Photovoltaic power station income optimization method, device, equipment and medium

Through the photovoltaic power station return optimization method combined with LSTM and autoregressive integral sliding average model, the problems of insufficient prediction accuracy and unsatisfactory optimization results in photovoltaic power generation are solved, and the capture of complex nonlinear relationships and processing of data loss are realized, and dynamic adjustment is achieved. The power purchasing strategy improves the economic benefits and return on investment of photovoltaic power plants.

CN119026935APending Publication Date: 2024-11-26STATE GRID BEIJING ELECTRIC POWER CO +1
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202410992295.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

In the existing photovoltaic power generation technology, the prediction accuracy is insufficient, the optimization effect is not ideal, and the prediction and optimization are not effectively combined, making it difficult to adapt to complex nonlinear relationships and data loss problems, and the return on photovoltaic investment cannot be accurately calculated.

Method used

The LSTM algorithm and the autoregressive integral sliding average model are used, combined with historical weather and electricity price data, and economic returns optimization model is built. By predicting power generation and electricity sales prices, the optimal power purchase strategy is solved to maximize economic returns.

Benefits of technology

It improves the prediction accuracy and optimization effect of photovoltaic power plants, can dynamically adjust power purchasing strategies, adapt to electricity price fluctuations and environmental changes, reduce operating costs, and enhance the reliability of return on investment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119026935A_ABST
    Figure CN119026935A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of photovoltaic power generation, and particularly relates to a photovoltaic power station income optimization method and device, equipment and a medium. The method comprises the following steps: inputting predicted weather data into a photovoltaic power generation prediction model to obtain photovoltaic predicted generating capacity; inputting the historical electricity selling price into an electricity selling price prediction model to obtain a predicted electricity selling price; constructing an economic benefit optimization model based on the photovoltaic predicted generating capacity and the predicted electricity selling price; the economic benefit optimization model comprises a target function taking maximum economic benefit as a target and a constraint condition corresponding to the target function; and solving the economic benefit optimization model to obtain an electricity purchasing strategy for maximizing the economic benefit of the photovoltaic power station. The method can accurately predict the generating capacity according to the weather condition and historical data, optimizes the matching between the power output and the market demand, reduces the energy waste and unused resources, comprehensively considers the photovoltaic generating capacity, the power grid electricity price, the user energy storage system and other factors, and comprehensively improves the overall photovoltaic benefit of the user.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of photovoltaic power generation, and specifically relates to a method, device, equipment and medium for optimizing the revenue of a photovoltaic power station. Background Art

[0002] Photovoltaic power generation technology has become a core component of the renewable energy sector worldwide, especially in promoting energy structure transformation and addressing climate change. Photovoltaic projects can convert solar energy into electrical energy, providing clean energy for residential, commercial and industrial use. However, due to the uncertainty of solar radiation and the fluctuation of electricity market prices, energy management and economic optimization of photovoltaic power generation projects have become a continuous challenge. In addition, with the liberalization of the electricity market and the dynamic changes in electricity prices, how to maximize economic benefits in different time periods has become a hot topic in the field of photovoltaic power generation. At present, the power production and consumption management of photovoltaic projects is usually based on a single neural network algorithm or optimization algorithm. The long short-term memory (LSTM) neural network algorithm is the most effective one for time memory among similar algorithms. It is suitable for scenarios with strong time correlation such as photovoltaic power generation. The mixed integer linear programming algorithm can consider multiple constraints and maximize the optimal solution. The two methods each have irreplaceable advantages. However, a single solution cannot effectively integrate market electricity price signals to dynamically adjust the power generation strategy to cope with the price differences between peak and trough periods in the market. Therefore, these technologies have limitations in improving the economic returns and market adaptability of photovoltaic projects. The combined algorithm can integrate advantages, maximize economic benefits while taking full account of constraints, and adapt to fluctuations in electricity prices and rapid changes in actual meteorological conditions.

[0003] The existing technologies in photovoltaic system revenue optimization have defects and deficiencies such as insufficient prediction accuracy, unsatisfactory optimization effect, and failure to effectively combine prediction and optimization. Specifically:

[0004] Unable to handle complex nonlinear relationships: Traditional statistical forecasting methods (such as time series analysis, ARIMA model, etc.) often have difficulty in providing high-precision forecasting results when faced with the high nonlinearity and randomness of photovoltaic power generation data. Photovoltaic power generation is affected by many factors (such as weather, temperature, light intensity, etc.), and traditional statistical methods are difficult to fully capture and model these complex nonlinear relationships.

[0005] Unable to adapt to the characteristics of photovoltaic data: Machine learning models (such as support vector machines, random forests, etc.) usually require a large amount of high-quality historical data for training, while the data of photovoltaic power generation systems may be missing or incomplete. Therefore, there is a lack of comprehensive methods that combine prediction and optimization for photovoltaic data: many methods have only made breakthroughs in prediction or optimization, and lack a systematic method that organically combines high-precision prediction with optimization algorithms, which makes it difficult to fully utilize the prediction results for optimization decisions. When faced with real-time changes in photovoltaic power generation, traditional methods find it difficult to update prediction results and optimization plans in a timely manner, and cannot adapt to the rapidly changing actual operating environment. Failure to combine the dynamic changes in electricity prices in the power market and the differences in electricity prices during peak and trough periods results in inaccurate calculations of photovoltaic investment returns, and is unable to provide investors with accurate references for returns. Summary of the invention

[0006] The purpose of the present invention is to provide a photovoltaic power station revenue optimization method, device, equipment and medium to at least solve one of the problems in the prior art in photovoltaic system revenue optimization, such as insufficient prediction accuracy, unsatisfactory optimization effect, and failure to effectively combine prediction and optimization.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] In a first aspect, the present invention provides a photovoltaic power station revenue optimization method, comprising the following steps:

[0009] Obtaining forecast weather data for the area where the target photovoltaic power station is located, inputting the forecast weather data into a pre-trained photovoltaic power generation forecast model, and the photovoltaic power generation forecast model outputs the forecast photovoltaic power generation in the future time period;

[0010] Obtaining the historical electricity selling price of the target photovoltaic power station to the power grid, inputting the historical electricity selling price into a pre-trained electricity selling price prediction model, and the electricity selling price prediction model outputs the predicted electricity selling price of the target photovoltaic power station to the power grid in the future time period;

[0011] Based on the predicted photovoltaic power generation and the predicted electricity selling price, an economic benefit optimization model is constructed; wherein the economic benefit optimization model includes an objective function with the maximum economic benefit as the goal, and constraints corresponding to the objective function;

[0012] Solve the economic benefit optimization model to obtain a power purchase strategy that maximizes the economic benefit of the photovoltaic power station.

[0013] Furthermore, the photovoltaic power generation prediction model is trained using the following method:

[0014] Obtaining historical weather data of the region where the photovoltaic power station is located, and historical power generation data corresponding to the historical weather data;

[0015] Building a training set based on the historical weather data and the historical power generation data;

[0016] Establish a power generation prediction model based on LSTM algorithm;

[0017] Based on the training set, a back propagation algorithm is used to train the power generation prediction model to obtain the trained photovoltaic power generation prediction model.

[0018] Furthermore, after obtaining historical weather data of the region where the photovoltaic power station is located and historical power generation data corresponding to the historical weather data, the historical weather data and the historical power generation data are cleaned to process missing values ​​and abnormal values;

[0019] Determine key features in the historical weather data that affect power generation, standardize the key features to obtain standardized key features, and construct the standardized key features and corresponding historical power generation data into a training set for model training.

[0020] Furthermore, the electricity selling price prediction model is constructed and trained based on an autoregressive integrated moving average model.

[0021] Furthermore, the electricity price prediction model is constructed based on the autoregressive integrated moving average model, including:

[0022] Acquire historical electricity price time series data, perform differential processing on the historical electricity price time series data, and determine a differential order that makes the historical electricity price time series data stable;

[0023] Determine the autoregressive order and the moving average order;

[0024] According to the determined difference order, autoregressive order and moving average order, an autoregressive integrated moving average model is constructed.

[0025] Furthermore, the objective function of the economic benefit optimization model is as follows:

[0026]

[0027] Among them, Z represents the total income of the photovoltaic power station in each time period; T is the time period, t is the time period, t=1,2,3,……T; is the predicted electricity price in period t; is the known power purchase price of the power grid company in time period t; s t is the electricity sales in period t; b t is the amount of electricity purchased in period t, and the amount of electricity purchased is used as the optimization variable.

[0028] Furthermore, the constraints corresponding to the objective function include:

[0029] Power balance constraints:

[0030]

[0031] Power generation limit:

[0032]

[0033] Restrictions on electricity purchase and sales:

[0034]

[0035] Among them, p t is the predicted photovoltaic power generation in period t; b t is the amount of electricity purchased during period t; s t is the electricity sales in period t; u t represents the internal power consumption during time period t; b max is the upper limit of electricity purchase; max It is the upper limit of electricity sales.

[0036] In a second aspect, the present invention provides a photovoltaic power station revenue optimization device, comprising:

[0037] A first acquisition module is used to acquire the predicted weather data of the area where the target photovoltaic power station is located, and input the predicted weather data into a pre-trained photovoltaic power generation prediction model, and the photovoltaic power generation prediction model outputs the predicted photovoltaic power generation in the future time period;

[0038] The second acquisition module is used to obtain the historical electricity sales price of the target photovoltaic power station to the power grid, and input the historical electricity sales price into a pre-trained electricity sales price prediction model, and the electricity sales price prediction model outputs the predicted electricity sales price of the target photovoltaic power station to the power grid in the future time period;

[0039] A model building module, used to build an economic benefit optimization model based on the predicted photovoltaic power generation and the predicted electricity selling price; wherein the economic benefit optimization model includes an objective function with the maximum economic benefit as the goal, and constraints corresponding to the objective function;

[0040] The model solving module is used to solve the economic benefit optimization model to obtain a power purchasing strategy that maximizes the economic benefits of the photovoltaic power station.

[0041] According to a third aspect of the present invention, an electronic device is provided, comprising a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the photovoltaic power station revenue optimization method as described above.

[0042] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the photovoltaic power station revenue optimization method as described above is implemented.

[0043] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0044] The present invention can accurately predict power generation based on weather conditions and historical data, optimize the matching between power output and market demand, reduce energy waste and unused resources, comprehensively consider factors such as photovoltaic power generation, grid electricity prices, and user energy storage systems, and comprehensively improve the overall benefits of user photovoltaics.

[0045] The present invention uses a photovoltaic power station revenue optimization method to comprehensively consider weather forecasts, electricity price forecasts, and the actual operation of the power station, build an accurate and efficient economic benefit optimization model, and solve the optimal power purchase strategy to maximize the economic benefits of the photovoltaic power station. This is of great significance for improving the operating efficiency of photovoltaic power stations, reducing operating costs, and promoting the sustainable development of renewable energy.

[0046] The LSTM model used in the present invention can process the time series characteristics in photovoltaic power generation data, and deal with the problem that the data of photovoltaic power generation systems may be missing or incomplete. The model can flexibly process multiple input features (such as weather, temperature, light intensity, etc.), capture their nonlinear relationships, adapt to different environmental changes, make the prediction results more reliable, accurately calculate photovoltaic income and investment return years, and provide investors with a clear investment basis.

[0047] The present invention uses mixed integer linear programming (MILP) to optimize calculations to ensure that the revenue from electricity sales is maximized when electricity prices are high, while saving electricity purchase costs when prices are low, thereby optimizing economic benefits throughout the day. Through predictive models and real-time data analysis, electricity purchases are dynamically adjusted to achieve dynamic cost management, further reduce operating costs, and maximize economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The drawings constituting a part of the present application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0049] Figure 1 A schematic diagram of a process for optimizing a photovoltaic power station revenue according to an embodiment of the present invention;

[0050] Figure 2 This is a structural block diagram of a photovoltaic power station revenue optimization device according to an embodiment of the present invention;

[0051] Figure 3The present invention is a structural block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0053] The following detailed description is an exemplary description, which is intended to provide further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present application belongs. The terms used in the present invention are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention.

[0054] Example 1

[0055] like Figure 1 As shown, a photovoltaic power station revenue optimization method includes the following steps:

[0056] S1. Obtain forecast weather data for the area where the target photovoltaic power station is located, input the forecast weather data into a pre-trained photovoltaic power generation forecast model, and the photovoltaic power generation forecast model outputs the forecast photovoltaic power generation in the future time period;

[0057] S2. Obtain the historical electricity selling price of the target photovoltaic power station to the power grid, input the historical electricity selling price into a pre-trained electricity selling price prediction model, and the electricity selling price prediction model outputs the predicted electricity selling price of the target photovoltaic power station to the power grid in the future time period;

[0058] S3. Based on the predicted photovoltaic power generation and the predicted electricity selling price, an economic benefit optimization model is constructed; wherein the economic benefit optimization model includes an objective function with the goal of maximizing economic benefits, and constraints corresponding to the objective function;

[0059] S4. Solve the economic benefit optimization model to obtain a power purchasing strategy that maximizes the economic benefits of the photovoltaic power station.

[0060] The photovoltaic power station revenue optimization method proposed in the present invention obtains the forecast weather data of the target photovoltaic power station area, and uses the photovoltaic power generation forecast model to predict the photovoltaic power generation in the future time period; at the same time, combined with the historical electricity price data, the electricity price forecast model is used to predict the electricity price in the future time period; finally, based on the photovoltaic forecast power generation and the forecast electricity price, an economic benefit optimization model is constructed, and the electricity purchase strategy that maximizes the economic benefits of the photovoltaic power station is solved. It can effectively cope with the uncertainty of weather conditions and market electricity prices, realize the intelligent and refined operation and management of photovoltaic power stations, and improve the economic benefits and competitiveness of photovoltaic power stations.

[0061] To further explain the present solution, the present invention also provides a photovoltaic power station revenue optimization method, comprising the following steps:

[0062] S100, obtaining forecast weather data for the area where the target photovoltaic power station is located, inputting the forecast weather data into a pre-trained photovoltaic power generation forecast model, and the photovoltaic power generation forecast model outputs the forecast photovoltaic power generation in a future time period.

[0063] Specifically, the photovoltaic power generation prediction model is trained by the following method: obtaining historical weather data of the area where the photovoltaic power station is located, and historical power generation data corresponding to the historical weather data; constructing a training set based on the historical weather data and historical power generation data; establishing a power generation prediction model based on the LSTM algorithm; based on the training set, using the back propagation algorithm to train the power generation prediction model to obtain the trained photovoltaic power generation prediction model.

[0064] In the preferred scheme, after obtaining the historical weather data of the area where the photovoltaic power station is located, and the historical power generation data corresponding to the historical weather data, the historical weather data and the historical power generation data are cleaned, and missing values ​​and abnormal values ​​are processed; the key features that affect the power generation in the historical weather data are determined, the key features are standardized to obtain standardized key features, and the standardized key features and the corresponding historical power generation data are constructed as a training set for model training.

[0065] As an example, the key features that affect power generation include light intensity x1, temperature x2, and wind speed x3. The following formula is used to standardize the above features:

[0066]

[0067] Among them, m i is feature x i The mean value, s i is feature x i The standard deviation of .

[0068] Optionally, historical power generation data and historical weather data (such as light, temperature, wind speed, etc.) can also be collected from photovoltaic projects of the same type and region. The collected data is cleaned, missing values ​​and outliers are processed, and the accuracy and completeness of the data are ensured for subsequent analysis.

[0069] In an optional solution, the present invention establishes a power generation prediction model based on the LSTM algorithm, uses historical power generation data and historical weather data to train the prediction model, and verifies the accuracy and reliability of the power generation prediction through cross-validation.

[0070] Specifically, the establishment of the photovoltaic power generation prediction model includes:

[0071] The LSTM algorithm is selected to process the nonlinear relationship in the photovoltaic power generation prediction data;

[0072] X={[P (t-n+1) , x 1(t-n+1) , x 2(t-n+1) , x 3(t-n+1) ],[P (t-n+2) , x 1(t-n+2) , x 2(t-n+2) , x 3(t-n+2) ],...,[P (t) , x 1(t) , x 2(t) , x 3(t) ]}

[0073] Among them, X is a vector containing all input features, defining the input data matrix X and the output data matrix Y, where X contains multiple historical feature data, light intensity x1, temperature x2, wind speed x3, and P is the corresponding photovoltaic power generation data. The input data includes data from multiple time periods. The basic unit of the LSTM network is the LSTM cell, and its core is the memory unit c t and hidden state h t LSTM uses three gating mechanisms (forget gate f t , input gate i t , output gate o t ) to control the flow of information.

[0074] Forget Gate:

[0075] f t =σ(W f ·[h t-1 ,x t ]+b f )

[0076] In the formula, f t represents the output vector of the forget gate, where the value of each element is between 0 and 1, σ represents the activation function, which compresses the input into the range of 0-1, and W f It represents the weight matrix of the forget gate, [h t-1 ,x t ] represents the hidden state h of the previous time step t-1 and the current input x t concatenate into a vector. b f Represents the bias vector of the forget gate.

[0077] Input Gate:

[0078] i t =σ(W i ·[h t-1 ,xt ]+b i )

[0079]

[0080] In the formula, i t Represents the output vector of the input gate, with a value between 0 and 1, W i represents the weight matrix of the input gate. b i Represents the bias vector of the input gate. Indicates that a new candidate value vector is created, W c represents the candidate value vector weight matrix, b c Represents the bias vector.

[0081] Memory unit update:

[0082] o t =σ(W o ·[h t-1 ,x t ]+b o )

[0083] h t =o t ·tanh(c t )

[0084] In the formula, o t Represents the output vector of the output gate, with a value between 0 and 1, W o represents the weight matrix of the output gate, b o represents the bias vector of the output gate, c t A vector representing candidate values ​​for the output gate.

[0085] The predicted output is calculated through forward propagation, and the mean square error of the loss function is calculated using historical power generation data:

[0086]

[0087] Where N is the number of samples, y i is the actual power generation, To predict power generation.

[0088] Use the back-propagation algorithm to update the network parameters (weights and biases) to minimize the loss function:

[0089]

[0090] Among them, θ represents the model parameters and η is the learning rate.

[0091] S200, obtaining the historical electricity selling prices of the target photovoltaic power station to the power grid, inputting the historical electricity selling prices into a pre-trained electricity selling price prediction model, and the electricity selling price prediction model outputs the predicted electricity selling prices of the target photovoltaic power station to the power grid in a future time period.

[0092] Specifically, the electricity selling price prediction model is constructed and trained based on an autoregressive integrated moving average model.

[0093] To be more specific, the electricity selling price prediction model is constructed based on the autoregressive integral moving average model, including: obtaining historical electricity price time series data, performing differential processing on the historical electricity price time series data, and determining the differential order that makes the historical electricity price time series data smooth; determining the autoregressive order and the moving average order; and constructing the autoregressive integral moving average model based on the determined differential order, autoregressive order and moving average order.

[0094] Similarly, after the historical electricity price data is obtained, data preprocessing and clearing are performed, and the features are standardized.

[0095] Optionally, the present invention sets a dynamic electricity price model based on a time series model combined with peak and valley time-of-use electricity prices. Specifically, the dynamic electricity price model adopts an autoregressive integrated moving average model in a time series model. The autoregressive integrated moving average model (ARIMA model) is used to predict future electricity price data based on historical electricity price data, including the following steps:

[0096] Collect historical electricity price data: such as daily, weekly or monthly electricity price records over a period of time;

[0097] Data cleaning: Clean the collected historical electricity price data to remove outliers, missing values, etc.;

[0098] Determine the difference order (d): Perform difference processing on the historical electricity price data to eliminate its non-stationarity. Determine the difference order d by observing the autocorrelation function (ACF) and partial autocorrelation function (PACF) diagrams of the differenced series;

[0099] Determine the autoregressive order (p) and the moving average order (q): Also by observing the ACF and PACF graphs, and using information criteria (such as AIC, BIC) and other methods, determine the order p of the autoregressive term and the order q of the moving average term;

[0100] Establish ARIMA model: According to the determined p, d, q values, establish ARIMA (p, d, q) model.

[0101] S300. Constructing an economic benefit optimization model based on the predicted photovoltaic power generation and the predicted electricity selling price; wherein the economic benefit optimization model includes an objective function with the goal of maximizing economic benefits, and constraints corresponding to the objective function.

[0102] Specifically, the objective function of the economic benefit optimization model is as follows:

[0103]

[0104] Among them, Z represents the total income of the photovoltaic power station in each time period; T is the time period, t is the time period, t=1,2,3,……T; is the predicted electricity price in period t; is the known power purchase price of the power grid company in time period t; s t is the electricity sales in period t; b t is the amount of electricity purchased in period t, and the amount of electricity purchased is used as the optimization variable.

[0105] The constraints corresponding to the objective function include:

[0106] Power balance constraints ensure a balance between power generation, power purchase, consumption and power sales in each period:

[0107]

[0108] Power generation is limited by sunlight and equipment capacity:

[0109]

[0110] Restrictions on electricity purchase and sales:

[0111]

[0112] Among them, p t is the predicted photovoltaic power generation in period t; b t is the amount of electricity purchased during period t; s t is the electricity sales in period t; u t represents the internal power consumption during time period t; b max is the upper limit of electricity purchase; max It is the upper limit of electricity sales.

[0113] S400: Solve the economic benefit optimization model to obtain a power purchase strategy that maximizes the economic benefit of the photovoltaic power station.

[0114] Specifically, when solving the economic benefit optimization model, this solution uses a mixed integer linear programming (MILP) model to handle the optimization of photovoltaic power generation and electricity sales revenue to achieve maximum economic benefits.

[0115] The electricity purchasing strategy obtained by solving this solution is a solution with a timing guidance strategy, which is used to guide the electricity purchase amount in each time period t within the time period T, thereby achieving the optimal economic benefit of the photovoltaic power station.

[0116] Example 2

[0117] like Figure 2 As shown, based on the same inventive concept as the above embodiment, the present invention also provides a photovoltaic power station revenue optimization device, comprising:

[0118] A first acquisition module is used to acquire the predicted weather data of the area where the target photovoltaic power station is located, and input the predicted weather data into a pre-trained photovoltaic power generation prediction model, and the photovoltaic power generation prediction model outputs the predicted photovoltaic power generation in the future time period;

[0119] The second acquisition module is used to obtain the historical electricity sales price of the target photovoltaic power station to the power grid, and input the historical electricity sales price into a pre-trained electricity sales price prediction model, and the electricity sales price prediction model outputs the predicted electricity sales price of the target photovoltaic power station to the power grid in the future time period;

[0120] A model building module, used to build an economic benefit optimization model based on the predicted photovoltaic power generation and the predicted electricity selling price; wherein the economic benefit optimization model includes an objective function with the maximum economic benefit as the goal, and constraints corresponding to the objective function;

[0121] The model solving module is used to solve the economic benefit optimization model to obtain a power purchasing strategy that maximizes the economic benefits of the photovoltaic power station.

[0122] Example 3

[0123] like Figure 3 As shown, the present invention also provides an electronic device 100 for implementing a photovoltaic power station revenue optimization method;

[0124] The electronic device 100 includes a memory 101 , at least one processor 102 , a computer program 103 stored in the memory 101 and executable on the at least one processor 102 , and at least one communication bus 104 .

[0125] The memory 101 may be used to store a computer program 103 , and the processor 102 implements the steps of a photovoltaic power station revenue optimization method in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101 .

[0126] The memory 101 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data (such as audio data) created according to the use of the electronic device 100, etc. In addition, the memory 101 may include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0127] At least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and uses various interfaces and lines to connect various parts of the entire electronic device 100.

[0128] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a photovoltaic power station revenue optimization method, and the processor 102 can execute the plurality of instructions to implement:

[0129] Obtaining forecast weather data for the area where the target photovoltaic power station is located, inputting the forecast weather data into a pre-trained photovoltaic power generation forecast model, and the photovoltaic power generation forecast model outputs the forecast photovoltaic power generation in the future time period;

[0130] Obtaining the historical electricity selling price of the target photovoltaic power station to the power grid, inputting the historical electricity selling price into a pre-trained electricity selling price prediction model, and the electricity selling price prediction model outputs the predicted electricity selling price of the target photovoltaic power station to the power grid in the future time period;

[0131] Based on the predicted photovoltaic power generation and the predicted electricity selling price, an economic benefit optimization model is constructed; wherein the economic benefit optimization model includes an objective function with the maximum economic benefit as the goal, and constraints corresponding to the objective function;

[0132] Solve the economic benefit optimization model to obtain a power purchase strategy that maximizes the economic benefit of the photovoltaic power station.

[0133] Example 4

[0134] If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0135] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0136] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0137] 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 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0138] 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 in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0139] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", 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 invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0140] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A photovoltaic power station revenue optimization method, It is characterized in that The steps include: Obtaining forecast weather data for the area where the target photovoltaic power station is located, inputting the forecast weather data into a pre-trained photovoltaic power generation forecast model, and the photovoltaic power generation forecast model outputs the forecast photovoltaic power generation in the future time period; Obtaining the historical electricity selling price of the target photovoltaic power station to the power grid, inputting the historical electricity selling price into a pre-trained electricity selling price prediction model, and the electricity selling price prediction model outputs the predicted electricity selling price of the target photovoltaic power station to the power grid in the future time period; Based on the predicted photovoltaic power generation and the predicted electricity selling price, an economic benefit optimization model is constructed; wherein the economic benefit optimization model includes an objective function with the maximum economic benefit as the goal, and constraints corresponding to the objective function; Solve the economic benefit optimization model to obtain a power purchase strategy that maximizes the economic benefit of the photovoltaic power station.

2. The photovoltaic power station revenue optimization method according to claim 1, It is characterized in that The photovoltaic power generation prediction model is trained using the following method: Obtaining historical weather data of the region where the photovoltaic power station is located, and historical power generation data corresponding to the historical weather data; Building a training set based on the historical weather data and the historical power generation data; Establish a power generation prediction model based on LSTM algorithm; Based on the training set, a back propagation algorithm is used to train the power generation prediction model to obtain the trained photovoltaic power generation prediction model.

3. The photovoltaic power station revenue optimization method according to claim 2, It is characterized in that After obtaining historical weather data of the region where the photovoltaic power station is located and historical power generation data corresponding to the historical weather data, the historical weather data and the historical power generation data are cleaned to process missing values ​​and abnormal values; Determine key features in the historical weather data that affect power generation, standardize the key features to obtain standardized key features, and construct the standardized key features and corresponding historical power generation data into a training set for model training.

4. The photovoltaic power station revenue optimization method according to claim 1, It is characterized in that The electricity selling price prediction model is constructed and trained based on an autoregressive integrated moving average model.

5. The photovoltaic power station revenue optimization method according to claim 4, It is characterized in that The electricity price prediction model is constructed based on the autoregressive integrated moving average model, and includes: Acquire historical electricity price time series data, perform differential processing on the historical electricity price time series data, and determine a differential order that makes the historical electricity price time series data stable; Determine the autoregressive order and the moving average order; According to the determined difference order, autoregressive order and moving average order, an autoregressive integrated moving average model is constructed.

6. The photovoltaic power station revenue optimization method according to claim 1, It is characterized in that The objective function of the economic benefit optimization model is as follows: Among them, Z represents the total income of the photovoltaic power station in each time period; T is the time period, t is the time period, t=1,2,3,……T; is the predicted electricity price in period t; is the known power purchase price of the power grid company in time period t; s t is the electricity sales in period t; b t is the amount of electricity purchased in period t, and the amount of electricity purchased is used as the optimization variable.

7. The photovoltaic power station revenue optimization method according to claim 1, It is characterized in that The constraints corresponding to the objective function include: Power balance constraints: Power generation limit: Restrictions on electricity purchase and sales: Among them, p t is the predicted photovoltaic power generation in period t; b t is the amount of electricity purchased during period t; s t is the electricity sales during period t; u t represents the internal power consumption during time period t; b max is the upper limit of electricity purchase; max It is the upper limit of electricity sales.

8. A photovoltaic power station revenue optimization device, It is characterized in that include: A first acquisition module is used to acquire the predicted weather data of the area where the target photovoltaic power station is located, and input the predicted weather data into a pre-trained photovoltaic power generation prediction model, and the photovoltaic power generation prediction model outputs the predicted photovoltaic power generation in the future time period; The second acquisition module is used to obtain the historical electricity sales price of the target photovoltaic power station to the power grid, and input the historical electricity sales price into a pre-trained electricity sales price prediction model, and the electricity sales price prediction model outputs the predicted electricity sales price of the target photovoltaic power station to the power grid in the future time period; A model building module, used to build an economic benefit optimization model based on the predicted photovoltaic power generation and the predicted electricity selling price; wherein the economic benefit optimization model includes an objective function with the maximum economic benefit as the goal, and constraints corresponding to the objective function; The model solving module is used to solve the economic benefit optimization model to obtain a power purchasing strategy that maximizes the economic benefits of the photovoltaic power station.

9. An electronic device, It is characterized in that It comprises a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the photovoltaic power station revenue optimization method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by the processor, the photovoltaic power station revenue optimization method according to any one of claims 1 to 7 is implemented.

Citation Information

Cited By

  • Inverter and energy storage cabinet multi-mode switching control system

    CN120566412A

  • Energy aggregation scheduling method, system and device and storage medium

    CN120822756A

  • Photovoltaic project economic evaluation parameter intelligent calibration method and system

    CN121524986A