Large-scale wind power integration power system optimization method considering cold-wave weather
By combining the distance-generating adversarial network and the joint optimization scheduling model of wind power-thermal power, and using matrix segmentation strategy, the operation difficulty and scheduling difficulty of the power system in cold weather is solved, the fine scheduling and control of the power system is realized, and the calculation is improved Speed and system stability.
Patent Information
- Application Number
- CN202411169035.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-23
- Publication Date
- 2024-12-03
AI Technical Summary
The existing power system optimization methods lack specific methods for cold wave weather, which leads to sudden changes in wind speed and increased loads, which increase the operation and scheduling difficulty of the power system. How to effectively perform fine scheduling and control in cold wave weather.
The wind power output power model based on the distance-generating adversarial network and the wind power-thermal power joint optimization scheduling model are adopted, combined with the matrix segmentation strategy, the low output value of wind power and unit output are obtained, the power system is optimized, and the power system optimization solution is constructed in cold wave weather.
In cold weather, the fine scheduling and control of the power system is realized, which improves the calculation speed of system operation, can cope with uncertainty with the minimum expected total cost of the system, and reduces the difficulty of operation and scheduling.
Smart Images

Figure CN119070284A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of power system optimization, and in particular to a power system optimization method for large-scale wind power grid connection taking into account cold wave weather. Background Art
[0002] In the relevant technologies, the new power system with new energy as the main body has higher and higher requirements for stability, but its natural "weather coupling" and "system fragility" have caused the wind power supply capacity to be damaged. In addition, the superposition of natural factors such as global warming has led to frequent extreme weather in recent years, further amplifying the uncertainty of both sides of the source and load and the risk of grid operation and backup coordination. It is particularly important to improve the supply guarantee capacity of high-proportion wind power power systems under the influence of extreme weather. However, in recent years, sudden large-scale power outages caused by extreme weather natural disasters have occurred to varying degrees in various parts of the world. In particular, due to the influence of cold waves, sudden drops in wind power and high temperatures, power supply is more likely to be tight in new energy supply areas. Among them, cold waves are one of the important extreme weather that affects the normal operation of large-scale wind power systems.
[0003] However, the power system optimization methods in related technologies are mostly aimed at general extreme weather, and there is a lack of power system optimization methods for cold wave weather. The sudden change of wind speed, the increase of load, and the difference of renewable energy power generation capacity in cold wave weather may increase the operation and scheduling difficulty of the power system to a certain extent. How to effectively and finely dispatch and control the power system under the high uncertainty brought by cold wave weather needs to be solved urgently. Summary of the invention
[0004] The present application provides a method for optimizing a power system for large-scale wind power grid-connected power plants in consideration of cold wave weather, in order to solve the problem that the power system optimization methods in the related technologies are mostly oriented towards general extreme weather and lack power system optimization methods for cold wave weather. The sudden change of wind speed, the increase of load, and the difference of new energy power generation capacity in cold wave weather may increase the operation difficulty and scheduling difficulty of the power system to a certain extent. The problem of how to effectively and finely schedule and control the power system under the high uncertainty brought by cold wave weather is solved.
[0005] The first aspect of the present application provides an optimization method for a large-scale wind power grid-connected power system taking into account cold wave weather, comprising the following steps: collecting cold wave weather information of the environment in which the power system is located; based on the cold wave weather information, using a pre-constructed wind power output power model for cold wave weather based on a distance-generative adversarial network to obtain a low output value of wind power in cold wave weather; based on the low output value of wind power in cold wave weather, using a pre-constructed wind power-thermal power joint optimization scheduling model for low wind power output to obtain the unit output and flow distribution in cold wave weather; based on the unit output and the flow distribution, using a matrix partitioning strategy to perform matrix decomposition on wind power and load to optimize the power system.
[0006] Optionally, in one embodiment of the present application, before obtaining the low wind power output value in the cold wave weather, it also includes: collecting cold wave wind power characteristics in historical data; generating wind power generation power in the cold wave according to the cold wave wind power characteristics, so as to establish the wind power output power model in the cold wave weather based on the distance-generative adversarial network; based on the optimal minimum expected system total cost of the power system to deal with the uncertainty brought by all cold wave weather, construct the wind power-thermal power joint optimization scheduling model based on low wind power output.
[0007] Optionally, in one embodiment of the present application, the construction of the wind power-thermal power joint optimization scheduling model based on low wind power output includes: establishing the objective function of the wind power-thermal power joint optimization scheduling model; generating the wind power-thermal power joint optimization scheduling model based on power balance constraints, flow constraints and the objective function under cold wave extreme weather conditions.
[0008] Optionally, in one embodiment of the present application, the objective function is:
[0009]
[0010] in, is the power generation cost of thermal power unit i in period t, is the startup cost of thermal power unit i in period t, is the shutdown cost of thermal power unit i in period t, is the power supply shortage cost of wind farm j in period t under cold wave weather.
[0011] Optionally, in one embodiment of the present application, the prediction formula of the wind power output power model under cold wave weather is:
[0012]
[0013] in, represents the predicted wind power, x jRepresents random noise in Gaussian distribution, and G represents the trained generator in the generative adversarial network.
[0014] Optionally, in one embodiment of the present application, the wind power-load historical power data matrix in the matrix segmentation strategy is:
[0015]
[0016] Among them, p w,t 、p load,t They are the vector matrices of wind power and load active power under cold wave weather. The first item in the brackets is the wind power data matrix, k∈K represents the number of wind farms, the horizontal term represents the active power of the kth wind farm and K wind farms from time t to t+T, and the vertical term represents the active power from the kth to Kth wind farms at time t+T. The second item in the brackets is the load data matrix, q∈Q represents the number of load areas, the horizontal term represents the active power of the qth load and Qth load from time t to t+T, and the vertical term represents the active power of the load from the qth to Qth area at time t+T.
[0017] A second aspect of the present application provides an electric power system optimization device for large-scale wind power grid-connected with consideration of cold wave weather, including: a first acquisition module, for collecting cold wave weather information of the environment in which the power system is located; a first acquisition module, for obtaining low wind power output values under cold wave weather based on the cold wave weather information, using a pre-built wind power output power model under cold wave weather based on a distance-generative adversarial network; a second acquisition module, for obtaining unit output and power flow distribution under cold wave weather based on the low wind power output values under cold wave weather, using a pre-built wind power-thermal power joint optimization scheduling model of low wind power output; an optimization module, for performing matrix decomposition of wind power and load based on the unit output and the power flow distribution, using a matrix partitioning strategy, to optimize the power system.
[0018] Optionally, in one embodiment of the present application, it further includes: a second acquisition module, used to collect cold wave wind power characteristics in historical data before obtaining the low wind power output value under the cold wave weather; an establishment module, used to generate wind power generation power under the cold wave according to the cold wave wind power characteristics, so as to establish the wind power output power model under the cold wave weather based on the distance-generative adversarial network; a construction module, used to deal with the uncertainty brought by all cold wave weather based on the optimal minimum expected system total cost of the power system, and to construct the wind power-thermal power joint optimization scheduling model based on the low wind power output;
[0019] Optionally, in one embodiment of the present application, the construction module includes: an establishment unit for establishing the objective function of the wind power-thermal power joint optimization scheduling model; a generation unit for generating the wind power-thermal power joint optimization scheduling model based on the power balance constraints, power flow constraints and the objective function under cold wave extreme weather conditions.
[0020] Optionally, in one embodiment of the present application, the objective function is:
[0021]
[0022] in, is the power generation cost of thermal power unit i in period t, is the startup cost of thermal power unit i in period t, is the shutdown cost of thermal power unit i in period t, is the power supply shortage cost of wind farm j in period t under cold wave weather.
[0023] Optionally, in one embodiment of the present application, the prediction formula of the wind power output power model under cold wave weather is:
[0024]
[0025] in, represents the predicted wind power, x j Represents random noise in Gaussian distribution, and G represents the trained generator in the generative adversarial network.
[0026] Optionally, in one embodiment of the present application, the wind power-load historical power data matrix in the matrix segmentation strategy is:
[0027]
[0028] Among them, p w,t 、p load,t They are the vector matrices of wind power and load active power under cold wave weather. The first item in the brackets is the wind power data matrix, k∈K represents the number of wind farms, the horizontal term represents the active power of the kth wind farm and K wind farms from time t to t+T, and the vertical term represents the active power from the kth to Kth wind farms at time t+T. The second item in the brackets is the load data matrix, q∈Q represents the number of load areas, the horizontal term represents the active power of the qth load and Qth load from time t to t+T, and the vertical term represents the active power of the load from the qth to Qth area at time t+T.
[0029] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the power system optimization method for large-scale wind power grid connection taking into account cold wave weather as described in the above embodiment.
[0030] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above-mentioned power system optimization method for large-scale wind power grid connection considering cold wave weather.
[0031] The fifth aspect of the present application provides a computer program product, including a computer program, which, when executed, is used to implement the above-mentioned power system optimization method for large-scale wind power grid connection considering cold wave weather.
[0032] The embodiment of the present application can link the system power outage with the start and stop of the unit and the fluctuation of the cross-section flow according to the low output of the wind power cluster, the standby of the thermal power unit and the network topology information under the cold wave weather, and construct a wind farm power output power model under the cold wave weather based on the distance-generation adversarial network, a wind power-thermal power joint optimization scheduling model based on the low output of wind power and a matrix partitioning strategy, and quickly calculate the optimization scheme of the power system. In this way, the power system can be optimized normally in the case of insufficient samples, and the uncertainty brought to the power system by the cold wave weather can be dealt with with the minimum expected system total cost, the calculation speed of the system operation can be effectively improved, and the power system can be finely dispatched and controlled. This solves the problem that the power system optimization methods in the related art are mostly oriented to general extreme weather, lack of power system optimization methods for cold wave weather, sudden changes in wind speed, increase in load, and differences in new energy power generation capacity under cold wave weather, which may increase the difficulty of operation and scheduling of the power system to a certain extent, and how to effectively finely dispatch and control the power system under the high uncertainty brought by the cold wave weather.
[0033] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:
[0035] Figure 1 A flowchart of a power system optimization method for large-scale wind power grid connection considering cold wave weather provided according to an embodiment of the present application;
[0036] Figure 2A flowchart of a power system optimization method for large-scale wind power grid connection considering cold wave weather according to one embodiment of the present application;
[0037] Figure 3 A schematic diagram of the structure of a power system optimization device for large-scale wind power grid connection considering cold wave weather provided in accordance with an embodiment of the present application;
[0038] Figure 4 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application.
[0039] Reference numerals:
[0040] 10-Electric power system optimization device for large-scale wind power grid connection considering cold wave weather: 100-first acquisition module, 200-first acquisition module, 300-second acquisition module and 400-optimization module; 401-memory, 402-processor and 403-communication interface. DETAILED DESCRIPTION
[0041] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.
[0042] The following is a description of the power system optimization method for large-scale wind power grid connection considering cold wave weather in the embodiment of the present application with reference to the accompanying drawings. The power system optimization methods in the related technologies mentioned in the above background technology are mostly oriented to general extreme weather, and lack power system optimization methods for cold wave weather. The sudden change of wind speed, the increase of load, and the difference of new energy power generation capacity in cold wave weather may increase the operation difficulty and scheduling difficulty of the power system to a certain extent. How to effectively finely dispatch and control the power system under the high uncertainty brought by cold wave weather, the present application provides a power system optimization method for large-scale wind power grid connection considering cold wave weather, in which the system power outage can be linked to the start and stop of the unit and the section flow fluctuation according to the low output of the wind power cluster, the standby of the thermal power unit and the network topology information under the cold wave weather, and the distance-generation adversarial network is used to generate the wind farm power output power model under cold wave weather, the wind power-thermal power joint optimization scheduling model based on the low output of wind power and the matrix partitioning strategy, and the power system optimization scheme is quickly calculated. This makes it possible to optimize the power system normally even when there are insufficient samples, and to deal with the uncertainty brought to the power system by cold wave weather with the minimum expected total system cost, effectively improving the calculation speed of system operation, and finely dispatching and controlling the power system. This solves the problem that the power system optimization methods in related technologies are mostly aimed at general extreme weather, and lack power system optimization methods for cold wave weather. The sudden change of wind speed, increase in load, and difference in new energy power generation capacity in cold wave weather may increase the difficulty of power system operation and dispatch to a certain extent. How to effectively dispatch and control the power system finely under the high uncertainty brought by cold wave weather.
[0043] Specifically, Figure 1 A flow chart of a method for optimizing a power system for large-scale wind power grid connection taking into account cold wave weather provided in an embodiment of the present application.
[0044] like Figure 1 As shown, the power system optimization method for large-scale wind power grid connection considering cold wave weather includes the following steps:
[0045] In step S101, cold wave weather information of the environment in which the power system is located is collected.
[0046] It is understandable that cold snaps are often accompanied by strong cold air activity, which leads to sudden changes in wind speed. When the wind speed suddenly increases, the power generation efficiency of the wind farm will increase accordingly, but if the wind force is too strong and exceeds the bearing capacity of the wind turbine, it may cause the wind turbine to stop operating to ensure safety, and the wind power output will be close to 0. In addition, in cold snap weather, the increase in load will cause thermal power units to not only consume more fuel, but also need to start more units to ensure a stable supply of electricity and heat, which will lead to a substantial increase in operating costs.
[0047] Due to the different increase in electricity demand in different regions and the differences in renewable energy generation capacity, cold wave weather may cause changes in regional power flow distribution. In cold wave weather, due to the large fluctuations in power load, the cross-sectional power flow distribution between various regions of the power system will also change accordingly. This time-varying nature may increase the difficulty of power system operation and require more sophisticated scheduling and control.
[0048] In some embodiments, in order to more accurately optimize the dispatch of the power system during cold wave weather, the present application can obtain cold wave weather information of the environment in which the power system is located, and use the cold wave weather information as a powerful data support for optimizing the power system.
[0049] For example, the most notable feature of cold wave weather is the sharp drop in temperature, which may have a significant impact on the normal operation of the power system. Extreme low temperatures may cause the insulation materials of power lines and cables to become brittle, increasing the risk of equipment short circuits and breakdowns; at the same time, low temperatures may also reduce the mechanical and electrical properties of power equipment, increasing the possibility of failures.
[0050] For example, during cold snaps, moisture in the air easily condenses into ice and adheres to the surfaces of power lines, insulators and other equipment. Freezing increases the resistance of the lines, leading to increased power transmission losses and potentially causing safety hazards such as short circuits. At the same time, thick layers of ice may also increase the weight of the lines, causing them to sag or break.
[0051] In addition, cold waves are often accompanied by strong cold winds, which may cause physical damage to power facilities, such as causing power lines to sway or even break; at the same time, it may also blow down power towers and cause more serious power outages.
[0052] Furthermore, the degree and form of impact of cold wave weather in different regions may vary. For example, some regions may be more susceptible to the direct impact of cold wave weather, such as high-altitude areas and coastal areas, while other regions may be less affected.
[0053] When obtaining cold wave weather information, the embodiments of the present application can specifically obtain the cold wave weather information in the environment where the power system is located, so that when formulating power system optimization strategies based on the cold wave weather information, it is more in line with the application in actual scenarios, which helps to maintain the stable operation of the power system.
[0054] Step S102, based on the cold wave weather information, using a pre-built wind power output power model under cold wave weather based on a distance-generative adversarial network to obtain a low wind power output value under cold wave weather.
[0055] In some embodiments, the wind power cluster may have low output due to the influence of rapid wind speed changes, freezing of units, and reduced power generation efficiency caused by cold waves. However, when dispatching the power system, the output value of each thermal power unit, wind power unit, etc. is an indispensable consideration. For example, in actual application, the power system optimization strategy should be formulated based on the actual output value of each wind power unit.
[0056] Based on this, the present application can construct a wind power output power model under cold wave weather based on a distance-generative adversarial network, and use the model to obtain the low output value of wind power under cold wave weather, which can be used in subsequent power system optimization plans.
[0057] Next, the construction process of the wind power output power model under cold wave weather based on the distance-generative adversarial network in the embodiment of the present application is further explained.
[0058] Optionally, in one embodiment of the present application, before obtaining the low wind power output value in cold wave weather, it also includes: collecting cold wave wind power characteristics in historical data; generating wind power generation power in cold waves according to the cold wave wind power characteristics, so as to establish a wind power output power model in cold wave weather based on a distance-generative adversarial network; based on the optimal minimum expected system total cost of the power system to deal with the uncertainty brought by all cold wave weather, a wind power-thermal power joint optimization scheduling model based on low wind power output is constructed.
[0059] Among them, the prediction formula of the wind power output model under cold wave weather can be expressed as:
[0060]
[0061] in, represents the predicted wind power, x j Represents random noise in Gaussian distribution, and G represents the trained generator in the generative adversarial network.
[0062] In certain embodiments, when the present application establishes a wind power output power model under cold wave weather based on a distance-generative adversarial network, it mainly but is not limited to utilizing the cold wave wind power characteristics in the historical data of the power system, generating wind power generation power under cold waves through the cold wave wind power characteristics, and then constructing a generative adversarial network based on the wind power generation power, thereby establishing a wind power output power model under cold wave weather based on a distance-generative adversarial network.
[0063] For example, when establishing the wind power output model under cold wave weather, the present application mainly but not limited to utilizes a generative adversarial network based on Wasserstein distance (also known as Earth Mover's Distance (EMD), which is a method of measuring the difference between two probability distributions). The generative adversarial network here can be understood as a deep learning model, which can capture the cold wave wind power characteristics in the historical data of the power system through the network, and utilize the cold wave wind power characteristics to generate wind power generation under cold waves, so as to construct a generative adversarial network based on the wind power generation power.
[0064] Specifically, the generative adversarial network in the embodiment of the present application mainly but not limited to includes a generator G and a discriminator D. During the training process, the generator will continuously use random noise to generate samples to try to deceive the discriminator until the discriminator loses the ability to judge the authenticity of the data samples. At this time, the data samples generated by the generator approximately fit the distribution P of the real data. r . WG Represents the generator loss function of the network, Loss WD Represents the discriminator loss function, and the objective function expression can be expressed as follows:
[0065]
[0066] Among them, r represents a set of real data, x represents a set of data that satisfies the Gaussian distribution P x The random noise, θ G and θ D are the neural network weights of the generator and the discriminator respectively.
[0067] The wind power output power model under cold wave weather based on the distance-generative adversarial network can be used to obtain the predicted power generation, and the low output value of wind power under cold wave weather can be obtained through the predicted power generation. For example, when the generative adversarial network in the embodiment of the present application is trained, the Gaussian noise x i To generate forecast wind power The formula can be expressed as follows:
[0068]
[0069] in, represents the predicted wind power, x j Represents random noise in Gaussian distribution, and G represents the trained generator in the generative adversarial network.
[0070] Furthermore, the embodiment of the present application also constructs a wind power-thermal power joint optimization scheduling model based on low wind power output, so as to cope with the uncertainties brought by all cold wave weather through the minimum expected system total cost. The process is further explained below.
[0071] Optionally, in one embodiment of the present application, a wind power-thermal power joint optimization dispatch model based on low wind power output is constructed, including: establishing an objective function of the wind power-thermal power joint optimization dispatch model; generating a wind power-thermal power joint optimization dispatch model based on power balance constraints, power flow constraints and objective functions under extreme weather conditions of cold waves. The objective function can be expressed as:
[0072]
[0073] in, is the power generation cost of thermal power unit i in period t, is the startup cost of thermal power unit i in period t, is the shutdown cost of thermal power unit i in period t, is the power supply shortage cost of wind farm j in period t under cold wave weather.
[0074] In the actual implementation process, this application considers the various constraints that may be encountered in actual application when constructing a wind power-thermal power joint optimization dispatch model based on low wind power output by considering the minimum expected system total cost to cope with the uncertainty brought by all cold wave weather. Therefore, when establishing the model, in addition to the objective function, multiple constraints are set, including but not limited to power balance constraints and flow constraints. The specific process can be expressed as follows:
[0075] First, the objective function of the minimum expected system total cost is established, which can be expressed as follows:
[0076]
[0077] in, is the power generation cost of thermal power unit i in period t, is the startup cost of thermal power unit i in period t, is the shutdown cost of thermal power unit i in period t, is the power supply shortage cost of wind farm j in period t under cold wave weather.
[0078] Next, consider the constraints contained in the unit commitment model for cold wave extreme weather, which can be expressed as follows:
[0079] (1) Power balance constraint, which can be expressed as follows:
[0080]
[0081] Where K is the number of system nodes, is the load of power system node k in period t, u i,t is the start and stop status of thermal power unit i in period t, P i,t , are the active power of thermal power unit i, wind farm j, and standby unit s in time period t, is the power shortage power of the power system during period t.
[0082] The power shortage rate is used to better reflect the power shortage situation. The power shortage rate formula can be expressed as follows:
[0083]
[0084] The wind power utilization rate is used to measure the operating efficiency of the wind farm. The formula can be expressed as follows:
[0085]
[0086] in, represents the wind power utilization rate of wind farm j at time t, Represents the installed capacity of wind farm j.
[0087] (2) Tidal constraints under cold waves
[0088]
[0089] Among them, G represents the transfer distribution factor matrix, G l-a Describes the impact of the injected power of node a on line l, G l-b Describes the impact of the injected power of node b on line l, P a,t represents the injected active power of the thermal power unit at node a during period t, P b,t represents the injected active power of the thermal power unit at node b during period t, represents the actual injected active power of the wind turbine at node a during period t, represents the actual active power injected by the wind turbine at node b during period t, represents the injected active power of the standby unit at node a during period t, represents the injected active power of the standby unit at node b during period t, P l Indicates the lower limit of active power allowed to pass through line l, Indicates the upper limit of active power allowed to pass through line 1.
[0090] After establishing the objective function of minimum expected system total cost, combined with power balance constraints and power flow constraints under cold wave weather, a wind power-thermal power joint optimization scheduling model based on low wind power output in the embodiment of the present application can be established.
[0091] The embodiment of the present application can integrate certain constraints when constructing a wind power-thermal power joint optimization scheduling model based on low wind power output, so that the actual model is more in line with actual application needs, greatly improving the practical application capabilities of power system scheduling optimization.
[0092] Step S103, based on the low output value of wind power under cold wave weather, a pre-built wind power-thermal power joint optimization dispatch model for low wind power output is used to obtain the unit output and power flow distribution under cold wave weather.
[0093] In other embodiments, after constructing a wind power-thermal power joint optimization scheduling model for low wind power output, the embodiments of the present application can use the model to obtain the output of each unit under cold wave weather and the power flow distribution in the power system under the influence of cold wave weather, so as to formulate corresponding power system optimization strategies according to the output of each unit and the power flow distribution of the cold wave.
[0094] The unit output here can be understood as the total output of various new energy sources including but not limited to wind turbines, thermal power units, etc. The power flow distribution here can be understood as the transmission direction and power size of power (including active power and reactive power) in the power system under the influence of cold wave weather, such as information on power flow direction and power quantity.
[0095] Next, the process of how to formulate corresponding power system optimization strategies based on the output of each wind turbine and the distribution of cold wave currents is further explained.
[0096] Step S104: Based on the unit output and power flow distribution, the wind power and load are matrix-decomposed using the matrix partitioning strategy to optimize the power system. The wind power-load historical power data matrix in the matrix partitioning strategy can be expressed as:
[0097]
[0098] Among them, p w,t 、p load,tThey are the vector matrices of wind power and load active power under cold wave weather. The first item in the brackets is the wind power data matrix, k∈K represents the number of wind farms, the horizontal term represents the active power of the kth wind farm and K wind farms from time t to t+T, and the vertical term represents the active power from the kth to Kth wind farms at time t+T. The second item in the brackets is the load data matrix, q∈Q represents the number of load areas, the horizontal term represents the active power of the qth load and Qth load from time t to t+T, and the vertical term represents the active power of the load from the qth to Qth area at time t+T.
[0099] As a possible implementation method, after obtaining the output of each wind turbine under cold weather and the power flow distribution in the power system caused by the cold weather, the present application can use a matrix segmentation strategy to decompose wind power and load to achieve scheduling optimization of the power system.
[0100] Among them, the matrix partitioning strategy can help better understand and control the intermittency of wind power and the volatility of load, thereby improving the stability and economy of the system. In the embodiment of the present application, it is mainly used to improve the calculation speed of system operation. Specifically, when establishing the matrix partitioning strategy, the wind power and load active power under historical cold wave weather can be collected first, and the wind power-load historical power data matrix can be constructed. The specific matrix is expressed as follows:
[0101]
[0102] Among them, p w,t 、p load,t They are the vector matrices of wind power and load active power under cold wave weather. The first item in the brackets is the wind power data matrix, k∈K represents the number of wind farms, the horizontal term represents the active power of the kth wind farm and K wind farms from time t to t+T, and the vertical term represents the active power from the kth to Kth wind farms at time t+T. The second item in the brackets is the load data matrix, q∈Q represents the number of load areas, the horizontal term represents the active power of the qth load and Qth load from time t to t+T, and the vertical term represents the active power of the load from the qth to Qth area at time t+T.
[0103] For example, Figure 2 This is a flow chart of a method for optimizing a power system by integrating large-scale wind power into the grid during cold wave weather according to an embodiment of the present application.
[0104] In step S201, the embodiment of the present application may first obtain weather information of cold wave weather.
[0105] Step S202, establishing a wind power output power model under cold wave weather based on a distance-generative adversarial network to obtain the low output value of wind power under cold wave weather.
[0106] Step S202, based on the low output value of wind power, a wind power-thermal power joint optimization dispatch model based on low wind power output is established to obtain the unit output and power flow distribution under cold wave weather.
[0107] Step S202, establish a matrix partitioning strategy, perform matrix decomposition on wind power and load, so as to optimize the power system. Specifically, this step can be expanded as follows:
[0108] Based on the information of unit output and flow distribution under cold wave weather, combined with the location, capacity and power generation characteristics of the wind farm, a wind power-load historical power data matrix is constructed, and the specific form can be shown in formula (10). Then, the wind power-load historical power data matrix is segmented according to the geographical location, grid structure or management area. For example, the matrix is segmented spatially according to the area of wind farms and loads, or the matrix is segmented temporally according to the temporal characteristics of wind power and loads (such as seasonality, daily periodicity, etc.).
[0109] Next, the wind power-thermal power joint optimization dispatch model based on low wind power output in the embodiment of the present application is solved based on the minimization cost objective function constructed in the embodiment of the present application and the constraints such as power balance constraint and power flow constraint. During the optimization process, the matrix partitioning strategy operation is used to quickly process wind power and load data, such as calculating supply and demand balance, evaluating system status, etc.
[0110] Furthermore, after obtaining the power system optimization plan, it can also be analyzed to evaluate its impact on the stability, economy and environmental protection of the power system, so as to formulate specific dispatching strategies based on the analysis results, including but not limited to the allocation of wind power and load, the start and stop plan of generators, etc. In addition, in actual operation, the dispatching strategy can also be dynamically adjusted and optimized based on real-time data and system feedback.
[0111] The embodiment of the present application can utilize a matrix segmentation strategy to decompose wind power and load, which can effectively improve the dispatching efficiency and optimization level of the power system, thereby meeting the growing power demand and sustainable development requirements.
[0112] According to the power system optimization method for large-scale wind power grid connection considering cold wave weather proposed in the embodiment of the present application, the system power outage can be linked to the start and stop of the unit and the fluctuation of the cross-section flow according to the low output of the wind power cluster, the standby of the thermal power unit and the network topology information under the cold wave weather, and the wind power output power model under the cold wave weather is generated based on the distance-generation adversarial network, and the wind power-thermal power joint optimization scheduling model and matrix partitioning strategy based on the low output of wind power are constructed to quickly calculate the power system optimization scheme. In this way, the power system can still be optimized normally in the case of insufficient samples, and the uncertainty brought to the power system by the cold wave weather can be dealt with at the minimum expected system total cost, the calculation speed of the system operation can be effectively improved, and the power system can be finely dispatched and controlled. This solves the problem that the power system optimization methods in the related art are mostly oriented to general extreme weather, lack of power system optimization methods for cold wave weather, sudden changes in wind speed, increase in load, and differences in new energy power generation capacity under cold wave weather may increase the difficulty of operation and scheduling of the power system to a certain extent, and how to effectively finely dispatch and control the power system under the high uncertainty brought by cold wave weather.
[0113] Next, a power system optimization device for large-scale wind power grid connection taking into account cold wave weather proposed in an embodiment of the present application will be described with reference to the accompanying drawings.
[0114] Figure 3 It is a structural schematic diagram of an electric power system optimization device for large-scale wind power grid connection considering cold wave weather according to an embodiment of the present application.
[0115] like Figure 3 As shown, the power system optimization device 10 for large-scale wind power grid connection in consideration of cold wave weather includes: a first acquisition module 100 , a first acquisition module 200 , a second acquisition module 300 and an optimization module 400 .
[0116] The first collection module 100 is used to collect cold wave weather information of the environment where the power system is located;
[0117] The first acquisition module 200 is used to obtain the low output value of wind power under cold wave weather based on the cold wave weather information by using a pre-built wind power output power model under cold wave weather based on a distance-generative adversarial network;
[0118] The second acquisition module 300 is used to obtain the unit output and power flow distribution under the cold wave weather based on the low output value of wind power under the cold wave weather by using the pre-built wind power-thermal power joint optimization dispatch model of low wind power output;
[0119] The optimization module 400 is used to perform matrix decomposition of wind power and load based on the unit output and power flow distribution by using a matrix partitioning strategy to optimize the power system.
[0120] Optionally, in one embodiment of the present application, it also includes: a second acquisition module, an establishment module and a construction module.
[0121] The second acquisition module is used to collect cold wave wind power characteristics in historical data before obtaining the low output value of wind power in cold wave weather;
[0122] Establish a module for generating wind power generation under cold waves according to the characteristics of cold wave wind power, so as to establish a wind power output power model under cold wave weather based on distance-generative adversarial network;
[0123] A construction module is used to deal with the uncertainty brought by all cold wave weather based on the minimum expected system total cost of the power system optimization, and to build a wind power-thermal power joint optimization dispatch model based on low wind power output;
[0124] Optionally, in one embodiment of the present application, the construction module includes: a building unit and a generating unit.
[0125] Among them, a unit is established to establish the objective function of the wind power-thermal power joint optimization dispatch model;
[0126] A generation unit is used to generate a wind power-thermal power joint optimization scheduling model based on power balance constraints, power flow constraints and objective functions under cold wave extreme weather conditions.
[0127] Optionally, in one embodiment of the present application, the objective function can be expressed as:
[0128]
[0129] in, is the power generation cost of thermal power unit i in period t, is the startup cost of thermal power unit i in period t, is the shutdown cost of thermal power unit i in period t, is the power supply shortage cost of wind farm j in period t under cold wave weather.
[0130] Optionally, in one embodiment of the present application, the prediction formula of the wind power output power model under cold wave weather can be expressed as:
[0131]
[0132] in, represents the predicted wind power, x j Represents random noise in Gaussian distribution, and G represents the trained generator in the generative adversarial network.
[0133] Optionally, in one embodiment of the present application, the wind power-load historical power data matrix in the matrix partitioning strategy can be expressed as:
[0134]
[0135] Among them, p w,t 、p load,t They are the vector matrices of wind power and load active power under cold wave weather. The first item in the brackets is the wind power data matrix, k∈K represents the number of wind farms, the horizontal term represents the active power of the kth wind farm and K wind farms from time t to t+T, and the vertical term represents the active power from the kth to Kth wind farms at time t+T. The second item in the brackets is the load data matrix, q∈Q represents the number of load areas, the horizontal term represents the active power of the qth load and Qth load from time t to t+T, and the vertical term represents the active power of the load from the qth to Qth area at time t+T.
[0136] It should be noted that the aforementioned explanation of the embodiment of the power system optimization method for large-scale wind power grid-connected considering cold wave weather is also applicable to the power system optimization device for large-scale wind power grid-connected considering cold wave weather of this embodiment, and will not be repeated here.
[0137] According to the power system optimization device for large-scale wind power grid connection considering cold wave weather proposed in the embodiment of the present application, the system power outage can be linked to the start and stop of the unit and the fluctuation of the cross-section flow according to the low output of the wind power cluster, the standby of the thermal power unit and the network topology information under the cold wave weather, and the wind farm power output power model under the cold wave weather is generated based on the distance-generation adversarial network, and the wind power-thermal power joint optimization scheduling model based on the low output of wind power and the matrix partitioning strategy are constructed to quickly calculate the power system optimization scheme. In this way, the power system can still be optimized normally in the case of insufficient samples, and the uncertainty brought to the power system by the cold wave weather can be dealt with with the minimum expected system total cost, the calculation speed of the system operation can be effectively improved, and the power system can be finely dispatched and controlled. This solves the problem that the power system optimization methods in the related art are mostly oriented to general extreme weather, lack of power system optimization methods for cold wave weather, sudden changes in wind speed, increase in load, and differences in new energy power generation capacity under cold wave weather may increase the difficulty of operation and scheduling of the power system to a certain extent, and how to effectively finely dispatch and control the power system under the high uncertainty brought by the cold wave weather.
[0138] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:
[0139] Memory 401 , processor 402 , and a computer program stored in the memory 401 and executable on the processor 402 .
[0140] When the processor 402 executes the program, the power system optimization method for large-scale wind power grid connection considering cold wave weather provided in the above embodiment is implemented.
[0141] Furthermore, the electronic device further comprises:
[0142] The communication interface 403 is used for communication between the memory 401 and the processor 402 .
[0143] The memory 401 is used to store computer programs that can be executed on the processor 402 .
[0144] The memory 401 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.
[0145] If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0146] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can communicate with each other through an internal interface.
[0147] The processor 402 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.
[0148] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned power system optimization method for large-scale wind power grid connection taking into account cold wave weather.
[0149] An embodiment of the present application also provides a computer program product, including a computer program, which can run computer instructions. When the computer instructions are executed by a processor, the power system optimization method for large-scale wind power grid connection considering cold wave weather provided in the embodiment of the present application is implemented.
[0150] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.
[0151] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
[0152] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.
[0153] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.
[0154] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of multiple of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0155] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.
[0156] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.
[0157] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.
Claims
1. A method for optimizing a power system for large-scale wind power grid connection in consideration of cold wave weather, characterized in that: The following steps are involved: Collect cold wave weather information in the environment where the power system is located; Based on the cold wave weather information, a pre-constructed wind power output power model under cold wave weather based on a distance-generative adversarial network is used to obtain a low output value of wind power under cold wave weather; Based on the low wind power output value under the cold wave weather, a pre-built wind power-thermal power joint optimization dispatch model for low wind power output is used to obtain the unit output and power flow distribution under the cold wave weather; Based on the unit output and the power flow distribution, a matrix partitioning strategy is used to perform matrix decomposition on wind power and load to optimize the power system.
2. The method according to claim 1, characterized in that Before obtaining the low output value of wind power in the cold wave weather, the method further includes: Collect cold wave wind power characteristics from historical data; Generate wind power generation power under cold wave according to the cold wave wind power characteristics, so as to establish the wind power output power model under cold wave weather based on the distance-generative adversarial network; Based on the minimum expected total system cost of the power system optimization to cope with the uncertainties brought by all cold wave weather, the wind power-thermal power joint optimization scheduling model based on low wind power output is constructed.
3. The method according to claim 2, characterized in that The construction of the wind power-thermal power joint optimization dispatch model based on low wind power output includes: Establishing the objective function of the wind power-thermal power joint optimization scheduling model; The wind power-thermal power joint optimization scheduling model is generated based on the power balance constraints, power flow constraints and the objective function under the cold wave extreme weather conditions.
4. The method according to claim 3, characterized in that The objective function is: in, is the power generation cost of thermal power unit i in period t, is the startup cost of thermal power unit i in period t, is the shutdown cost of thermal power unit i in period t, is the power supply shortage cost of wind farm j in period t under cold wave weather.
5. The method according to claim 1, characterized in that The prediction formula of the wind power output model under the cold wave weather is: in, represents the predicted wind power, x j Represents random noise in Gaussian distribution, and G represents the trained generator in the generative adversarial network.
6. The method according to claim 1, characterized in that The wind power-load historical power data matrix in the matrix partitioning strategy is: Among them, p w,t 、p load,t They are the vector matrices of wind power and load active power under cold wave weather. The first item in the brackets is the wind power data matrix, k∈K represents the number of wind farms, the horizontal term represents the active power of the kth wind farm and K wind farms from time t to t+T, and the vertical term represents the active power from the kth to Kth wind farms at time t+T. The second item in the brackets is the load data matrix, q∈Q represents the number of load areas, the horizontal term represents the active power of the qth load and Qth load from time t to t+T, and the vertical term represents the active power of the load from the qth to Qth area at time t+T.
7. A power system optimization device for large-scale wind power grid connection considering cold wave weather, characterized in that: include: A collection module is used to collect cold wave weather information in the environment where the power system is located; A first acquisition module is used to obtain a low output value of wind power under cold wave weather based on the cold wave weather information by using a pre-built wind power output power model under cold wave weather based on a distance-generative adversarial network; The second acquisition module is used to obtain the unit output and power flow distribution under the cold wave weather based on the low output value of wind power under the cold wave weather by using a pre-built wind power-thermal power joint optimization dispatch model of low wind power output; The optimization module is used to perform matrix decomposition of wind power and load based on the unit output and the power flow distribution by using a matrix partitioning strategy to optimize the power system.
8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the power system optimization method for large-scale wind power grid connection taking into account cold wave weather as described in any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement a power system optimization method for large-scale wind power grid connection considering cold wave weather as described in any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed, it is used to implement the power system optimization method for large-scale wind power grid connection considering cold wave weather as described in any one of claims 1 to 6.
