first in the hydropower station cluster of the regulation group. The installed capacity of the hydropower stations; Solve the conditional objective function using classical optimization methods , and obtain the operating power and operating status of each hydropower station in the hydropower station cluster of the regulation group in the future period, forming an optimized scheduling sequence for each hydropower station in the hydropower station cluster of the regulation group in the future period.

10. A time-sharing and group-sharing conditional target optimization scheduling system for light and water clusters, characterized in that: include: a partitioning module configured to use technical parameters of each hydropower station in the hydropower station cluster in the distribution network to construct a feature vector representing the operating capacity of the hydropower station, and to use a machine learning method to partition each hydropower station into a basic group hydropower station cluster and a regulation group hydropower station cluster; A first construction module is configured to construct a first-day-ahead prediction model and a first-day-intraday prediction model for photovoltaic power generation, and a second-day-ahead prediction model and a second-day-intraday prediction model for load power based on photovoltaic power generation system historical data and load historical data; a second construction module configured to construct a day-ahead forecasting and dispatching optimization model for the basic group of hydropower station clusters according to the first day-ahead forecasting model and the second day-ahead forecasting model, and to form a first dispatching plan for the basic group of hydropower station clusters by adopting a two-stage conditional optimization method; The third construction module is configured to construct an intraday forecasting scheduling optimization model for the hydropower station cluster of the regulation group according to the first intraday forecasting model and the second intraday forecasting model, and adopt a two-stage conditional optimization method to form a second scheduling plan for the hydropower station cluster of the regulation group.

Images