Optimization control method and device of power grid and power grid optimization system

Abstract

The invention provides a power grid optimization control method and device and a power grid optimization system. The method comprises the steps of obtaining related data of a power grid; a control optimization model is constructed, the control optimization model is obtained through training by using multiple sets of training data through an NSWOA algorithm, each set of training data in the multiple sets of training data comprises historical related data obtained in a historical time period and historical optimization data corresponding to the historical related data, and the historical optimization data correspond to the historical related data; the historical optimization data is data of a strategy for at least carrying out optimization control on a historical output value and historical power distribution of the power equipment; inputting the related data into a control optimization model to obtain optimization data corresponding to the related data; and controlling operation of power equipment of the power grid according to the optimization data corresponding to the related data. According to the scheme, the problem of poor stability of power grid operation in the prior art is solved.

Description

Technical Field

[0001] The present application relates to power grid optimization, and more specifically, to a power grid optimization control method, device, computer program product, and power grid optimization system. Background Art

[0002] With the continuous expansion of renewable energy power generation and the increase in the proportion of grid connection, the volatility and uncertainty of renewable energy power generation output have become increasingly prominent, bringing a series of major challenges and risks to the operation of the power grid. The volatility of renewable energy power generation poses a challenge to the stability of power grid load, which may cause frequent grid tripping, voltage fluctuations and other problems, thus posing a serious threat to the safe and stable operation of the power grid.

[0003] The uncertainty of renewable energy generation makes grid dispatching more complicated, and it is difficult for dispatchers to accurately predict renewable energy output, which significantly increases the risk of grid operation. As the scale of the grid expands and load demand increases, the difficulty of safe and stable operation of the grid continues to increase, and the grid faces more severe security risks and challenges. Summary of the invention

[0004] The main purpose of the present application is to provide a power grid optimization control method, device, computer program product and power grid optimization system to at least solve the problem of poor stability of power grid operation in the prior art.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for optimizing control of a power grid is provided, comprising: obtaining relevant data of the power grid, wherein the relevant data include one or more of the output power, load and operating cost of the power equipment, and the power equipment includes one or more of wind power equipment, photovoltaic equipment and thermal power unit equipment; constructing a control optimization model, wherein the control optimization model is obtained by training through the NSWOA algorithm using multiple groups of training data, and each group of training data in the multiple groups of training data includes historical relevant data obtained within a historical time period and historical optimization data corresponding to the historical relevant data, wherein the historical optimization data is data of a strategy for optimizing control of at least the historical output value and historical power distribution of the power equipment; inputting the relevant data into the control optimization model to obtain optimization data corresponding to the relevant data; and controlling the operation of the power equipment of the power grid according to the optimization data corresponding to the relevant data.

[0006] Optionally, obtaining relevant data of the power grid includes: obtaining initial relevant data at a first moment; analyzing the initial relevant data using a target algorithm to obtain the relevant data at a second moment, wherein the target algorithm includes at least one or more of linear regression, time series analysis, random forest, neural network, and support vector machine, and the first moment is earlier than the second moment.

[0007] Optionally, after acquiring relevant data of the power grid, the method further includes: performing a risk assessment on the power grid based on the relevant data to obtain an assessment result; and optimizing and controlling the power equipment of the power grid when the assessment result indicates that the power grid has risks.

[0008] Optionally, a risk assessment is performed on the power grid based on the relevant data to obtain an assessment result, including: when the relevant data meets preset conditions, determining that the power grid is at risk; when the relevant data does not meet the preset conditions, determining that the power grid is not at risk, wherein the preset conditions include one or more of the output power being greater than a maximum power threshold, the output power being less than a minimum power threshold, the load rate corresponding to the load being greater than a maximum load rate, and the operating cost being greater than a preset cost.

[0009] Optionally, before constructing the control optimization model, the method further includes: obtaining a first objective function, wherein the first objective function is a function used for model training when constructing the control optimization model, wherein the first objective function is:

[0010] P g =P f,t -P w,t -P l,t +P c,t -P d,t ,

[0011] minF1 represents the first objective function, S T represents the s intervals divided by the scheduling period T, P g represents the net load value at time t, Represents the average net load in a scheduling cycle, P f,t represents the load power at time t, P w,t represents the actual grid-connected power of the wind power equipment at time t, P l,t represents the actual grid-connected power of the photovoltaic device at time t, P c,t represents the charging power of the energy storage system at time t, P d,t Represents the discharge power of the energy storage system at time t.

[0012] Optionally, before constructing the control optimization model, the method further includes: obtaining a second objective function, wherein the second objective function is a function used for model training when constructing the control optimization model, wherein the second objective function is:

[0013] minF2=J wlf (U)+F h,

[0014] minF2 represents the second objective function, J wlf (U) represents the risk value of the power grid, F h represents the coal consumption cost of the thermal power unit equipment, S G represents the total number of thermal power units, β 1,i represents the first consumption coefficient of the thermal power unit equipment, β 1,i ∈[0,0.01], P i,t represents the output value of the thermal power unit at time t, β 2,i represents the second consumption coefficient of the thermal power unit equipment, β 2,i ∈[15,30],β 3,i represents the third consumption coefficient of the thermal power unit equipment, β 3,i ∈[0,1000].

[0015] Optionally, before constructing the control optimization model, the method also includes: obtaining constraint conditions, wherein the constraint conditions are conditions used for model training when constructing the control optimization model, wherein the constraint conditions include one or more of a first constraint condition on grid flow, a second constraint condition on power balance, a third constraint condition on the output of the wind power equipment, a fourth constraint condition on the output of the photovoltaic equipment, a fifth constraint condition on the output of the thermal power unit equipment, and a sixth constraint condition on the operation of the energy storage system.

[0016] According to another aspect of the present application, an optimization control device for a power grid is provided, comprising: a first acquisition unit, used to acquire relevant data of the power grid, wherein the relevant data include one or more of the output power, load and operating cost of the power equipment, and the power equipment includes one or more of wind power equipment, photovoltaic equipment and thermal power unit equipment; a construction unit, used to construct a control optimization model, wherein the control optimization model is obtained by training through the NSWOA algorithm using multiple groups of training data, and each group of training data in the multiple groups of training data includes historical relevant data acquired within a historical time period and historical optimization data corresponding to the historical relevant data, wherein the historical optimization data is data of a strategy for optimizing control of at least the historical output value and historical power distribution of the power equipment; a processing unit, used to input the relevant data into the control optimization model to obtain optimization data corresponding to the relevant data; a first control unit, used to control the operation of the power equipment of the power grid according to the optimization data corresponding to the relevant data.

[0017] According to another aspect of the present application, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the steps of any one of the methods for optimizing and controlling a power grid are implemented.

[0018] According to another aspect of the present application, a power grid optimization system is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing any one of the optimization control methods of the power grid.

[0019] By applying the technical solution of the present application, the NSWOA algorithm can effectively handle multi-objective optimization problems, retain a set of non-inferior solutions in the population through non-dominated sorting, and thus help decision makers find a balance between multiple conflicting objectives. The algorithm has strong global search capabilities and convergence speed, and can quickly find a better solution. Therefore, this solution uses the NSWOA algorithm to solve the optimization problem of the power grid, obtain the data of the optimization strategy, and then control the operation of the power grid. This can ensure that the power grid operates in a multi-objective balanced manner, thereby ensuring good stability of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0021] Figure 1 A hardware structure block diagram of a mobile terminal for executing an optimization control method for a power grid provided in an embodiment of the present application is shown;

[0022] Figure 2 A schematic diagram of a flow chart of an optimization control method for a power grid provided according to an embodiment of the present application is shown;

[0023] Figure 3 The flow chart of solving the optimization model of power grid preventive control considering risk assessment by using NSWOA algorithm is shown;

[0024] Figure 4 A flow chart of a method for optimizing power grid preventive control considering risk assessment is shown;

[0025] Figure 5 A structural block diagram of an optimization control device for a power grid provided according to an embodiment of the present application is shown.

[0026] The above drawings include the following reference numerals:

[0027] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0028] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0029] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] As introduced in the background technology, the stability of power grid operation in the prior art is poor. To solve the above problems, the embodiments of the present application provide a power grid optimization control method, device, computer program product and power grid optimization system.

[0032] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0033] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a method for optimizing and controlling a power grid according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0034] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the display method of device information in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal 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 a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0035] In this embodiment, a method for optimizing control of a power grid running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0036] Figure 2 FIG. 1 is a flow chart of a method for optimizing and controlling a power grid according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0037] Step S201, obtaining relevant data of the power grid, wherein the relevant data includes one or more of output power, load and operating cost of the power equipment, and the power equipment includes one or more of wind power equipment, photovoltaic equipment and thermal power unit equipment;

[0038] Specifically, wind power equipment uses wind power to drive the wind wheel to rotate, and the wind wheel drives the generator to generate electricity. Photovoltaic equipment uses solar photovoltaic cells to convert solar energy into electrical energy. Thermal power unit equipment uses fossil fuels such as coal, oil, and natural gas to burn and drive the generator to generate electricity.

[0039] Specifically, relevant data of the power equipment can be obtained, and the relevant data may include output power, load, and operating cost. Of course, it is not limited to the above-mentioned data, and can also be any other feasible data, such as voltage, current, operating time, temperature, humidity, pressure, power, etc.

[0040] Step S202, constructing a control optimization model, wherein the control optimization model is obtained by training with the NSWOA algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical related data acquired in a historical time period and historical optimization data corresponding to the historical related data, wherein the historical optimization data is data of a strategy for optimizing control of at least the historical output value and the historical power distribution of the power equipment;

[0041] Specifically, the NSWOA algorithm is used to solve the grid preventive control optimization model considering risk assessment to obtain an optimal dispatching scheme that meets multi-objective constraints. The NSWOA algorithm can be used for machine learning training to obtain a control optimization model.

[0042] Step S203, inputting the above-mentioned relevant data into the above-mentioned control optimization model to obtain optimization data corresponding to the above-mentioned relevant data;

[0043] Specifically, relevant data of the current power grid can be input into the control optimization model, and the control optimization model can output optimization data corresponding to the relevant data.

[0044] Step S204: controlling the operation of the power equipment of the power grid according to the optimization data corresponding to the related data.

[0045] Specifically, the obtained optimization data can be used to control the operation of the power grid to ensure better stability of the power grid.

[0046] Through this embodiment, the NSWOA algorithm can effectively handle multi-objective optimization problems, retain a set of non-inferior solutions in the population through non-dominated sorting, and thus help decision makers find a balance between multiple conflicting objectives. The algorithm has a strong global search capability and convergence speed, and can quickly find a better solution. Therefore, this scheme uses the NSWOA algorithm to solve the optimization problem of the power grid, obtain the data of the optimization strategy, and then control the operation of the power grid, so as to ensure that the power grid operates in a multi-objective balanced manner, thereby ensuring the stability of the power grid.

[0047] Specifically, the current grid dispatch lacks a preventive control optimization method that takes risk assessment into account, which results in the dispatchers lacking effective technical means to conduct real-time online risk prevention and control when facing the volatility of renewable energy output, making it difficult to effectively reduce the safety and stability risks of the grid. Traditional power system planning and operation modes are usually difficult to effectively adapt to this uncertainty, so a new method is urgently needed to optimize the preventive control strategy of the grid.

[0048] Therefore, this scheme establishes a model that takes into account the uncertainty of renewable energy output. According to the various risk indicators of the power grid, a data set for risk assessment is constructed. Considering the goal of minimizing the net load fluctuation of the power grid and minimizing the control cost of the power grid operation, the maximum absorption of renewable energy is achieved. At the same time, a risk optimization model for power grid security and stability that takes into account the uncertainty of wind power and photovoltaic output is constructed. The model is solved by the whale-based multi-objective optimization algorithm, and the optimal scheduling scheme is obtained.

[0049] This scheme can effectively optimize the preventive control strategy of the new energy power grid and ensure the stable operation of the power grid. It proposes an optimized control scheme for the power grid and finds an optimal scheduling scheme to ensure the safety and stability of the power grid. The NSWOA multi-objective optimization algorithm is used to solve the model, and a reasonable scheduling solution for energy storage equipment and adjusting the output of each unit is obtained. The NSWOA algorithm can effectively handle multi-objective optimization problems and provide a more accurate and efficient optimization solution for power grid preventive control.

[0050] Specifically, the NSWOA multi-objective optimization algorithm is used to solve the problem. The NSWOA algorithm is an evolutionary algorithm based on the whale optimization algorithm and non-dominated sorting. It can effectively handle multi-objective optimization problems and retain the set of non-inferior solutions in the population through non-dominated sorting, thereby helping decision makers find a balance between multiple conflicting goals. It uses the characteristics of the whale optimization algorithm, has strong global search capabilities and convergence speed, and can quickly find a better solution. It combines the advantages of multi-objective optimization and evolutionary algorithms and can achieve better performance in solving complex multi-objective optimization problems. The algorithm has a good convergence speed and uniformity of population distribution, can reduce the computational complexity of the cluster system, and uses an elite retention strategy to continue the excellent solution to speed up the convergence speed of the algorithm. The specific solution process is as follows: Figure 3 As shown, the optimal scheduling solution is finally obtained.

[0051] Initialize the population according to the preventive control optimization model of the power grid considering risk assessment, calculate the indicators corresponding to the individuals in the population, obtain the individual fitness value, update the fitness value, calculate the congestion, record the current optimal individual, update the calculation parameters a and vectors A and C, where parameter a represents the control parameter for adjusting the search range of each individual in the population, vectors A and C represent the distance vector between the previous whale individual and the randomly selected whale individual, and P is a random number between 0 and 1. If P is less than 0.5 and the absolute value of A is less than 1, then shrink the encirclement and conduct a local search. Apply the reverse learning strategy to all individuals and update the current optimal solution. If the absolute value of A is greater than or equal to 1, then shrink the encirclement and conduct a global search. If P is greater than or equal to 0.5, then update the position of the data spiral mechanism. According to the greedy criterion, select the optimal individual before and after the distribution disturbance is applied to the optimal individual. If the number of iterations K is less than the minimum number of iterations max_K, then continue to iterate, otherwise output the curve of the optimal scheduling plan.

[0052] In the specific implementation process, obtaining relevant data of the power grid can be achieved through the following steps: obtaining initial relevant data at a first moment; using a target algorithm to analyze the above initial relevant data to obtain the above relevant data at a second moment, wherein the above target algorithm includes at least one or more of linear regression, time series analysis, random forest, neural network, and support vector machine, and the above first moment is earlier than the above second moment.

[0053] In this solution, the target algorithm can be used to predict and analyze the initial relevant data, and the relevant data at the second moment can be predicted by the initial relevant data at the first moment. This can better understand the changing trends and laws of the data and help make more accurate predictions and decisions. At the same time, choosing different target algorithms can analyze the data more comprehensively and improve the accuracy and efficiency of data analysis.

[0054] Specifically, in this scheme, the characteristics of wind power and photovoltaic output can be analyzed to establish a data set that considers the uncertainty of new energy output, that is, relevant data; in a power grid with a high proportion of new energy access, the uncertainty set of wind power and photovoltaic output can be expressed as:

[0055]

[0056] G w represents the uncertain set of wind power output, G l represents the uncertain set of photovoltaic output, are the wind power and photovoltaic output values ​​at time t according to the actual dispatch decision of the power grid; are the predicted values ​​of wind power and photovoltaic power output of the power grid at time t respectively; are the upward and downward adjustment coefficients of wind power output at time t, They are the upward and downward adjustment coefficients of photovoltaic output at time t, and their values ​​are 0 or 1; They are the upward and downward adjustment power margins of wind power output at time t, They are the upward and downward adjustment power margins of the photovoltaic output at time t respectively; are the uncertainties of wind power and photovoltaic power in spatial scale respectively; N T is the uncertainty budget of wind power and photovoltaic power on a time scale; W and L are the total number of wind farms and photovoltaic power stations in the grid respectively; T is the optimized operation time period of the grid.

[0057]

[0058] Φ is the cumulative probability distribution function of the normal distribution; η∈(0,1) is the setting value of the significance level.

[0059] During the specific implementation process, after obtaining relevant data of the power grid, the above method also includes the following steps: performing risk assessment on the above power grid based on the above relevant data to obtain assessment results; when the above assessment results indicate that the above power grid has risks, optimizing and controlling the above power equipment of the above power grid.

[0060] In this scheme, the risk assessment of the power grid can also be carried out. If the power grid is risky, the power grid can be optimized and controlled. If the power grid is not risky, the power grid can be optimized and controlled, or not optimized and controlled. Through this scheme, it can be accurately determined whether the power grid is risky, and then the power grid can be optimized and controlled more accurately.

[0061] During the specific implementation process, a risk assessment is performed on the above-mentioned power grid based on the above-mentioned relevant data to obtain an assessment result, which can be achieved through the following steps: when the above-mentioned relevant data meets the preset conditions, it is determined that the above-mentioned power grid is risky; when the above-mentioned relevant data does not meet the above-mentioned preset conditions, it is determined that the above-mentioned power grid is not risky, wherein the above-mentioned preset conditions include one or more of the above-mentioned output power being greater than the maximum power threshold, the above-mentioned output power being less than the minimum power threshold, the load rate corresponding to the above-mentioned load being greater than the maximum load rate, and the above-mentioned operating cost being greater than the preset cost.

[0062] In this scheme, when relevant data meets the preset conditions, the power grid is considered to be at risk, and when relevant data does not meet the preset conditions, the power grid is considered to be not at risk. In this way, whether the power grid is at risk can be further accurately determined based on the preset conditions.

[0063] Specifically, by determining the various risk indicators of the power grid, analyzing the risk of wind power abandonment, solar power abandonment and load loss in the power grid, a data set for specific cost risk assessment is constructed; this paper assumes that the actual output power of wind power and photovoltaic power in the power grid approximately obeys the expected normal distribution of the predicted value of wind power and photovoltaic power output at time t, then the safe operation range of wind power and photovoltaic power is When the wind power and photovoltaic power output are higher than the upper limit of the safe operation range, the power grid is at risk of abandoning wind and photovoltaic power; when the wind power and photovoltaic power output are lower than the lower limit of the safe operation range, the power grid is at risk of load loss. The wind abandonment risk, photovoltaic abandonment risk and load loss risk of the power grid can be expressed as:

[0064]

[0065] are the wind abandonment risk, solar abandonment risk and load loss risk of the power grid respectively; G w , G l They are the capacity of wind farms and photovoltaic power stations in the power grid; are the probability density functions of wind power and photovoltaic output respectively.

[0066] The cost risk severity function considering the uncertainty of wind power and photovoltaic output is expressed as:

[0067]

[0068] λ w ,λ l ,λ f They are the penalty costs for unit wind curtailment, solar curtailment and load loss respectively.

[0069] Considering the uncertainties in grid operation, the safety and stability risk assessment analyzes and evaluates the probability of potential grid risks and the severity of risk accidents. The total risk calculation expression for wind power abandonment, solar power abandonment and load loss is:

[0070]

[0071] J wlf (U) is the risk value of the power grid; P(X a ) is the ath risk accident X of the power grid a Probability of occurrence; Risk event X b The probability that the power grid is in the predicted state after the occurrence; F is the load condition of the power grid at time t; Z wlf (U ab ) is the risk accident X when the power grid is in the predicted state U b the severity of.

[0072] In some embodiments, before constructing the control optimization model, the method further includes the following steps: obtaining a first objective function, wherein the first objective function is a function used for model training when constructing the control optimization model, wherein the first objective function is:

[0073] P g =P f,t -P w,t -P l,t +P c,t -P d,t ,

[0074] minF1 represents the first objective function mentioned above, S T represents the s intervals divided by the scheduling period T, P g represents the net load value at time t, Represents the average net load in a scheduling cycle, P f,t represents the load power at time t, P w,t represents the actual grid-connected power of the above wind power equipment at time t, P l,t represents the actual grid-connected power of the above photovoltaic equipment at time t, P c,t represents the charging power of the energy storage system at time t, P d,t Represents the discharge power of the energy storage system at time t.

[0075] In this plan, the first objective function is established, with the goal of minimizing net load fluctuations, optimizing the energy storage output at each stage of the system, and rationally dispatching energy storage equipment to maximize the absorption of new energy.

[0076] In some embodiments, before constructing the control optimization model, the method further includes the following steps: obtaining a second objective function, wherein the second objective function is a function used for model training when constructing the control optimization model, wherein the second objective function is:

[0077] minF2=J wlf (U)+F h ,

[0078] minF2 represents the second objective function mentioned above, J wlf (U) represents the risk value of the power grid, F h represents the coal consumption cost of the above thermal power unit equipment, S G represents the total number of thermal power units, β 1,i represents the first consumption coefficient of the above thermal power unit equipment, β 1,i ∈[0,0.01], P i,trepresents the output value of the above thermal power unit at time t, β 2,i represents the second consumption coefficient of the above thermal power unit equipment, β 2,i ∈[15,30],β 3,i represents the third consumption coefficient of the above thermal power unit equipment, β 3,i ∈[0,1000].

[0079] In this plan, a second objective function is established, with the goal of minimizing the risk of grid operation control costs. The optimization goal is to minimize the risk of grid operation control costs, including the total risk cost of wind abandonment, solar abandonment and load loss and the cost of adjusting the output control of thermal power units, so as to improve the economy and reliability of system operation.

[0080] In order to set the constraints of the multi-objective function so that it satisfies multiple constraints such as grid flow constraints, power balance constraints, energy storage system operation constraints, wind power, photovoltaic and thermal power unit output constraints, before constructing the control optimization model, the above method also includes the following steps: obtaining constraints, wherein the above constraints are the conditions used for model training when constructing the above control optimization model, wherein the above constraints include one or more of the first constraint of grid flow, the second constraint of power balance, the third constraint of the output of the above wind power equipment, the fourth constraint of the output of the above photovoltaic equipment, the fifth constraint of the output of the above thermal power unit equipment, and the sixth constraint of the operation of the energy storage system.

[0081] In this solution, constraints can also be set when training the model. This can avoid fitting or instability during training, prevent the data from being too large or too small, ensure the validity of the data, and further improve the generalization ability of the model. Constraints can also help accelerate the convergence speed of the model, reduce training time and computing resource consumption, and improve the stability and interpretability of the model, making the subsequently generated optimization data more accurate.

[0082] Specifically, the multi-objective function constraints are as follows:

[0083] (1) Grid flow constraints

[0084]

[0085] P t i , are the active power and reactive power of grid node i at time t respectively; are the voltages of nodes i and j in the distribution network at time t; G ij , B ij are the conductance and susceptance between nodes i and j respectively; The phase angle difference at time t is Sine and cosine of .

[0086] (2) Power balance constraints

[0087]

[0088] Indicates S G The total output of the thermal power unit equipment at time t.

[0089] (3) Wind power output constraints

[0090] 0<P w,t <P w,t,max ,

[0091] P w,t,max Indicates the maximum output of the wind farm at time t.

[0092] (4) Photovoltaic output constraints

[0093] 0<P l,t <P l,t,max ,

[0094] P l,t,max Indicates the maximum output of the photovoltaic power station at time t.

[0095] (5) Output constraints of thermal power units

[0096] P i,t,min ≤P i,t ≤P i,t,max

[0097] P i,t,min and P i,t,max They represent the minimum and maximum output of thermal power unit i respectively.

[0098] (6) Energy storage system operation constraints

[0099] ① Energy storage energy constraint is:

[0100]

[0101] ②Power constraints of energy storage system:

[0102]

[0103] P r max , P r min are the upper and lower limits of energy storage and release of the energy storage system respectively; P t S , P t rare the storage and discharge power of the energy storage system at time t respectively; They are the storage and discharge states of the energy storage system at time t, respectively. They are 0 / 1 variables. When the value is 0, it is in the shutdown state, and when the value is 1, it is in the working state.

[0104] In summary, in the scheme of this application, the volatility and uncertainty of renewable energy power generation not only bring challenges to the large-scale grid connection and consumption of renewable energy, but also increase the risk of safe and stable operation of the power grid. This scheme is a preventive control optimization method for power grids that takes risk assessment into consideration. First, by analyzing the output characteristics of wind power and photovoltaic power in the power grid, a data set that considers the uncertainty of renewable energy output is established; by determining the various risk indicators of the power grid, a data set for risk assessment is constructed; the goal of maximizing the consumption of renewable energy is considered to minimize the net load fluctuation of the power grid and minimize the control cost of the power grid operation; a power grid safety and stability risk optimization model that takes into account the uncertainty of wind power and photovoltaic output is constructed; finally, the NSWOA multi-objective optimization algorithm based on the whale optimization algorithm (Non-Dominated Sorting Whale Optimization Algorithm) is used to solve the model and obtain the optimized scheduling plan. Provide technical means for dispatching and operating personnel to conduct real-time online risk prevention and control, and effectively reduce the safety and stability risks of the power grid.

[0105] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the power grid optimization control method of the present application will be described in detail below in conjunction with specific embodiments.

[0106] This embodiment relates to a specific power grid optimization control method, such as Figure 4 As shown, the following steps are included:

[0107] Step S1: Analyze the output characteristics of wind power and photovoltaic power, and establish a data set that takes into account the uncertainty of new energy output.

[0108] Step S2: By determining various risk indicators of the power grid, analyzing the risk of wind power abandonment, solar power abandonment and load loss in the power grid, a data set for specific cost risk assessment is constructed.

[0109] Step S3: Establish two objective functions, namely, to minimize net load fluctuation, optimize the energy storage output of each stage of the system, and maximize the absorption of new energy; to minimize the risk of grid operation control cost, and improve the economy and reliability of system operation.

[0110] Step S4: Set the constraints of the multi-objective function to satisfy various constraints such as power grid flow constraints, power balance constraints, energy storage system operation constraints, wind power, photovoltaic and thermal power unit output constraints, etc.

[0111] Step S5: The NSWOA algorithm is used to solve the power grid preventive control optimization model considering risk assessment to obtain an optimal dispatching scheme that meets multi-objective constraints.

[0112] The embodiment of the present application also provides an optimization control device for a power grid. It should be noted that the optimization control device for the power grid of the embodiment of the present application can be used to execute the optimization control method for the power grid provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0113] The following is an introduction to the optimization control device for the power grid provided in the embodiments of the present application.

[0114] Figure 5 is a structural block diagram of an optimization control device for a power grid according to an embodiment of the present application. Figure 5 As shown, the device comprises:

[0115] A first acquisition unit 10 is used to acquire relevant data of the power grid, wherein the relevant data includes one or more of output power, load and operation cost of the power equipment, and the power equipment includes one or more of wind power equipment, photovoltaic equipment and thermal power unit equipment;

[0116] A construction unit 20 is used to construct a control optimization model, wherein the control optimization model is obtained by training with the NSWOA algorithm using multiple sets of training data, each of the multiple sets of training data includes historical related data acquired in a historical time period and historical optimization data corresponding to the historical related data, wherein the historical optimization data is data of a strategy for optimizing control of at least the historical output value and the historical power distribution of the power equipment;

[0117] The processing unit 30 is used to input the above-mentioned relevant data into the above-mentioned control optimization model to obtain the optimization data corresponding to the above-mentioned relevant data;

[0118] The first control unit 40 is used to control the operation of the above-mentioned power equipment of the above-mentioned power grid according to the above-mentioned optimization data corresponding to the above-mentioned relevant data.

[0119] Through this embodiment, the NSWOA algorithm can effectively handle multi-objective optimization problems, retain a set of non-inferior solutions in the population through non-dominated sorting, and thus help decision makers find a balance between multiple conflicting objectives. The algorithm has a strong global search capability and convergence speed, and can quickly find a better solution. Therefore, this scheme uses the NSWOA algorithm to solve the optimization problem of the power grid, obtain the data of the optimization strategy, and then control the operation of the power grid, so as to ensure that the power grid operates in a multi-objective balanced manner, thereby ensuring the stability of the power grid.

[0120] During the specific implementation process, the first acquisition unit includes an acquisition module and a processing module, the acquisition module is used to acquire the initial relevant data at the first moment; the processing module is used to analyze the above-mentioned initial relevant data using a target algorithm to obtain the above-mentioned relevant data at the second moment, wherein the above-mentioned target algorithm includes at least one or more of linear regression, time series analysis, random forest, neural network, and support vector machine, and the above-mentioned first moment is earlier than the above-mentioned second moment.

[0121] In this solution, the target algorithm can be used to predict and analyze the initial relevant data, and the relevant data at the second moment can be predicted by the initial relevant data at the first moment. This can better understand the changing trends and laws of the data and help make more accurate predictions and decisions. At the same time, choosing different target algorithms can analyze the data more comprehensively and improve the accuracy and efficiency of data analysis.

[0122] During the specific implementation process, the above-mentioned device also includes an evaluation unit and a second control unit. The evaluation unit is used to perform risk evaluation on the above-mentioned power grid according to the above-mentioned relevant data after acquiring relevant data of the power grid to obtain an evaluation result; the second control unit is used to optimize the control of the above-mentioned power equipment of the above-mentioned power grid when the above-mentioned evaluation result indicates that the above-mentioned power grid has risks.

[0123] In this scheme, the risk assessment of the power grid can also be carried out. If the power grid is risky, the power grid can be optimized and controlled. If the power grid is not risky, the power grid can be optimized and controlled, or not optimized and controlled. Through this scheme, it can be accurately determined whether the power grid is risky, and then the power grid can be optimized and controlled more accurately.

[0124] During the specific implementation process, the evaluation unit includes an evaluation module, which is used to determine that the above-mentioned power grid is risky when the above-mentioned relevant data meets the preset conditions, and determine that the above-mentioned power grid is not risky when the above-mentioned relevant data does not meet the above-mentioned preset conditions, wherein the above-mentioned preset conditions include one or more of the above-mentioned output power being greater than the maximum power threshold, the above-mentioned output power being less than the minimum power threshold, the load rate corresponding to the above-mentioned load being greater than the maximum load rate, and the above-mentioned operating cost being greater than the preset cost.

[0125] In this scheme, when relevant data meets the preset conditions, the power grid is considered to be at risk, and when relevant data does not meet the preset conditions, the power grid is considered to be not at risk. In this way, whether the power grid is at risk can be further accurately determined based on the preset conditions.

[0126] In some embodiments, the apparatus further includes a second acquisition unit, which is used to acquire a first objective function before constructing the control optimization model, wherein the first objective function is a function used for model training when constructing the control optimization model, wherein the first objective function is:

[0127] P g =P f,t -P w,t -P l,t +P c,t -P d,t ,

[0128] minF1 represents the first objective function mentioned above, S T represents the s intervals divided by the scheduling period T, P g represents the net load value at time t, Represents the average net load in a scheduling cycle, P f,t represents the load power at time t, P w,t represents the actual grid-connected power of the above wind power equipment at time t, P l,t represents the actual grid-connected power of the above photovoltaic equipment at time t, P c,t represents the charging power of the energy storage system at time t, P d,t Represents the discharge power of the energy storage system at time t.

[0129] In this plan, the first objective function is established, with the goal of minimizing net load fluctuations, optimizing the energy storage output at each stage of the system, and rationally dispatching energy storage equipment to maximize the absorption of new energy.

[0130] In some embodiments, the apparatus further includes a third acquisition unit, which is used to acquire a second objective function before constructing the control optimization model, wherein the second objective function is a function used for model training when constructing the control optimization model, wherein the second objective function is:

[0131] minF2=J wlf (U)+F h ,

[0132] minF2 represents the second objective function mentioned above, J wlf(U) represents the risk value of the power grid, F h represents the coal consumption cost of the above thermal power unit equipment, S G represents the total number of thermal power units, β 1,i represents the first consumption coefficient of the above thermal power unit equipment, β 1,i ∈[0,0.01], P i,t represents the output value of the above thermal power unit at time t, β 2,i represents the second consumption coefficient of the above thermal power unit equipment, β 2,i ∈[15,30],β 3,i represents the third consumption coefficient of the above thermal power unit equipment, β 3,i ∈[0,1000].

[0133] In this plan, a second objective function is established, with the goal of minimizing the risk of grid operation control costs. The optimization goal is to minimize the risk of grid operation control costs, including the total risk cost of wind abandonment, solar abandonment and load loss and the cost of adjusting the output control of thermal power units, so as to improve the economy and reliability of system operation.

[0134] In order to set the constraints of the multi-objective function so that it satisfies multiple constraints such as power grid flow constraints, power balance constraints, energy storage system operation constraints, wind power, photovoltaic and thermal power unit output constraints, the above-mentioned device also includes a fourth acquisition unit, and the fourth acquisition unit is used to obtain the constraints before constructing the control optimization model, wherein the above-mentioned constraints are the conditions used for model training when constructing the above-mentioned control optimization model, wherein the above-mentioned constraints include a first constraint condition of power grid flow, a second constraint condition of power balance, a third constraint condition of the output of the above-mentioned wind power equipment, a fourth constraint condition of the output of the above-mentioned photovoltaic equipment, a fifth constraint condition of the output of the above-mentioned thermal power unit equipment, and one or more of the sixth constraint condition of the operation of the energy storage system.

[0135] In this solution, constraints can also be set when training the model. This can avoid fitting or instability during training, prevent the data from being too large or too small, ensure the validity of the data, and further improve the generalization ability of the model. Constraints can also help accelerate the convergence speed of the model, reduce training time and computing resource consumption, and improve the stability and interpretability of the model, making the subsequently generated optimization data more accurate.

[0136] The above-mentioned power grid optimization control device includes a processor and a memory, and the above-mentioned acquisition unit, construction unit, processing unit and control unit are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions. The above-mentioned modules are all located in the same processor; or, the above-mentioned modules are located in different processors in any combination.

[0137] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be provided, and the problem of poor stability of power grid operation in the prior art can be solved by adjusting kernel parameters.

[0138] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0139] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the optimization control method for the power grid.

[0140] Specifically, the optimization control method of the power grid includes:

[0141] Step S201, obtaining relevant data of the power grid, wherein the relevant data includes one or more of output power, load and operating cost of the power equipment, and the power equipment includes one or more of wind power equipment, photovoltaic equipment and thermal power unit equipment;

[0142] Step S202, constructing a control optimization model, wherein the control optimization model is obtained by training with the NSWOA algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical related data acquired in a historical time period and historical optimization data corresponding to the historical related data, wherein the historical optimization data is data of a strategy for optimizing control of at least the historical output value and the historical power distribution of the power equipment;

[0143] Step S203, inputting the above-mentioned relevant data into the above-mentioned control optimization model to obtain optimization data corresponding to the above-mentioned relevant data;

[0144] Step S204: controlling the operation of the power equipment of the power grid according to the optimization data corresponding to the related data.

[0145] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the optimization control method of the power grid is executed when the program is run.

[0146] Specifically, the optimization control method of the power grid includes:

[0147] Step S201, obtaining relevant data of the power grid, wherein the relevant data includes one or more of output power, load and operating cost of the power equipment, and the power equipment includes one or more of wind power equipment, photovoltaic equipment and thermal power unit equipment;

[0148] Step S202, constructing a control optimization model, wherein the control optimization model is obtained by training with the NSWOA algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical related data acquired in a historical time period and historical optimization data corresponding to the historical related data, wherein the historical optimization data is data of a strategy for optimizing control of at least the historical output value and the historical power distribution of the power equipment;

[0149] Step S203, inputting the above-mentioned relevant data into the above-mentioned control optimization model to obtain optimization data corresponding to the above-mentioned relevant data;

[0150] Step S204: controlling the operation of the power equipment of the power grid according to the optimization data corresponding to the related data.

[0151] An embodiment of the present invention provides a device, the device including a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, at least the following steps are implemented:

[0152] Specifically, the optimization control method of the power grid includes:

[0153] Step S201, obtaining relevant data of the power grid, wherein the relevant data includes one or more of output power, load and operating cost of the power equipment, and the power equipment includes one or more of wind power equipment, photovoltaic equipment and thermal power unit equipment;

[0154] Step S202, constructing a control optimization model, wherein the control optimization model is obtained by training with the NSWOA algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical related data acquired in a historical time period and historical optimization data corresponding to the historical related data, wherein the historical optimization data is data of a strategy for optimizing control of at least the historical output value and the historical power distribution of the power equipment;

[0155] Step S203, inputting the above-mentioned relevant data into the above-mentioned control optimization model to obtain optimization data corresponding to the above-mentioned relevant data;

[0156] Step S204: controlling the operation of the power equipment of the power grid according to the optimization data corresponding to the related data.

[0157] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0158] A computer program product includes a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method in each embodiment of the present application are implemented:

[0159] Specifically, the optimization control method of the power grid includes:

[0160] Step S201, obtaining relevant data of the power grid, wherein the relevant data includes one or more of output power, load and operating cost of the power equipment, and the power equipment includes one or more of wind power equipment, photovoltaic equipment and thermal power unit equipment;

[0161] Step S202, constructing a control optimization model, wherein the control optimization model is obtained by training with the NSWOA algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical related data acquired in a historical time period and historical optimization data corresponding to the historical related data, wherein the historical optimization data is data of a strategy for optimizing control of at least the historical output value and the historical power distribution of the power equipment;

[0162] Step S203, inputting the above-mentioned relevant data into the above-mentioned control optimization model to obtain optimization data corresponding to the above-mentioned relevant data;

[0163] Step S204: controlling the operation of the power equipment of the power grid according to the optimization data corresponding to the related data.

[0164] The present application also provides a power grid optimization system, comprising one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the above-mentioned power grid optimization control methods.

[0165] Specifically, the optimization control method of the power grid includes:

[0166] Step S201, obtaining relevant data of the power grid, wherein the relevant data includes one or more of output power, load and operating cost of the power equipment, and the power equipment includes one or more of wind power equipment, photovoltaic equipment and thermal power unit equipment;

[0167] Step S202, constructing a control optimization model, wherein the control optimization model is obtained by training with the NSWOA algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical related data acquired in a historical time period and historical optimization data corresponding to the historical related data, wherein the historical optimization data is data of a strategy for optimizing control of at least the historical output value and the historical power distribution of the power equipment;

[0168] Step S203, inputting the above-mentioned relevant data into the above-mentioned control optimization model to obtain optimization data corresponding to the above-mentioned relevant data;

[0169] Step S204: controlling the operation of the power equipment of the power grid according to the optimization data corresponding to the related data.

[0170] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0171] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0172] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0173] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0174] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0175] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0176] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0177] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0178] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0179] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0180] 1) The optimization control method of the power grid of the present application, the NSWOA algorithm can effectively handle multi-objective optimization problems, and retain the set of non-inferior solutions in the population through non-dominated sorting, thereby helping decision makers find a balance between multiple conflicting objectives. The algorithm has strong global search capabilities and convergence speed, and can quickly find a better solution. Therefore, this scheme adopts the NSWOA algorithm to solve the optimization problem of the power grid, obtain the data of the optimization strategy, and then control the operation of the power grid, so as to ensure that the power grid operates in a multi-objective balanced manner, thereby ensuring the stability of the power grid.

[0181] 2) The optimization control device of the power grid of the present application, the NSWOA algorithm can effectively handle multi-objective optimization problems, and retain the set of non-inferior solutions in the population through non-dominated sorting, thereby helping decision makers find a balance between multiple conflicting objectives. The algorithm has strong global search capabilities and convergence speed, and can quickly find a better solution. Therefore, this scheme adopts the NSWOA algorithm to solve the optimization problem of the power grid, obtain the data of the optimization strategy, and then control the operation of the power grid. This can ensure that the power grid operates in a multi-objective balanced manner, thereby ensuring the stability of the power grid.

[0182] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for optimizing and controlling a power grid, characterized in that: include: Acquire relevant data of the power grid, wherein the relevant data includes one or more of output power, load and operating cost of power equipment, and the power equipment includes one or more of wind power equipment, photovoltaic equipment and thermal power unit equipment; Constructing a control optimization model, wherein the control optimization model is obtained by training with the NSWOA algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical relevant data acquired in a historical time period and historical optimization data corresponding to the historical relevant data, wherein the historical optimization data is data of a strategy for optimizing control of at least the historical output value and the historical power distribution of the power equipment; Inputting the relevant data into the control optimization model to obtain optimization data corresponding to the relevant data; The operation of the power equipment of the power grid is controlled according to the optimization data corresponding to the relevant data.

2. The method according to claim 1, characterized in that Obtain relevant data of the power grid, including: Obtaining initial relevant data at the first moment; The initial correlation data is analyzed using a target algorithm to obtain the correlation data at a second moment, wherein the target algorithm includes at least one or more of linear regression, time series analysis, random forest, neural network, and support vector machine, and the first moment is earlier than the second moment.

3. The method according to claim 1, characterized in that After obtaining the relevant data of the power grid, the method further includes: Performing risk assessment on the power grid according to the relevant data to obtain an assessment result; When the evaluation result indicates that the power grid has risks, the power equipment of the power grid is optimally controlled.

4. The method according to claim 3, characterized in that: Performing a risk assessment on the power grid according to the relevant data to obtain an assessment result, including: When the relevant data meets the preset conditions, it is determined that the power grid is at risk; when the relevant data does not meet the preset conditions, it is determined that the power grid is not at risk, wherein the preset conditions include one or more of the output power being greater than a maximum power threshold, the output power being less than a minimum power threshold, the load rate corresponding to the load being greater than a maximum load rate, and the operating cost being greater than a preset cost.

5. The method according to claim 1, characterized in that Before constructing the control optimization model, the method further includes: Obtain a first objective function, wherein the first objective function is a function used for model training when constructing the control optimization model, wherein the first objective function is: P g =P f,t -P w,t -P l,t +P c,t -P d,t , minF1 represents the first objective function, S T represents the s intervals divided by the scheduling period T, P g represents the net load value at time t, Represents the average net load in a scheduling cycle, P f,t represents the load power at time t, P w,t represents the actual grid-connected power of the wind power equipment at time t, P l,t represents the actual grid-connected power of the photovoltaic device at time t, P c,t represents the charging power of the energy storage system at time t, P d,t Represents the discharge power of the energy storage system at time t.

6. The method according to claim 1, characterized in that Before constructing the control optimization model, the method further includes: Obtain a second objective function, wherein the second objective function is a function used for model training when constructing the control optimization model, wherein the second objective function is: minF2=J wlf (U)+F h , minF2 represents the second objective function, J wlf (U) represents the risk value of the power grid, F h represents the coal consumption cost of the thermal power unit equipment, S G represents the total number of thermal power units, β 1,i represents the first consumption coefficient of the thermal power unit equipment, β 1,i ∈[0,0.01], P i,t represents the output value of the thermal power unit at time t, β 2,i represents the second consumption coefficient of the thermal power unit equipment, β 2,i ∈[15,30],β 3,i represents the third consumption coefficient of the thermal power unit equipment, β 3,i ∈[0,1000].

7. The method according to claim 1, characterized in that Before constructing the control optimization model, the method further includes: Obtain constraint conditions, wherein the constraint conditions are conditions used for model training when constructing the control optimization model, wherein the constraint conditions include one or more of a first constraint condition of grid flow, a second constraint condition of power balance, a third constraint condition of the output of the wind power equipment, a fourth constraint condition of the output of the photovoltaic equipment, a fifth constraint condition of the output of the thermal power unit equipment, and a sixth constraint condition of the operation of the energy storage system.

8. An optimization control device for a power grid, characterized in that: include: A first acquisition unit is used to acquire relevant data of the power grid, wherein the relevant data includes one or more of output power, load and operation cost of the power equipment, and the power equipment includes one or more of wind power equipment, photovoltaic equipment and thermal power unit equipment; A construction unit, configured to construct a control optimization model, wherein the control optimization model is obtained by training with a NSWOA algorithm using a plurality of sets of training data, each set of training data in the plurality of sets of training data includes historical related data acquired in a historical time period and historical optimization data corresponding to the historical related data, wherein the historical optimization data is data of a strategy for optimizing control of at least the historical output value and the historical power distribution of the power equipment; A processing unit, used for inputting the relevant data into the control optimization model to obtain optimization data corresponding to the relevant data; The first control unit is used to control the operation of the power equipment of the power grid according to the optimization data corresponding to the relevant data.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for optimizing control of a power grid as claimed in any one of claims 1 to 7 are implemented.

10. A power grid optimization system, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the optimization control method of the power grid described in any one of claims 1 to 7.

Images