Economic and energy index design and planning method oriented to source network load storage

Abstract

The invention belongs to the technical field of electric power project construction investment, and particularly relates to a source network load storage oriented economic and energy index design and planning method, which comprises the following steps: an electric energy monthly demand prediction model of a region where a source network load storage integrated project is located is based on a full-dimensional dynamic convolution-bidirectional time sequence convolution network and decomposition error correction; obtaining a prediction result of an annual energy consumption demand, and giving an annual available electric energy capacity model and an annual electric energy production-sales association model; and the economic benefits and energy efficiency indexes of the whole-process input and output of the source-network-load-storage integrated project are constructed. Providing an evaluation method for the economic benefits and the energy efficiency of the source-network-load-storage integrated project in different states; an improved raccoon optimization algorithm is adopted to optimize economic benefits and maximize energy efficiency, and supply and demand constraint verification is met. The method can be used for evaluating the investment value of the source-network-load-storage integrated project, and also provides support for energy optimization and utilization after construction.

Description

Technical Field

[0001] The invention belongs to the technical field of power project construction investment, and in particular relates to an economic and energy indicator design and planning method oriented to source, grid, load and storage. Background Art

[0002] We will strive to build a clean, low-carbon, safe and efficient energy system, improve the utilization rate of clean energy and the efficiency of power system operation, and better play the role of source-grid-load-storage integration and multi-energy complementarity in ensuring energy security. my country has built a number of provincial-level power auxiliary services, medium- and long-term, and spot market systems, introduced market players such as power supply side, load side, and electric energy storage, fully liberalized market-based transactions, promoted the establishment of a market trading mechanism for market-based transaction users to participate in the provision of auxiliary services, cultivated users' load management capabilities, and increased users' enthusiasm for peak load regulation.

[0003] However, the integrated source-grid-load-storage project involves multiple types of energy, such as hydropower, wind power, photovoltaic power and thermal power, as well as multiple links such as power transmission and distribution construction, load and storage, and is related to the export and purchase of electricity, as well as the complementarity and dispatch of different types of energy, and even to cross-regional power dispatch. On the one hand, it achieves a balance between energy production and use, and on the other hand, it involves the full utilization of clean and low-carbon energy. Therefore, the integrated source-grid-load-storage project is related to a variety of information. How to scientifically and effectively design and plan the integrated source-grid-load-storage project is extremely important for builders or investors.

[0004] For the design and planning of the above-mentioned integrated source, grid, load and storage projects, on the one hand, it is necessary to evaluate the total load demand from the perspective of the construction party. However, the current load demand calculation method is single and has low practicality for future scenarios, so a relatively accurate prediction method needs to be formed. On the other hand, from the perspective of investors, subjective evaluation is difficult to weigh the comprehensive value of the construction of integrated source, grid, load and storage projects, which leads to low credibility of the value assessment of integrated source, grid, load and storage projects, and thus delays the construction of integrated source, grid, load and storage projects. In addition, the evaluation results of integrated source, grid, load and storage also lack an effective means of planning and designing various indicators, which is not conducive to the guiding role of the evaluation method on the implementation results.

[0005] In summary, there is an urgent need for a load demand forecasting method, an investment value assessment model and method, and an optimization method suitable for source-grid-load-storage integrated projects to assist in the multi-angle scientific and effective design and planning of source-grid-load-storage integrated projects and optimize the corresponding indicators. Summary of the invention

[0006] In view of the technical problems that the current load demand calculation method is single and has low practicality for future scenarios, the present invention provides an economic and energy indicator design and planning method for source, grid, load and storage.

[0007] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0008] A method for designing and planning economic and energy indicators for source-grid-load-storage includes the following steps:

[0009] S1. Construct a monthly electricity demand forecasting model for the region where the source-grid-load-storage integration project is located based on full-dimensional dynamic convolution-bidirectional time series convolution network and decomposition error correction. Combined with the natural resource conditions of the project area, construct an annual available capacity model for power station generation. Finally, establish a correlation model between annual energy consumption demand and annual electricity production and sales volume.

[0010] S2. The construction cost, subsequent operation and maintenance cost, power production, line loss, terminal load and energy storage links in the construction of the source-grid-load-storage integrated project are uniformly described by economic quantities;

[0011] S3. Combined with the comprehensive value of the investment in the source-grid-load-storage integration project, a calculation model for economic benefits and energy efficiency used in the evaluation of the source-grid-load-storage integration project is constructed;

[0012] S4. Based on the potential supply and demand relationship of the integrated power generation, grid, load and storage project, calculate the economic and energy efficiency indicators under different supply and demand conditions, and conduct value assessment of the integrated power generation, grid, load and storage project according to different supply and demand conditions;

[0013] S5. Combined with the economic benefit and energy efficiency calculation model modified by the value assessment model under different supply and demand conditions, the improved raccoon optimization algorithm is used to optimize the economic benefit and energy efficiency to maximize and meet the supply and demand constraints.

[0014] The method for establishing the correlation model between annual energy consumption demand and annual electricity production and sales volume in S1 is:

[0015] S11. Collect historical power demand data with reduced noise. Specifically, obtain monthly historical power demand data H(t) and I(t); use a singular spectrum analysis algorithm to obtain a first intermediate monthly historical power demand sequence F without interference, i.e., denoised;

[0016] S12, constructing a matrix for the collected data set, wherein the method is to perform wavelet analysis on the first intermediate monthly power demand sequence F to obtain the second intermediate monthly power demand sequence F n There are N in total, where N represents the level of wavelet decomposition; based on the N second intermediate monthly power demand sequences F n , construct the first power demand matrix f, and normalize it to obtain the second monthly power demand matrix f 1 ;

[0017] S13, based on the step size of the time series, divide the second monthly power demand matrix f 1, and obtain the matrix slice with a step size of [t―T, t―1], and extract the features of the input matrix based on the dynamic convolutional neural network to obtain the comprehensive feature f 2 , T>1;

[0018] S14, the comprehensive feature f of the existing matrix 2 Input the bidirectional time series convolutional network time prediction model to obtain the monthly power demand forecast result D at the current time step t t ; Input the comprehensive features into the BiTCN convolutional time prediction model to obtain the time step t i Monthly electricity demand forecast results;

[0019] d(t)=D t

[0020] Where d(t) represents the comprehensive forecast result of monthly electricity demand at the current time step t, D t represents the monthly electricity demand forecast result at the current time step t;

[0021] S15, the monthly power demand forecast result D of the current time step t t Input the variational mode decomposition model to obtain the first monthly power demand forecast component G at the current time step t 1 , Second monthly electricity demand forecast component G 2 , the third month electricity demand forecast component G 3 ; Use the trained error correction model to correct the results of the first monthly power demand forecast component, the second monthly power demand forecast component, and the third monthly power demand forecast component, and then splice them to obtain the final monthly power demand forecast result g(t);

[0022] S16. Based on the monthly electricity demand forecast results g(t), evaluate the total annual electricity demand for industry, civil and commercial use in the region

[0023] S17. In combination with the natural conditions and electricity demand in the planning area of ​​the source-grid-load-storage integration project, the construction of the source-grid-load-storage integration project needs to evaluate the maximum capacity of various power stations on the source side and construct the power station construction capacity matrix C:

[0024]

[0025] They represent the maximum capacity of hydropower, wind power, photovoltaic power, thermal power, etc. on the source side. It also represents the maximum capacity of electrical energy that can be provided in the area;

[0026] Assume that the available capacity of various energy sources in year n is expressed as:

[0027]

[0028] Among them, η j j=1, 2, 3, 4 represent the output capacity of different power stations, for thermal power η j It can be 1. Wind power and photovoltaic power can be set according to the local historical meteorological laws. j is the annual average attenuation coefficient. The annual attenuation coefficient of photovoltaic power generation is currently approximately 0.4% to 2%. Based on this, the annual (n) available capacity matrix of the power station on the source side can be determined, as described below:

[0029] C(n)=[c 1 (n) c 2 (n) c 3 (n) c 4 (n)]

[0030] c j (n)j=1, 2, 3, 4 represent the available capacity of hydropower, wind power, photovoltaic power, thermal power, etc. on the source side respectively. Let K represent the number of hours per year, K=365*24=8760, then the annual maximum power supply on the source side (n) is

[0031] S18. Construct a correlation model between annual energy consumption demand and annual electricity production and sales (KW.h) matrix B, which is described in detail as follows:

[0032]

[0033] Where W(t) is the total annual electricity demand for industry, civil and commerce in the region of S16, b 1j j = 1, 2, 3, 4 represents the electricity production in the region, b 2j Indicates the loss in power transmission and distribution, b 3j Indicates the consumption at the load end, b 4j The energy storage is mainly for photovoltaic and wind energy. If hydropower and thermal power plants do not need to be equipped with energy storage devices, this part of the data is zero. If other types of energy require energy storage, the corresponding elements can be set according to actual needs. Indicates the proportion of different energy sources. Ideally, ξ j Representing the losses caused by different types of transmission and distribution and communication networks, the annual power production and sales (KW.h) matrix B can be described as:

[0034]

[0035] The method for obtaining the denoised monthly historical electric energy demand sequence in S11 is:

[0036] Obtain the specific data sequence H(t) and change trend sequence I(t) of the monthly electricity demand in the target source-grid-load-storage integration project area over the past few years;

[0037] H(t) and I(t) are input into a singular spectrum analysis including embedding, decomposition, grouping and reconstruction to extract seasonal trends, long-term trends and noises in the time series, implement the above nonlinear time series analysis or denoising function, and obtain the denoised first intermediate monthly historical electricity demand series F.

[0038] The method for constructing the first monthly electric energy demand matrix according to the N second intermediate monthly electric energy demand sequences in S12 is:

[0039] Let F n , n∈{1,2,…N} represents the nth second intermediate monthly power demand sequence, then the first monthly power demand matrix is ​​expressed as:

[0040]

[0041] Where T represents transpose, f represents the first power demand matrix; after normalization, the second monthly power demand matrix f is obtained 1 .

[0042] The method of the feature extraction training process in S13 is:

[0043] The second monthly power demand matrix is ​​divided by combining sliding window and slicing to obtain a time step of [t i ―T 1 ,t i ―1], t i ∈[t―T+T 1 ,t―1];

[0044] The time step is [t i ―T 1 ,t i ―1] as the matrix slices of the training sample, and the time step t i The real monthly electricity demand data is used as the label of the training sample to generate the training sample set;

[0045] For each training sample, the time step is [t i ―T 1 ,t i ―1] matrix slice and time step t i The other features of are concatenated to obtain the comprehensive feature f 2 .

[0046] The method for correcting the initial monthly comprehensive forecast result of electric energy demand by using the trained error correction model in S15 is:

[0047] Calculate time step t k ∈[t―T 2 ,t―1] and the initial monthly electricity demand forecast results at time step t k The deviation between the actual monthly electricity demand and the error sequence is constructed.

[0048] The error sequence P t The deviation between the initial monthly power demand comprehensive forecast result predicted by the LSTM network model at the current time step t and the actual monthly power demand at the current time step t is input;

[0049] According to the initial monthly comprehensive forecast result of the current time step t, the first monthly electricity demand forecast component G is decomposed into the first monthly electricity demand forecast component G after variational mode decomposition. 1 , Second monthly electricity demand forecast component G 2 , the third month electricity demand forecast component G 3 , and the deviation between the three initial monthly electricity demand forecast components at the current time step t and the actual monthly electricity demand at the current time step t is added to obtain the final monthly electricity demand forecast component at the current time step t, and the above final monthly electricity demand forecast components are combined to obtain the final monthly electricity demand forecast result g(t).

[0050] The method of uniformly describing the static construction cost, operation and maintenance cost and power production and sales in the S2 source-grid-load-storage integration project using economic means is as follows:

[0051] S21. The capital investment in multiple links involved in the construction of the source-grid-load-storage integrated project includes the capital investment in the construction of hydropower, wind power, photovoltaic power, thermal power, etc. on the source side, the capital investment in the construction of power transmission and distribution on the grid side, the capital investment in the supporting equipment and lines for industrial, commercial and residential power consumption on the load measurement side, and the capital investment in batteries and related equipment on the energy storage side. The construction investment cost of the source-grid-load-storage can be described by the matrix A:

[0052]

[0053] Among them, a j1 、a j2 、a j3 、a j4 j=1, 2, 3, 4 represent the full-process construction investment costs of different types of energy construction, namely the construction investment on the source side, grid side, load side and energy storage side. Specifically, the first column represents the investment cost of hydropower, the second column represents the investment cost of wind power, the third column represents the investment cost of photovoltaic power, and the fourth column represents the investment cost of thermal power;

[0054] S22. According to the uncertain risk input costs of electricity production, transmission and distribution, and user-side equipment and line operation and maintenance of hydropower, wind power, photovoltaic power, and thermal power, establish the operation and maintenance cost matrix D:

[0055]

[0056] In the operation and maintenance cost matrix D, each column represents the operation and maintenance costs of the source side, the grid side, the load side, and the energy storage side. The first column represents the operation and maintenance cost of hydropower, the second column represents the operation and maintenance cost of wind power, the third column represents the operation and maintenance cost of photovoltaic power, and the fourth column represents the operation and maintenance cost of thermal power.

[0057] S23. In order to facilitate the unified evaluation of the economic value of the investment in the source-grid-load-storage integration project, the production and sales of electric energy are uniformly converted into the corresponding economic costs, which are described by the electricity price corresponding to KW.h. Different types of energy may have different prices in each link of production and sales. A transaction price matrix P is constructed to calculate the prices corresponding to each part. The price matrix P is described as follows:

[0058]

[0059] The first column in matrix B represents the price of each link of hydropower, the second column represents the price of each link of wind power, the third column represents the price of each link of photovoltaic power, and the fourth column represents the price of each link of thermal power. In the source-grid-load-storage integrated project, if the energy transaction price does not involve the power generation end, then p 1j j=1, 2, 3, 4 can be 0;

[0060] S24. Based on the calculation method of Hadamard product, the power production, loss, load consumption and energy storage are converted into the corresponding economic benefit matrix M, which can be described as:

[0061]

[0062] Among them, ○ represents the calculation of Hadamard product, which means the matrix of the total number of rows and columns so that the elements with the same subscript are multiplied, m ij =b ij *p ij i=1,2,3,4j=1,2,3,4,m 1j Represents the revenue from the sale of electricity from hydropower, wind power, photovoltaic power, and thermal power on the source side, m 2j Represents the economic loss caused by power loss in the power transmission and distribution process and communication network, m 3j is the economic income generated by the load consuming electric energy, m 4j is the economic value of energy storage. Similarly, if the energy transaction price does not involve the power generation end, then m 1j For j=1, 2, 3, 4, just take 0.

[0063] The method for constructing the economic benefit and energy efficiency calculation model used in the evaluation of the source-grid-load-storage integration project in S3 is:

[0064] S31: Assuming the number of operating years is N, construct the main economic indicators Y = [y 1 y 2 y 3 ], used to evaluate the economic value of integrated project investment, where y 1 Represents the average annual economic return rate of the total source, grid, load and storage in this region; y 2 Represents the average annual economic return rate of new energy in this region; 3 Represents the average annual economic return rate of non-new energy; the specific calculation of each part is as follows:

[0065]

[0066] y 3 =y 1 ―y 2 ;

[0067] S32: Assuming the number of operating years is N, construct the power efficiency Z = [z 1 z 2 z 3 ], where z 1 represents the total annual energy output efficiency of source, grid, load and storage; 2 Represents the proportion of renewable energy power generation; 3 It represents the absorption capacity of new energy. The specific calculation of each part is as follows:

[0068]

[0069] S33: Combining economic indicators and energy efficiency indicators, an economic benefit and energy efficiency calculation model for the evaluation of source-grid-load-storage integrated projects is constructed. The specific description is:

[0070]

[0071] The method for evaluating the value of the source-grid-load-storage integration project in S4 according to different supply and demand conditions is as follows:

[0072] S41, when When the local electricity demand is large, it means that all kinds of power generation and supporting equipment of source, grid, load and storage need to operate at full load. The economic benefit and energy efficiency of the source, grid, load and storage integrated project adopt the economic benefit and energy efficiency calculation model of S33 [Y, Z] T Just do an assessment;

[0073] S42, when When the annual electricity demand is less than the planned annual available electricity, it can maximize the proportion of new energy consumption. Increase the average annual economic return rate of new energy 2 On the other hand, it has the value of providing electricity to areas outside the source-grid-load-storage integration project plan. The maximum amount of electricity it can provide to the outside world is The corresponding annual external power supply matrix O and price matrix U of the source-grid-load-storage integrated project can be described as follows:

[0074]

[0075] Among them, j j=1, 2, 3, 4 represent the external power supply of hydropower, wind power, photovoltaic power and thermal power respectively, u j j = 1, 2, 3, 4 represent the prices of hydropower, wind power, photovoltaic power and thermal power sold to the outside world respectively, and Therefore, the annual average economic return rate of the total source, grid, load and storage is 1 and the annual average economic return rate of new energy y 2 The calculation method is adjusted to:

[0076]

[0077] Since electric energy can be provided outside the interval, the output of new energy can be given priority. On the one hand, it can reduce the cost of local energy storage and provide space for subsequent new energy storage. On the other hand, it can also reduce the abandonment of new energy wind and solar. Therefore, the corresponding total energy efficiency, new energy efficiency and its absorption capacity evaluation method and its energy efficiency calculation method are adjusted as follows:

[0078]

[0079] Ideally, the actual maximum power supply of renewable energy is close to the annual planned available power, that is,

[0080] Subsequently, the adjusted economic benefits and energy efficiency are input into the calculation model [Y,Z] T Just do an assessment;

[0081] S43, when When there is no need to supply power to other areas, it means that there is a surplus of power from local sources, grids, loads and storage, and the proportion of new energy consumption can be prioritized. Maximize and improve the power generation and consumption capacity of new energy and the average annual economic return rate Y 2 , reducing the supply of other energy sources. In this case, the proportion of each energy source in power generation and consumption will change and is calculated as follows:

[0082]

[0083] Among them, λ i i = 2, 3 is used to adjust the energy storage and load consumption, 0 < λ i <1, the new annual energy demand and annual electricity production-sales (KW.h) matrix B only needs to calculate the values ​​of its elements according to the new weights, and then evaluate the various indicators of the source-grid-load-storage integration project based on step S33, and input them into the calculation model [Y, Z] T Just do the assessment.

[0084] The method of maximizing economic benefits and energy efficiency using the improved raccoon optimization algorithm in S5 is:

[0085] S51. The initialization strategy for constructing the improved raccoon optimization algorithm is:

[0086]

[0087] x i+1 =ax i (1-x i )

[0088] Among them, the model [Y, Z] T is the improved economic benefit and energy efficiency calculation model based on the above three supply and demand situations, x 0 is the initial state of the optimization algorithm, a∈(0,4], the larger a is, the higher the chaos is, and when a=4, it is in a completely chaotic state;

[0089] S52. The search strategy for constructing the improved raccoon optimization algorithm is:

[0090]

[0091] in, N is the number of individuals, Indicates the current individual position, is the j-th dimension position generated, r and I are integers randomly selected from (0,1) and (1,2), respectively. is the fitness of the random position, F i is the fitness of the ith individual;

[0092] S53. The adaptive optimal guidance strategy of the improved raccoon optimization algorithm is constructed as follows:

[0093]

[0094] u=R 1 +R 2 ×(1―(T max ―t) / T max ) 2

[0095] Where i = 1, 2, ..., N, j = 1, 2, 3; N is the number of individuals, Indicates the current individual position, are the local upper and lower bounds of the j-th dimension respectively; R 1 and R 2 is a random number between (0,1);

[0096] S54, initializing the parameters of the improved raccoon optimization algorithm; that is, taking the economic benefit and energy efficiency in the scheduling model as the population;

[0097] S55, obtain the optimal individual position of the current population, carry out maximum optimization based on this individual and perform supply and demand constraint verification on the result. If the verification passes, the optimal economic benefit and energy efficiency configuration scheme is obtained, that is, the optimal economic index Y = [y1y2y3] and electric energy efficiency Z = [z 1 z 2 z 3 ], where y 1 Represents the total annual average economic return rate of the source, grid, load and storage in this region described in S31, y 2 Represents the average annual economic return rate of new energy in the region described in S31, y 3 represents the average annual economic return rate of non-renewable energy described in S31, z 1 represents the total annual energy output efficiency of the source, grid, load and storage in S32; 2 Represents the proportion of renewable energy power generation in S32; z 3 Indicates the absorption capacity of new energy in S32; otherwise, returns to S54.

[0098] Compared with the prior art, the present invention has the following beneficial effects:

[0099] The present invention introduces a singular spectrum denoising method for the original monthly electricity demand data of a specified time window, uses a dynamic convolutional network to read depth information, and uses a convolutional time model to obtain prediction results. On the other hand, it also introduces variational mode decomposition, performs error correction and superposition from three components, and significantly improves the accuracy of the prediction. Furthermore, the electricity demand forecast results are combined with the natural resource conditions of the project investment site to establish an annual available capacity model, and then a correlation model between annual energy consumption demand and annual electricity production-sales volume is constructed. In order to evaluate the economic benefits of the source-grid-load-storage integrated project, the construction cost, operation and maintenance cost of multiple links of the source-grid-load-storage and electricity production, distribution, sales and storage are respectively constructed with their mathematical models, and the construction, operation and maintenance, and production and sales of the source-grid-load-storage integrated project are associated with the economic scale using the calculation method of the Hadamard product. In view of the economic benefits and energy efficiency of the source-grid-load-storage integrated project investment, a corresponding set of evaluation indicators and a corresponding calculation method are designed. Based on the supply and demand balance of power grid, load and storage, the economic and energy efficiency evaluation methods under different supply and demand conditions are given, which provides an evaluation method for the comprehensive investment value of power grid, load and storage integrated projects and the optimal utilization of energy after completion. Finally, based on the supply and demand relationship, an effective evaluation index optimization method is provided.

[0100] The energy types corresponding to the source, grid, load and storage in the present invention are described as mainly hydropower, wind power, photovoltaic power and thermal power. When planning and designing the actual source, grid, load and storage integrated project, one or more energy sources can be selected according to the local actual situation, or they can be replaced by other energy sources. The evaluation model can be used to replace the data or delete the data corresponding to irrelevant energy. The basic method is consistent, which has positive significance for the investment planning and design of the source, grid, load and storage integrated project construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0101] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0102] The structures, proportions, sizes, etc. illustrated in this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with the technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantial technical significance. Any structural modification, change in proportion or adjustment of size shall still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0103] Figure 1 It is a flow chart of the steps of the present invention. DETAILED DESCRIPTION

[0104] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. These descriptions are only to further illustrate the features and advantages of the present invention, rather than to limit the claims of the present invention. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0105] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0106] like Figure 1 As shown in the figure, a method for designing and planning economic and energy indicators for a source-grid-load-storage integrated project specifically includes the following steps:

[0107] S1: Based on ODConv (Omni-Dimensional Dynamic Convolution)-BiTCN (Bidirectional Temporal Convolutional Networks) and decomposition error correction, the monthly electricity demand forecasting model for the area where the source-grid-load-storage integration project is located is used to obtain the forecast results of annual energy consumption demand, and the annual available electricity capacity model is given as well as the correlation model with the annual electricity production and sales volume.

[0108] S11: Collecting historical power demand data with reduced noise, the specific method is to obtain monthly historical power demand data; using a singular spectrum analysis (Singular Spectrum Analysis, SSA) algorithm to obtain a first intermediate monthly historical power demand sequence without interference, i.e., denoised.

[0109] Historical electricity data refers to the specific data series H(t) and change trend series I(t) of electricity demand every month in the target source-grid-load-storage integration project area over several years.

[0110] Singular Spectrum Analysis (SSA) mainly includes four steps: embedding-decomposition-grouping-reconstruction. It is a nonlinear time series data processing method that uses decomposition and reconstruction of the time series matrix to extract seasonal trends, long-term trends, noise, etc. in the time series, so as to analyze or denoise the time series and use it for other tasks. H(t) and I(t) are input to obtain the denoised first intermediate monthly historical electricity demand series F.

[0111] S12: construct a matrix for the collected data set by wavelet analysis of the first intermediate monthly power demand sequence F and the second intermediate monthly power demand sequence F n A total of N, where N represents the level of wavelet decomposition. Based on the N second intermediate monthly power demand sequences, the first power demand matrix is ​​constructed, and the second monthly power demand matrix f is obtained by normalization. 1 .

[0112] Wavelet Transform (WT) is a multi-resolution signal analysis tool based on stretched and translated frequency and time windows. In theory, it will significantly improve the accuracy of power demand forecasting. Wavelet analysis extracts characteristic information from the signal, further solving computational problems and improving accuracy compared to Fourier transform. After the original data is processed by wavelet analysis, N subsequences are obtained, and these N subsequences are normalized into matrices for subsequent prediction processing.

[0113] Preferably, constructing the first monthly electric energy demand matrix according to the N second intermediate monthly electric energy demand sequences comprises:

[0114] Let F n , n∈{1,2,…N} represents the nth second intermediate monthly power demand sequence, then the first monthly power demand matrix is ​​expressed as:

[0115]

[0116] Where T represents transpose, f represents the first power demand matrix, and after normalization, the second monthly power demand matrix f is obtained. 1 .

[0117] S13: Divide the second monthly power demand matrix f based on the step size of the time series 1 , and obtain the matrix slice with step size [t―T, t―1], and extract the features of the input matrix based on the dynamic convolution neural network (Omni-Dimensional Dynamic Convolution, ODConv) to obtain the comprehensive feature f 2 , T>1.

[0118] ODConv is an improved convolutional neural network for processing image data. Its basic structure still includes convolutional layer, pooling layer and fully connected layer. The convolutional layer uses the convolution kernel to perform convolution operation on the input to extract spatial information and features. The pooling layer downsamples the output of the convolutional layer, reducing the size of the feature map and thus reducing the number of parameters and calculations. The fully connected layer is used for the final classification or regression task.

[0119] In order to extract more implicit features from the original power demand sequence, this method is different from the dynamic convolution method of ODConv. It uses SE attention to achieve dynamics in four dimensions: channel, filter, space, and convolution kernel, improving the accuracy of lightweight and large CNNs while maintaining efficient inference speed, providing better performance while reducing additional parameters. Therefore, ODConv is used to extract the features of the historical power demand sequence.

[0120] Preferably, the feature extraction training process includes:

[0121] The second monthly power demand matrix is ​​divided by combining sliding window and slicing to obtain a time step of [t i ―T 1 ,t i ―1], t i ∈[t―T+T 1 ,t―1].

[0122] The time step is [t i ―T 1 ,t i ―1] as the matrix slices of the training sample, and the time step t i The real monthly electricity demand data is used as the labels of training samples to generate a training sample set.

[0123] For each training sample, the time step is [t i ―T 1 ,t i ―1] matrix slice and time step t i The other features of are concatenated to obtain the comprehensive feature f 2 .

[0124] S14: Input the comprehensive features of the existing matrix into the Bidirectional Temporal Convolutional Networks (BiTCN) time prediction model to obtain the monthly electricity demand prediction result of the current time step t.

[0125] Bidirectional Temporal Convolution Network (BiTCN) is a variant of Convolutional Neural Network (CNN). Convolutional neural network is commonly used in the field of vision, but its application in prediction is still insufficient. BiTCN aims to use two temporal convolutional networks, one responsible for encoding future covariates and the other responsible for encoding past covariates and historical values ​​of the sequence. In this way, the model can learn temporal information from the data, and the use of convolution maintains computational efficiency.

[0126] In the specific implementation, BiTCN processes input data through multiple layers of convolutional layers. Each layer of convolution extracts features through different filters and activation functions, and uses dilated convolution to increase the receptive field, that is, to expand the model's coverage of input data without increasing parameters. In addition, by applying a regular network loss (Dropout) and L2 regularization technology, the model can suppress overfitting and improve generalization ability.

[0127] The comprehensive features are input into the BiTCN convolutional time prediction model to obtain the time step t i Monthly electricity demand forecast results.

[0128] Preferably, the initial monthly comprehensive forecast result of electric energy demand at the current time step t includes:

[0129] d(t)=D t

[0130] Where d(t) represents the comprehensive forecast result of monthly electricity demand at the current time step t, D t Represents the monthly electricity demand forecast result at the current time step t.

[0131] S15: The monthly electricity demand forecast result D at the current time step t t Input the variational mode decomposition model (VMD) to obtain the first monthly power demand forecast component, the second monthly power demand forecast component, and the third monthly power demand forecast component at the current time step t. Use the trained error correction model to correct the results of the first monthly power demand forecast component, the second monthly power demand forecast component, and the third monthly power demand forecast component, and then splice them to obtain the final monthly power demand forecast result g(t).

[0132] VMD (Variational Mode Decomposition) is an adaptive, completely non-recursive modal variation and signal processing method. Its adaptability is reflected in the determination of the number of modal decompositions of a given sequence according to actual conditions. In the subsequent search and solution process, it can adaptively match the optimal center frequency and finite bandwidth of each mode, and can realize the frequency domain division of the signal, thereby obtaining the effective components of the given signal, and finally obtaining the optimal solution to the variational problem.

[0133] In the implementation of the present invention, this decomposition method is mainly used to divide the prediction results before correction into three segments for error correction, thereby effectively avoiding the impact of volatility and reducing the non-stationarity of the monthly electricity forecast result sequence with high complexity and strong nonlinearity, thereby ultimately achieving the effect of enhancing error correction.

[0134] Preferably, the method of correcting the initial monthly comprehensive forecast result of electric energy demand by using the trained error correction model includes:

[0135] S151: Calculate time step t k ∈[t―T 2 ,t―1] and the initial monthly electricity demand forecast results at time step t k The deviation between the actual monthly electricity demand and the error sequence is constructed.

[0136] S152: Error sequence P t The deviation between the initial monthly energy demand comprehensive forecast result predicted by the input LSTM network model at the current time step t and the actual monthly energy demand at the current time step t.

[0137] S153: Based on the initial monthly power demand comprehensive forecast result at the current time step t, the first monthly power demand forecast component G is decomposed into the first monthly power demand forecast component G by variational mode decomposition. 1 , Second monthly electricity demand forecast component G 2 , the third month electricity demand forecast component G 3 , and the deviation between the three initial monthly power demand forecast components at the current time step t and the actual monthly power demand at the current time step t is added to obtain the final monthly power demand forecast component at the current time step t. The above final monthly power demand forecast components are combined to obtain the final monthly power demand forecast result g(t).

[0138] S16: Based on the monthly electricity demand estimation model g(t), the total annual electricity demand for industry, civil and commercial use in the region can be evaluated.

[0139] S17: In combination with the natural conditions and electricity demand in the planning area of ​​the source-grid-load-storage integration project, the construction of the source-grid-load-storage integration project needs to evaluate the maximum capacity (unit: KW) of various power stations on the source side. For this purpose, the power station construction capacity matrix C is constructed:

[0140]

[0141] They represent the maximum capacity of hydropower, wind power, photovoltaic power, thermal power, etc. on the source side. It also represents the maximum capacity of electricity that can be provided in the area.

[0142] As different energy generation equipment and materials increase in operating time and are affected by local climate conditions, it is difficult to ensure that each energy source can always work at its designed capacity, and the power generation capacity is attenuated and the output is insufficient, especially for photovoltaic power generation, which will attenuate to a certain extent every year. At the same time, photovoltaic, wind power and hydropower will all be affected by annual meteorological conditions, and the output will also be different. In order to accurately evaluate the investment benefits of the source-grid-load-storage integration project in the future, the available capacity expression of each type of energy in the nth year is assumed to be:

[0143]

[0144] Among them, η j j=1, 2, 3, 4 represent the output capacity of different power stations, for thermal power η i It can be 1. Wind power and photovoltaic power can be set according to local historical meteorological laws. i is the annual average attenuation coefficient, and the annual attenuation coefficient of photovoltaic power generation is currently approximately 0.4% to 2%. Therefore, the annual (n) available capacity matrix of the power station on the source side can be determined, as described below:

[0145] C(n)=[c 1 (n) c 2 (n) c 3 (n) c 4 (n)]

[0146] c j (n)j=1, 2, 3, 4 represent the available capacity of hydropower, wind power, photovoltaic power, thermal power, etc. on the source side respectively. Let K represent the number of hours per year, K=365*24=8760, then the annual maximum power supply on the source side (n) is

[0147] S18: Due to the influence of geographical environment and climatic conditions, when new energy is able to generate sufficient electricity, it needs to be supplied to the load side in a timely manner. On the other hand, it can also be used for energy storage to reduce the abandonment rate of new energy and wind power, improve the consumption of new energy, and improve the balance of power supply. For this purpose, a correlation model between annual energy consumption demand and annual electricity production and sales (KW.h) matrix B is constructed, which is described as follows:

[0148]

[0149] Where W(t) is the total annual electricity demand for industry, civil and commerce in the region of S16, b 1j j = 1, 2, 3, 4 represents the electricity production in the region, b 2j Indicates the loss in power transmission and distribution, b 3j Indicates the consumption at the load end, b 4jThe energy storage is mainly for photovoltaic and wind energy. If hydropower and thermal power plants do not need to be equipped with energy storage devices, this part of the data is zero. If other types of energy require energy storage, the corresponding elements can be set according to actual needs. Different energy proportions, ideally In order to improve the absorption capacity of new energy, its proportion is usually the maximum absorption ratio under the condition of ensuring the smoothness of the power grid. The annual proportion of new energy can be roughly determined based on the planned capacity and output capacity of new energy. At present, most of the domestic projects plan and construct source-grid-load-storage integrated projects with the consumption of new energy accounting for no less than 40% of the total power consumption. ξ j Represents the losses caused by different types of power transmission and distribution and communication networks. The annual power production and sales (KW.h) matrix B can be described as:

[0150]

[0151] The above main calculations are for calculating the power demand-production and sales model of the integrated source-grid-load-storage project for different energy situations. In actual situations, it is necessary to calculate the values ​​according to the specific situation of the project implementation. The matrix B provides a calculation model with the same structure for the subsequent power efficiency and economic benefit evaluation of the integrated source-grid-load-storage project.

[0152] S2: The construction costs, subsequent operation and maintenance costs, power production, line losses, terminal loads and energy storage involved in the construction of the integrated source-grid-load-storage project are uniformly described using economic quantities.

[0153] S21: The capital investment in multiple links involved in the construction of the source-grid-load-storage integrated project, specifically the construction capital investment of hydropower, wind power, photovoltaic, thermal power, etc. on the source side, the capital investment of transmission and distribution construction on the grid side, the capital investment of supporting equipment and lines for industrial, commercial and residential electricity consumption on the load measurement, and the capital investment of batteries and related equipment on the energy storage side, the construction investment cost of the source-grid-load-storage (unit: 10,000 yuan) can be described by matrix A:

[0154]

[0155] Among them, a j1 、a j2 、a j3 、a j4 j=1, 2, 3, 4 respectively represent the full-process construction investment costs of different types of energy construction, namely the construction investment on the source side, grid side, load side and energy storage side. Specifically, the first column represents the wind power investment cost, the second column represents the thermal power investment cost, the third column represents the photovoltaic investment cost, and the fourth column represents the hydropower investment cost.

[0156] S22: Based on the uncertain risk input costs (unit: 10,000 yuan) of electricity production, transmission and distribution, and user-side equipment and line operation and maintenance of hydropower, wind power, photovoltaic power, and thermal power, establish the operation and maintenance cost matrix D:

[0157]

[0158] In the operation and maintenance cost matrix D, each column represents the operation and maintenance cost of the source side, grid side, load side and energy storage side, where the first column represents the hydropower operation and maintenance cost, the second column represents the wind power operation and maintenance cost, the third column represents the photovoltaic operation and maintenance cost, and the fourth column represents the thermal power operation and maintenance cost.

[0159] S23: In order to facilitate the unified evaluation of the economic value of the source-grid-load-storage integrated project investment, the production and sales of electric energy are uniformly converted into the corresponding economic costs, which are described by the electricity price corresponding to KW.h. Considering that different types of energy may have different prices in each link of production and sales, in order to accurately and effectively evaluate the overall economic benefits, a transaction price matrix P is constructed to calculate the prices corresponding to each part. The price matrix P is described as follows:

[0160]

[0161] There are differences in the operation modes of the integrated source, grid, load and storage projects after they are completed. Therefore, the values ​​of each element in the price matrix P need to be determined in combination with the future operation mode, which helps to accurately evaluate the economic benefits of the investment in the integrated source, grid, load and storage project. The first column in the matrix B represents the prices of each link of hydropower, the second column represents the prices of each link of wind power, the third column represents the prices of each link of photovoltaic power, and the fourth column represents the prices of each link of thermal power. In the integrated source, grid, load and storage project, if the energy transaction price does not involve the power generation end, then p 1j For j=1, 2, 3, 4, just take 0.

[0162] S24: Based on the calculation method of Hadamard product, the power production, loss, load consumption and energy storage are converted into the corresponding economic benefit matrix M, which can be described as:

[0163]

[0164] Among them, ○ represents the calculation of Hadamard product, which means the matrix of the total number of rows and columns so that the elements with the same subscript are multiplied, m ij =b ij *p ij i=1,2,3,4j=1,2,3,4. m 1j The revenue from the sale of electricity on the source side (hydropower, wind power, photovoltaic power, thermal power), m 2j Represents the economic loss caused by power loss in the power transmission and distribution process and communication network, m 3j is the economic income generated by the load consuming electric energy, m 4jis the economic value of energy storage. Similarly, if the energy transaction price does not involve the power generation end, then m 1j For j=1, 2, 3, 4, just take 0.

[0165] S3: Combining the comprehensive value of investment in integrated power generation, grid, load and storage projects, a set of economic benefits and energy efficiency indicators for the entire input and output process of integrated power generation, grid, load and storage projects is constructed to form an evaluation model for describing the investment value of integrated power generation, grid, load and storage projects.

[0166] S31: Assuming the number of operating years is N, construct the main economic indicators Y = [y 1 y 2 y 3 ] is used to evaluate the economic value of integrated project investment. 1 Represents the average annual economic return rate of the total source, grid, load and storage in this region. 2 Represents the average annual economic return rate of new energy in this region. 3 Represents the average annual economic return rate of non-new energy. The specific calculation of each part is as follows:

[0167]

[0168] y 3 =y 1 ―y 2 ;

[0169] Other economic indicators can be calculated based on the above model. For example, when only considering the economic benefits of source, grid, load and storage of a certain type of energy, the irrelevant elements in matrices A, D and M can be set to zero.

[0170] S32: Assuming the number of operating years is N, construct the power efficiency Z = [z 1 z 2 z 3 ], which is used to describe the energy efficiency, inter-regional energy dispatch and new energy consumption of integrated project construction. 1 It indicates the total energy output efficiency of the source, grid, load and storage each year, reflecting the balance of power supply and demand in the region, and also reflects the utilization rate of the source, grid, load and storage in the region. 2 Represents the proportion of renewable energy power generation, reflecting the renewable energy output capacity of the region. 3 Indicates the absorption capacity of new energy. The specific calculation of each part is as follows:

[0171]

[0172] Other energy efficiency indicators can also be calculated based on the above model. For example, if only a certain type of energy production efficiency or energy storage efficiency is considered, the irrelevant elements in the matrices B and C(n) can be set to zero.

[0173] S33: Combining economic indicators and energy efficiency indicators, an economic benefit and energy efficiency calculation model for the evaluation of source-grid-load-storage integrated projects is constructed. The specific description is:

[0174]

[0175] S4: Based on the potential supply and demand relationship of the integrated power generation, grid, load and storage project, the calculation methods of economic and energy efficiency indicators under different supply and demand conditions are given, and an evaluation method is provided for the potential economic benefits and energy efficiency of the integrated power generation, grid, load and storage project, thereby providing support for the optimal utilization of energy after completion.

[0176] In combination with the natural conditions and energy demand scale of different regions, and under the condition of ensuring reliable and stable energy supply and demand, the value assessment of source-grid-load-storage integration projects is carried out for different supply and demand situations, including the following three situations:

[0177] S41: When When the local electricity demand is large, it means that all kinds of power generation and supporting equipment of source, grid, load and storage need to operate at full load. The economic benefit and energy efficiency of the source, grid, load and storage integrated project adopt the economic benefit and energy efficiency calculation model of S33 [Y, Z] T Just do the assessment.

[0178] S42: When When the annual electricity demand is less than the planned annual available electricity, it can maximize the proportion of new energy consumption. Increase the average annual economic return rate of new energy 2 On the other hand, it has the value of providing electricity outside the source-grid-load-storage integrated project area. The maximum amount of electricity it can provide to the outside world is The corresponding annual external power supply matrix O and its price matrix U of the source-grid-load-storage integrated project can be described as follows:

[0179]

[0180] Among them, j j=1, 2, 3, 4 represent the external power supply of hydropower, wind power, photovoltaic power and thermal power respectively, u j j = 1, 2, 3, 4 represent the prices of hydropower, wind power, photovoltaic power and thermal power sold to the outside world respectively, and (t). Therefore, the annual average economic return rate of the total source, grid, load and storage is 1 and the annual average economic return rate of new energy y 2 The calculation method is adjusted to:

[0181]

[0182] Since electric energy can be provided outside the interval, the output of new energy can be given priority. On the one hand, it can reduce the cost of local energy storage and provide space for subsequent new energy storage. On the other hand, it can also reduce the abandonment of new energy wind and solar. Therefore, the corresponding total energy efficiency, new energy efficiency and its absorption capacity evaluation method and its energy efficiency calculation method are adjusted as follows:

[0183]

[0184] Ideally, the actual maximum power supply of renewable energy is close to the annual planned available power, that is,

[0185] Subsequently, the adjusted economic benefits and energy efficiency are input into the calculation model [Y,Z] T Just do an assessment;

[0186] S43: When When there is no need to supply power to other areas, it means that there is a surplus of power from local sources, grids, loads and storage, and the proportion of new energy consumption can be prioritized. Maximize and improve the power generation and consumption capacity of new energy and the average annual economic return rate Y 2 , reducing the supply of other energy sources. In this case, the proportion of each energy generation and consumption will change and is calculated as follows:

[0187]

[0188] Among them, λ i (i=2,3) is used to adjust the energy storage and load consumption, 0<λ i <1. Therefore, the new annual energy demand and annual electricity production and sales (KW.h) matrix B only needs to calculate the values ​​of its elements according to the new weights, and then evaluate the various indicators of the source-grid-load-storage integration project based on step S33.

[0189] S5: Taking the supply and demand relationship described above for the integrated source-grid-load-storage project as a constraint, based on the updated economic benefit and energy efficiency models in the three cases, the economic benefit and energy efficiency are maximized as the optimization goals, and the intelligent search algorithm is used to find the optimal parameters of economic benefit and energy efficiency.

[0190] The intelligent search algorithm used in this embodiment is the Improved Coati Optimization Algorithm (ICOA).

[0191] The raccoon optimization algorithm is a heuristic optimization algorithm based on the behavior of coatis populations in nature, proposed by M Dehghani et al. in 2023. The algorithm mainly solves the optimization problem by simulating the behavior of raccoons hunting iguanas and escaping from predators. Compared with other well-known heuristic algorithms, it has obvious advantages by balancing the use of global search and local search. The key to the raccoon optimization algorithm lies in the iguana hunting or exploration step and the predator escape or development step. In the iguana hunting stage, the strategy of attacking iguanas is simulated, so that the algorithm moves to different positions in the search space, reflecting the global search ability in the problem space. In the predator escape stage, the simulation of raccoons constantly escaping from predators allows the algorithm to approach the safe position of the current position. This is the development ability of COA in local search.

[0192] The improved raccoon optimization algorithm is based on the original algorithm and adds chaos mapping, flight strategy, and lens imaging refraction reverse learning strategy to solve nonlinear problems and effectively avoid falling into local optimality and expand the search range.

[0193] For those skilled in the art, given the constraints of the intelligent search algorithm and the parameters that need to be updated, based on the characteristics of different intelligent search algorithms, those skilled in the art can undoubtedly figure out how to use the intelligent search algorithm to update the target parameters. Common intelligent search algorithms include: coyote algorithm, particle swarm algorithm, whale algorithm, vulture algorithm or ant colony algorithm, etc.

[0194] S51: The initialization strategy for constructing the Improved Coati Optimization Algorithm (ICOA) is:

[0195]

[0196] x i+1 =ax i (1-x i )

[0197] Among them, the model [Y, Z] T is the improved economic benefit and energy efficiency calculation model based on the above three supply and demand situations, x 0 is the initial state of the optimization algorithm, a∈(0,4], the larger a is, the higher the chaos is, and when a=4, it is in a completely chaotic state.

[0198] S52: The search strategy for constructing the Improved Coati Optimization Algorithm (ICOA) is:

[0199]

[0200] in, N is the number of individuals, Indicates the current individual position, is the j-th dimension position generated, r and I are integers randomly selected from (0,1) and (1,2), respectively. is the fitness of the random position, F i is the fitness of the ith individual.

[0201] S53: The adaptive optimal guidance strategy of the Improved Coati Optimization Algorithm (ICOA) is constructed as follows:

[0202]

[0203] u=R 1 +R 2 ×(1―(T max ―t) / T max ) 2

[0204] Where i = 1, 2, ..., N, j = 1, 2, 3. N is the number of individuals, Indicates the current individual position, are the local upper and lower bounds of the j-th dimension respectively. 1 and R 2 is a random number between (0,1).

[0205] S54: Initialize the parameters of the improved raccoon optimization algorithm; that is, take the economic benefit and energy efficiency in the scheduling model as the population.

[0206] S55: Get the optimal individual position of the current population, use this individual to carry out maximum optimization and perform supply and demand constraint verification on the result. If the verification passes, the optimal economic benefit and energy efficiency configuration plan is obtained, that is, the optimal economic indicator Y = [y 1 y 2 y 3 ] and power efficiency Z = [z 1 z 2 z 3 ], where y 1 Represents the total annual average economic return rate of the source, grid, load and storage in this region described in S31, y 2 Represents the average annual economic return rate of new energy in the region described in S31, y 3 represents the average annual economic return rate of non-renewable energy described in S31, z 1 It represents the total annual energy output efficiency of source, grid, load and storage in S32. 2 Represents the proportion of renewable energy power generation in S32. 3Indicates the consumption capacity of new energy in S32. Otherwise, return to S54.

[0207] Only the preferred embodiments of the present invention are described in detail above, but the present invention is not limited to the above embodiments. Various changes can be made within the knowledge scope of ordinary technicians in this field without departing from the purpose of the present invention, and various changes should be included in the protection scope of the present invention.

Claims

1. A method for designing and planning economic and energy indicators for source-grid-load-storage, characterized in that: The following steps are involved: S1. Construct a monthly electricity demand forecasting model for the region where the source-grid-load-storage integration project is located based on full-dimensional dynamic convolution-bidirectional time series convolution network and decomposition error correction. Combined with the natural resource conditions of the project area, construct an annual available capacity model for power station generation. Finally, establish a correlation model between annual energy consumption demand and annual electricity production and sales volume. S2. The construction cost, subsequent operation and maintenance cost, power production, line loss, terminal load and energy storage links in the construction of the source-grid-load-storage integrated project are uniformly described by economic quantities; S3. Combined with the comprehensive value of the investment in the source-grid-load-storage integration project, a calculation model for economic benefits and energy efficiency used in the evaluation of the source-grid-load-storage integration project is constructed; S4. Based on the potential supply and demand relationship of the integrated power generation, grid, load and storage project, calculate the economic and energy efficiency indicators under different supply and demand conditions, and conduct value assessment of the integrated power generation, grid, load and storage project according to different supply and demand conditions; S5. Combined with the economic benefit and energy efficiency calculation model modified by the value assessment model under different supply and demand conditions, the improved raccoon optimization algorithm is used to optimize the economic benefit and energy efficiency to maximize and meet the supply and demand constraints.

2. The method for designing and planning economic and energy indicators for source-grid-load-storage according to claim 1, characterized in that: The method for establishing the correlation model between annual energy consumption demand and annual electricity production and sales volume in S1 is: S11. Collect historical power demand data with reduced noise. Specifically, obtain monthly historical power demand data H(t) and I(t); use a singular spectrum analysis algorithm to obtain a first intermediate monthly historical power demand sequence F without interference, i.e., denoised; S12, constructing a matrix for the collected data set, wherein the method is to perform wavelet analysis on the first intermediate monthly power demand sequence F to obtain the second intermediate monthly power demand sequence F n There are N in total, where N represents the level of wavelet decomposition; based on the N second intermediate monthly power demand sequences F n , construct the first power demand matrix f, and obtain the second monthly power demand matrix f1 through normalization; S13, based on the step size of the time series, divide the second monthly power demand matrix f1, and obtain the matrix slice with a step size of [t-T, t-1], and extract the features of the input matrix based on the dynamic convolutional neural network to obtain the comprehensive feature f2, T>1; S14, input the comprehensive feature f2 of the existing matrix into the bidirectional temporal convolutional network time prediction model to obtain the monthly power demand prediction result D at the current time step t t ; Input the comprehensive features into the BiTCN convolutional time prediction model to obtain the time step t i Monthly electricity demand forecast results; d(t)=D t Where d(t) represents the comprehensive forecast result of monthly electricity demand at the current time step t, D t represents the monthly electricity demand forecast result at the current time step t; S15, the monthly power demand forecast result D of the current time step t t Input the variational mode decomposition model to obtain the first monthly power demand forecast component G1, the second monthly power demand forecast component G2, and the third monthly power demand forecast component G3 at the current time step t; use the trained error correction model to correct the results of the first monthly power demand forecast component, the second monthly power demand forecast component, and the third monthly power demand forecast component, and then splice them to obtain the final monthly power demand forecast result g(t); S16. Based on the monthly electricity demand forecast results g(t), evaluate the total annual electricity demand for industry, civil and commercial use in the region S17. In combination with the natural conditions and electricity demand in the planning area of ​​the source-grid-load-storage integration project, the construction of the source-grid-load-storage integration project needs to evaluate the maximum capacity of various power stations on the source side and construct the power station construction capacity matrix C: They represent the maximum capacity of hydropower, wind power, photovoltaic power, thermal power, etc. on the source side. It also represents the maximum capacity of electrical energy that can be provided in the area; Assume that the available capacity of various energy sources in year n is expressed as: Among them, η j j=1, 2, 3, 4 represent the output capacity of different power stations, for thermal power η j It can be 1. Wind power and photovoltaic power can be set according to the local historical meteorological laws. j is the annual average attenuation coefficient. The annual attenuation coefficient of photovoltaic power is currently approximately 0.4% to 2%. Therefore, the annual (n) available capacity matrix of the power station on the source side can be determined, which is described as follows: C(n)=[c1(n)c2(n)c3(n)c4(n)] c j (n)j=1, 2, 3, 4 represent the available capacity of hydropower, wind power, photovoltaic power, thermal power, etc. on the source side respectively. Let K represent the number of hours per year, K=365*24=8760, then the annual maximum power supply on the source side (n) is S18. Construct a correlation model between annual energy consumption demand and annual electricity production and sales (KW.h) matrix B, which is described as follows: Where W(t) is the total annual electricity demand for industry, civil and commercial use in the region in S16, b 1j j = 1, 2, 3, 4 represents the electricity production in the region, b 2j Indicates the loss in power transmission and distribution, b 3j Indicates the consumption at the load end, b 4j The energy storage is mainly for photovoltaic and wind energy. If hydropower and thermal power plants do not need to be equipped with energy storage devices, this part of the data is zero. If other types of energy require energy storage, the corresponding elements can be set according to actual needs. Indicates the proportion of different energy sources. Ideally, ξ j Representing the losses caused by different types of transmission and distribution and communication networks, the annual power production and sales (KW.h) matrix B can be described as:

3. The method for designing and planning economic and energy indicators for source-grid-load-storage according to claim 2, characterized in that: The method for obtaining the denoised monthly historical electric energy demand sequence in S11 is: Obtain the specific data sequence H(t) and change trend sequence I(t) of the monthly electricity demand in the target source-grid-load-storage integration project area over the past few years; H(t) and I(t) are input into a singular spectrum analysis including embedding, decomposition, grouping and reconstruction to extract seasonal trends, long-term trends and noises in the time series, implement the above nonlinear time series analysis or denoising function, and obtain the denoised first intermediate monthly historical electricity demand series F.

4. The method for designing and planning economic and energy indicators for source-grid-load-storage according to claim 2, characterized in that: The method for constructing the first monthly electric energy demand matrix according to the N second intermediate monthly electric energy demand sequences in S12 is: Let F n , n∈{1,2,…N} represents the nth second intermediate monthly power demand sequence, then the first monthly power demand matrix is ​​expressed as: Wherein, T represents transposition, and f represents the first electric energy demand matrix; after normalization processing, the second monthly electric energy demand matrix f1 is obtained.

5. The method for designing and planning economic and energy indicators for source-grid-load-storage according to claim 2, characterized in that: The method of the feature extraction training process in S13 is: The second monthly power demand matrix is ​​divided by combining sliding window and slicing to obtain a time step of [t i ―T1,t i ―1], t i ∈[t―T+T1,t―1]; The time step is [t i ―T1,t i ―1] as the matrix slices of the training sample, and the time step t i The real monthly electricity demand data is used as the label of the training sample to generate the training sample set; For each training sample, the time step is [t i ―T1,t i ―1] matrix slice and time step t i The other features are concatenated to obtain the comprehensive feature f2.

6. The method for designing and planning economic and energy indicators for source-grid-load-storage according to claim 2, characterized in that: The method for correcting the initial monthly comprehensive forecast result of electric energy demand by using the trained error correction model in S15 is: Calculate time step t k The initial monthly electricity demand forecast results of ∈[t―T2,t―1] and the time step t k The deviation between the actual monthly electricity demand and the error sequence is constructed. The error sequence P t The deviation between the initial monthly power demand comprehensive forecast result predicted by the LSTM network model at the current time step t and the actual monthly power demand at the current time step t is input; According to the comprehensive forecast result of the initial monthly electricity demand at the current time step t, it is decomposed into the first monthly electricity demand forecast component G1, the second monthly electricity demand forecast component G2, the third monthly electricity demand forecast component G3 through variational modal decomposition, and the deviations between the three initial monthly electricity demand forecast components at the current time step t and the actual monthly electricity demand at the current time step t are added to obtain the final monthly electricity demand forecast component at the current time step t, and the above final monthly energy demand forecast components are combined to obtain the final monthly energy demand forecast result g(t).

7. The method for designing and planning economic and energy indicators for source-grid-load-storage according to claim 1, characterized in that: The method of uniformly describing the static construction cost, operation and maintenance cost and power production and sales in the S2 source-grid-load-storage integration project using economic means is as follows: S21. The capital investment in multiple links involved in the construction of the source-grid-load-storage integrated project includes the capital investment in the construction of hydropower, wind power, photovoltaic power, thermal power, etc. on the source side, the capital investment in the construction of power transmission and distribution on the grid side, the capital investment in the supporting equipment and lines for industrial, commercial and residential power consumption on the load measurement side, and the capital investment in batteries and related equipment on the energy storage side. The construction investment cost of the source-grid-load-storage can be described by the matrix A: Among them, a j1 、a j2 、a j3 、a j4 j=1, 2, 3, 4 represent the full-process construction investment costs of different types of energy construction, namely the construction investment on the source side, grid side, load side and energy storage side. Specifically, the first column represents the investment cost of hydropower, the second column represents the investment cost of wind power, the third column represents the investment cost of photovoltaic power, and the fourth column represents the investment cost of thermal power; S22. According to the uncertain risk input costs of electricity production, transmission and distribution, and user-side equipment and line operation and maintenance of hydropower, wind power, photovoltaic power, and thermal power, establish the operation and maintenance cost matrix D: In the operation and maintenance cost matrix D, each column represents the operation and maintenance costs of the source side, the grid side, the load side, and the energy storage side. The first column represents the operation and maintenance cost of hydropower, the second column represents the operation and maintenance cost of wind power, the third column represents the operation and maintenance cost of photovoltaic power, and the fourth column represents the operation and maintenance cost of thermal power. S23. In order to facilitate the unified evaluation of the economic value of the investment in the source-grid-load-storage integration project, the production and sales of electric energy are uniformly converted into the corresponding economic costs, which are described by the electricity price corresponding to KW.h. Different types of energy may have different prices in each link of production and sales. A transaction price matrix P is constructed to calculate the prices corresponding to each part. The price matrix P is described as follows: The first column in matrix B represents the price of each link of hydropower, the second column represents the price of each link of wind power, the third column represents the price of each link of photovoltaic power, and the fourth column represents the price of each link of thermal power. In the source-grid-load-storage integrated project, if the energy transaction price does not involve the power generation end, then p 1j j=1, 2, 3, 4 can be 0; S24. Based on the calculation method of Hadamard product, the power production, loss, load consumption and energy storage are converted into the corresponding economic benefit matrix M, which can be described as: Among them, ○ represents the calculation of Hadamard product, which means the matrix of the total number of rows and columns so that the elements with the same subscript are multiplied, m ij =b ij *p ij i=1,2,3,4j=1,2,3,4,m 1j Represents the revenue from the sale of electricity from hydropower, wind power, photovoltaic power, and thermal power on the source side, m 2j Represents the economic loss caused by power loss in the power transmission and distribution process and communication network, m 3j is the economic income generated by the load consuming electric energy, m 4j is the economic value of energy storage. Similarly, if the energy transaction price does not involve the power generation end, then m 1j For j=1, 2, 3, 4, just take 0.

8. The method for designing and planning economic and energy indicators for source-grid-load-storage according to claim 1, characterized in that: The method for constructing the economic benefit and energy efficiency calculation model used in the evaluation of the source-grid-load-storage integration project in S3 is: S31: Assuming the number of operating years is N, construct the main economic indicator Y = [y1y2y3] to evaluate the economic value of the integrated project investment, where y1 represents the annual average economic return rate of the total source, grid, load and storage in the region; y2 represents the annual average economic return rate of new energy in the region; y3 represents the annual average economic return rate of non-new energy; the specific calculation of each part is as follows: y3=y1―y2; S32: Assuming the number of operating years is N, construct the power efficiency Z = [z1z2z3], where z1 represents the total energy output efficiency of the source, grid, load and storage each year; z2 represents the proportion of new energy power generation; z3 represents the absorption capacity of new energy. The specific calculation of each part is as follows: S33: Combining economic indicators and energy efficiency indicators, an economic benefit and energy efficiency calculation model for the evaluation of source-grid-load-storage integrated projects is constructed. The specific description is:

9. The method for designing and planning economic and energy indicators for source-grid-load-storage according to claim 8, characterized in that: The method for evaluating the value of the source-grid-load-storage integration project in S4 according to different supply and demand conditions is as follows: S41, when When the local electricity demand is large, it means that all kinds of power generation and supporting equipment of source, grid, load and storage need to operate at full load. The economic benefit and energy efficiency of the source, grid, load and storage integrated project adopt the economic benefit and energy efficiency calculation model of S33 [Y, Z] T Just do an assessment; S42, when When the annual electricity demand is less than the planned annual available electricity, it can maximize the proportion of new energy consumption. Improve the annual average economic return rate of new energy Y2, on the other hand, it has the value of providing electricity to areas outside the source-grid-load-storage integration project plan. The maximum amount of electricity it can provide to the outside world is The corresponding annual external power supply matrix O and price matrix U of the source-grid-load-storage integrated project can be described as follows: Among them, j j=1, 2, 3, 4 represent the external power supply of hydropower, wind power, photovoltaic power and thermal power respectively, u j j = 1, 2, 3, 4 represent the prices of hydropower, wind power, photovoltaic power and thermal power sold to the outside world respectively, and Therefore, the calculation method of the total annual average economic return rate y1 of source, grid, load and storage and the annual average economic return rate y2 of new energy is adjusted to: Since electric energy can be provided outside the interval, the output of new energy can be given priority. On the one hand, it can reduce the cost of local energy storage and provide space for subsequent new energy storage. On the other hand, it can also reduce the abandonment of new energy wind and solar. Therefore, the corresponding total energy efficiency, new energy efficiency and its absorption capacity evaluation method and its energy efficiency calculation method are adjusted as follows: Ideally, the actual maximum power supply of renewable energy is close to the annual planned available power, that is, Subsequently, the adjusted economic benefits and energy efficiency are input into the calculation model [Y,Z] T Just do an assessment; S43, when When there is no need to supply power to other areas, it means that there is a surplus of power from local sources, grids, loads and storage, and the proportion of new energy consumption can be prioritized. Maximize, improve the power generation and consumption capacity of new energy and the annual average economic return rate Y2, reduce the supply of other energy, in this case, the proportion of each energy generation and consumption will change and is calculated as follows: Among them, λ i i = 2, 3 is used to adjust the energy storage and load consumption, 0 < λ i <1, the new annual energy demand and annual electricity production-sales (KW.h) matrix B only needs to calculate the values ​​of its elements according to the new weights, and then evaluate the various indicators of the source-grid-load-storage integration project based on step S33, and input them into the calculation model [Y, Z] T Just do the assessment.

10. The method for designing and planning economic and energy indicators for source-grid-load-storage according to claim 1, characterized in that: The method of maximizing economic benefits and energy efficiency using the improved raccoon optimization algorithm in S5 is: S51. The initialization strategy for constructing the improved raccoon optimization algorithm is: x i+1 =ax i (1―x i ) Among them, the model [Y, Z] T is the improved economic benefit and energy efficiency calculation model based on the above three supply and demand situations. x0 is the initial situation of the optimization algorithm, a∈(0,4], the larger a is, the higher the chaos is. When a=4, it is in a completely chaotic state. S52. The search strategy for constructing the improved raccoon optimization algorithm is: in, j=1,2,3, N is the number of individuals, Indicates the current individual position, is the j-th dimension position generated, r and I are integers randomly selected from (0,1) and (1,2), respectively. is the fitness of the random position, F i is the fitness of the ith individual; S53, constructing the adaptive optimal guidance strategy of the improved raccoon optimization algorithm is: u=R1+R2×(1―(T max ―t) / T max ) 2 Where i = 1, 2, ..., N, j = 1, 2, 3; N is the number of individuals, Indicates the current individual position, are the local upper and lower bounds of the j-th dimension respectively; R1 and R2 are random numbers between (0,1); S54, initializing the parameters of the improved raccoon optimization algorithm; that is, taking the economic benefit and energy efficiency in the scheduling model as the population; S55. Obtain the optimal individual position of the current population, carry out maximum optimization based on this individual and perform supply and demand constraint verification on the result. If the verification passes, the optimal economic benefit and energy efficiency configuration plan is obtained, that is, the optimal economic indicator Y = [y1y2y3] and electric energy efficiency Z = [z1z2z3], among which y1 represents the total annual average economic return rate of the source, grid, load and storage in the region described in S31, y2 represents the annual average economic return rate of the new energy in the region described in S31, y3 represents the annual average economic return rate of the non-new energy described in S31, z1 represents the total annual energy output efficiency of the source, grid, load and storage in S32; z2 represents the proportion of power generation of the new energy in S32; z3 represents the absorption capacity of the new energy in S32; otherwise, return to S54.

Images