Intelligent energy station site selection optimization method and device, electronic equipment and storage medium

Abstract

The application provides a smart energy station site selection optimization method and device, electronic equipment and storage medium, relates to the new energy field, and the method comprises the following steps: constructing a space-time graph through a space-time mask autoencoder in a space-time generative pre-training model; pre-training the space-time graph by using the space-time generative pre-training model, learning the internal space-time mode of the truck energy charging behavior through an adaptive mask strategy, obtaining a space-time representation and training a space-time prediction dynamic diffusion model; and taking the minimum comprehensive cost as an objective function, constructing a smart energy station site selection optimization model to optimize the site selection of the smart energy station. The smart energy station site selection optimization model constructed by the application is a multi-objective optimization model integrating hydrogenation, charging, photovoltaic and energy storage, comprehensively considers different energy supply needs of new energy trucks, and improves the accuracy and real-time performance of site selection prediction. In addition, the application pays more attention to environmental protection and power grid stability in site selection decision-making, and realizes comprehensive optimization of the site selection scheme.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of new energy, in particular to a smart energy station site selection optimization method and device, an electronic device and a storage medium. BACKGROUND

[0002] With the continuous progress of new energy truck technology and the increasing policy support, the share of new energy trucks is showing a rapid growth trend. Many regions have formulated specific new energy truck development goals, including expected growth in new energy commercial vehicle production, comprehensive electrification plans for public vehicles, and specific promotion measures for new energy trucks.

[0003] The rapid development of new energy trucks faces the following challenges: ① Although charging stations for new energy vehicles have been built on a large scale, most existing charging station infrastructure considers the charging needs of new energy family passenger cars with 7 seats or less, and less considers the charging needs of electric trucks: in terms of charging power, truck charging piles usually support higher charging power, and electric trucks basically support double-gun charging of one vehicle with two fast-charging interfaces; in terms of auxiliary power supply, the BMS auxiliary power supply of electric trucks is 24V, while the BMS auxiliary power supply of small cars is 12V. ② With the gradual rise of the hydrogen fuel cell vehicle market, the demand for hydrogen refueling stations is also growing. However, the existing hydrogen refueling station network still has obvious deficiencies in quantity and distribution, and cannot fully meet the growing energy demand. Current hydrogen refueling stations are mostly concentrated in specific areas, making it difficult for many potential users to conveniently access hydrogen energy due to geographical limitations. In addition, the service capacity of existing hydrogen refueling stations is limited by their size and technical level, and they cannot efficiently provide fast energy charging services for a large number of vehicles during peak periods. Based on this, the existing charging stations and hydrogen refueling stations cannot meet the energy needs of new energy trucks. SUMMARY

[0004] To overcome the deficiencies of the prior art, the present application provides a smart energy station site selection optimization method and device, an electronic device and a storage medium, which solve the problems of over-reliance on specific energy types, lack of comprehensive energy management strategies, and defects in dynamic demand response and multi-objective optimization in new energy truck smart energy station site selection.

[0005] To achieve the above purposes, the present application is implemented through the following technical solutions:

[0006] In a first aspect, the embodiments of the present application provide a smart energy station site selection optimization method, which comprises: obtaining first data information of new energy trucks in a historical period, and preprocessing the first data information to obtain second data information; analyzing the operation mode of the new energy trucks based on the second data information, and determining the main operation area and the potential growth area of the new energy trucks; wherein the operation mode includes driving route, cargo type and transportation frequency; constructing a spatio-temporal graph to represent the charging behavior of the truck by using a spatio-temporal mask autoencoder in a spatio-temporal generative pre-training model; wherein the spatio-temporal graph takes the truck and the charging station as nodes, and takes the spatio-temporal relationship between the truck and the charging station as edges; pre-training the spatio-temporal graph by using the spatio-temporal generative pre-training model, learning the internal spatio-temporal pattern of the charging behavior of the truck by using an adaptive mask strategy, and obtaining a spatio-temporal representation; taking the spatio-temporal representation as input information, training a spatio-temporal prediction dynamic diffusion model to learn the charging demand change from the current state to the future state for charging demand prediction; based on the charging demand prediction of the spatio-temporal prediction dynamic diffusion model, taking the minimum comprehensive cost as the objective function, constructing a smart energy station site selection optimization model to optimize the site selection of the smart energy station; wherein the smart energy station site selection optimization model is a multi-objective optimization model integrating hydrogenation, charging, photovoltaic and energy storage.

[0007] In a second aspect, the embodiments of the present application provide a smart energy station site selection optimization device, which comprises a preprocessing module, an analysis and determination module, a spatio-temporal graph construction module, a pre-training module, a learning and prediction module and a model construction module; wherein the preprocessing module is used to obtain first data information of new energy trucks in a historical period, and preprocess the first data information to obtain second data information; the analysis and determination module is used to analyze the operation mode of the new energy trucks based on the second data information, and determine the main operation area and the potential growth area of the new energy trucks; wherein the operation mode includes driving route, cargo type and transportation frequency; the spatio-temporal graph construction module is used to construct a spatio-temporal graph to represent the charging behavior of the truck by using a spatio-temporal mask autoencoder in a spatio-temporal generative pre-training model; wherein the spatio-temporal graph takes the truck and the charging station as nodes, and takes the spatio-temporal relationship between the truck and the charging station as edges; the pre-training module is used to pre-train the spatio-temporal graph by using the spatio-temporal generative pre-training model, learn the internal spatio-temporal pattern of the charging behavior of the truck by using an adaptive mask strategy, and obtain a spatio-temporal representation; the learning and prediction module is used to take the spatio-temporal representation as input information, train a spatio-temporal prediction dynamic diffusion model to learn the charging demand change from the current state to the future state for charging demand prediction; the model construction module is used to construct a smart energy station site selection optimization model based on the charging demand prediction of the spatio-temporal prediction dynamic diffusion model, take the minimum comprehensive cost as the objective function, and optimize the site selection of the smart energy station; wherein the smart energy station site selection optimization model is a multi-objective optimization model integrating hydrogenation, charging, photovoltaic and energy storage.

[0008] In a third aspect, an electronic device is provided, which comprises a processor, a memory, and a program stored in the memory and executable on the processor, and the program, when executed by the processor, implements the intelligent energy station site selection optimization method in the first aspect.

[0009] In a fourth aspect, a computer readable storage medium is provided, which stores a program or instructions, and the program or instructions, when executed by a processor, implement the intelligent energy station site selection optimization method in the first aspect.

[0010] The present application provides an intelligent energy station site selection optimization method, device, electronic device and storage medium. Compared with the prior art, the present application has the following beneficial effects:

[0011] The intelligent energy station site selection optimization model constructed by the present application is a multi-objective optimization model integrating hydrogenation, charging, photovoltaic and energy storage, which comprehensively considers the different energy supply needs of new energy trucks, improves the accuracy and real-time performance of site selection prediction by introducing a deep learning algorithm. In addition, the present application pays more attention to environmental protection and grid stability in site selection decision-making, and realizes comprehensive optimization of the site selection scheme. The present application pays more attention to environmental protection in site selection decision-making, optimizes the energy structure and improves the energy utilization efficiency by introducing photovoltaic power generation and energy storage equipment. This comprehensive consideration of charging and hydrogenation and other energy supply methods in site selection optimization helps to reduce the impact on the environment and promote the development of the logistics industry towards a greener and more intelligent direction. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0013] Figure 1 is an exemplary schematic diagram of the intelligent energy station site selection optimization method provided by the present application;

[0014] Figure 2 is another exemplary schematic diagram of the intelligent energy station site selection optimization method provided by the present application;

[0015] Figure 3 is a logistics enterprise new energy truck energy demand prediction framework diagram provided by the present application;

[0016] Figure 4 is a schematic diagram of the intelligent energy station system design provided by the present application;

[0017] Figure 5 is a flow chart of a smart energy station site selection optimization algorithm provided by an embodiment of the present application;

[0018] Figure 6 is a structural schematic diagram of a smart energy station site selection optimization device provided by an embodiment of the present application;

[0019] Figure 7 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application are described clearly and completely. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0021] It should be noted that, in this document, relational terms such as first and second and the like can be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises... a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0022] The embodiments of the present application provide a smart energy station site selection optimization method and device, an electronic device, and a storage medium, and solve the problems of over-reliance on specific energy types, lack of comprehensive energy management strategies, and defects in dynamic demand response and multi-objective optimization in new energy truck smart energy station site selection.

[0023] The technical solutions in the embodiments of the present application are as follows to solve the above technical problems:

[0024] With the continuous progress of new energy truck technology and the increasing policy support, the share of new energy trucks is showing a rapid growth trend. Many regions have formulated specific new energy truck development goals, including expected growth in new energy commercial vehicle production, comprehensive electrification plans for public domain vehicles, and specific promotion measures for new energy trucks.

[0025] The rapid development of new energy trucks faces the following challenges: ①Although charging stations for new energy vehicles have been constructed on a large scale, most existing charging station infrastructure is designed to meet the charging needs of new energy family passenger cars with 7 seats or fewer, and less consideration is given to the charging needs of electric trucks. In terms of charging power, truck charging piles usually support higher charging power, and electric trucks basically support dual-gun charging of a vehicle with two fast-charging interfaces. In terms of auxiliary power supply, the BMS auxiliary power supply of an electric truck is 24V, while the BMS auxiliary power supply of a small car is 12V. ②With the gradual rise of the hydrogen fuel cell vehicle market, the demand for hydrogen refueling stations is also increasing. However, the existing hydrogen refueling station network still has obvious deficiencies in quantity and distribution, and cannot fully meet the growing energy needs. Current hydrogen refueling stations are mostly concentrated in specific areas, making it difficult for many potential users to conveniently access hydrogen energy due to geographical limitations. In addition, the service capacity of existing hydrogen refueling stations is limited by their size and technical level, and they cannot efficiently provide fast energy charging services for a large number of vehicles during peak periods.

[0026] Based on the above two points, the existing charging stations and hydrogen refueling stations cannot meet the energy needs of new energy trucks. Existing technologies often ignore the comprehensive layout of multi-energy supply stations, that is, simultaneous planning of charging and hydrogen refueling facilities. In addition, most methods do not fully utilize renewable energy sources such as solar energy and energy storage technology, which is an important deficiency in terms of energy costs and environmental impact. Furthermore, existing technologies generally lack the integration of real-time data and dynamic adjustment capabilities, which are particularly important when responding to rapid changes in logistics demand. Finally, existing methods are not comprehensive in considering the comprehensive evaluation of cost, efficiency, and environmental impact, often focusing on a single indicator while ignoring the importance of multi-objective optimization.

[0027] In summary, existing technologies have certain limitations in the site selection optimization of new energy truck smart energy stations, including excessive dependence on specific energy types, lack of comprehensive energy management strategies, and deficiencies in dynamic demand response and multi-objective optimization.

[0028] In order to better understand the above technical solutions, the following will combine the drawings in the specification and specific embodiments to explain the above technical solutions in detail.

[0029] First, a smart energy station site selection optimization method provided by the embodiments of the present application will be introduced.

[0030] The flowchart of the smart energy station site selection optimization method provided by the embodiments of the present application is shown in Figure 1 、 Figure 2 and Figure 3 The smart energy station site selection optimization method can include the following steps S110-S160.

[0031] S110, acquire first data information of the new energy truck in a historical period, and pre-process the first data information to obtain second data information.

[0032] S120, analyze the operation mode of the new energy truck based on the second data information, and determine the main operation area and the potential growth area of the new energy truck; wherein the operation mode includes the driving route, the cargo type and the transportation frequency.

[0033] S130, construct a spatio-temporal graph to represent the charging behavior of the truck by using a spatio-temporal mask autoencoder in a spatio-temporal generative pre-training model; wherein the spatio-temporal graph takes the truck and the charging station as nodes, and takes the spatio-temporal relationship between the truck and the charging station as edges.

[0034] S140, pre-train the spatio-temporal graph by using the spatio-temporal generative pre-training model, learn the internal spatio-temporal pattern of the charging behavior of the truck by using an adaptive mask strategy, and obtain a spatio-temporal representation.

[0035] S150, take the spatio-temporal representation as input information, train a spatio-temporal prediction dynamic diffusion model to learn the charging demand change from the current state to the future state for charging demand prediction.

[0036] S160, based on the charging demand prediction of the spatio-temporal prediction dynamic diffusion model, take the minimum comprehensive cost as an objective function, construct a smart energy station site optimization model to optimize the site selection of the smart energy station; wherein the smart energy station site optimization model is a multi-objective optimization model integrating hydrogenation, charging, photovoltaic and energy storage.

[0037] The above is a specific implementation of the smart energy station site optimization method provided by the embodiment of the present application. The charging demand prediction process of the new energy truck includes spatio-temporal generative pre-training and diffusion model prediction of charging demand; in the pre-training stage, the mask autoencoder MAE task is used as the training target, and the spatio-temporal representation function is learned to reconstruct the masking information of the spatio-temporal data according to the unmasked spatio-temporal data. The smart energy station site optimization model considers geographical location, traffic convenience, land cost, environmental impact, and power grid access conditions, and takes into account the charging aggregator cost-user cost-power grid stability cost; the smart energy station site optimization model can evaluate the energy demand of different types of new energy trucks, including power and hydrogen, and consider the energy consumption characteristics and energy supplement time of different vehicle types.

[0038] It should be noted that the present application predicts the incremental charging / hydrogenation demand of new energy trucks of future logistics enterprises by collecting and analyzing historical and current data of new energy trucks, including the number, type, distribution and usage frequency of vehicles, and infrastructure data of existing charging stations and hydrogenation stations. By using the spatio-temporal generative pre-training model and the spatio-temporal prediction dynamic diffusion model, the present application can predict the future new energy truck charging demand trend, and design a smart energy station model integrating hydrogenation, charging, photovoltaic power generation and energy storage, considering key factors such as geographical location, traffic convenience, land cost, environmental impact and grid access conditions.

[0039] It should also be noted that the smart energy station site optimization model constructed by the present application is a multi-objective optimization model, which realizes the optimal balance of charging aggregator cost, user cost and grid stability cost while ensuring economy, environmental friendliness and operation efficiency. By using the scarab beetle optimization algorithm integrating the black widow thought, the present application completes the optimization of the site of the smart energy station. This method combines local search and global search, balances exploration and development, to achieve efficient search, and outputs the optimal or suboptimal charging station site selection scheme after meeting the convergence criteria.

[0040] In an example, in the process of constructing the spatio-temporal graph, in order to capture the spatio-temporal information of new energy truck charging, a three-dimensional tensor is defined wherein, represents the region, i.e. the location of the truck charging station; represents the set of time points; F represents various features of each region at each time point, including land type, traffic flow, charging occupancy rate, charging pricing and weather conditions; a spatio-temporal hypergraph is used for spatio-temporal modeling; the hypergraph is composed of three parts:

[0041] ① vertex Each vertex represents a region r in time point t;

[0042] ② hyperedge ε={e1...e H}, each of which connects multiple vertices to reflect multi-part regional relationships (for example, all charging stations can be connected by a hyperedge);

[0043] ③ vertex-hyperedge association wherein N represents the number of vertices, and H is a trainable parameter.

[0044] In an example, in the pre-training phase of the spatio-temporal graph, a mask autoencoder (MAE) task is used as the training target, and the goal of the MAE task is to reconstruct the masking information of the spatio-temporal data according to the unmasked spatio-temporal data by learning a spatio-temporal representation function f; for [t K-L+1, t KTemporal-spatial data trained during the period, the objective function is as follows:

[0045]

[0046] In the formula, The prediction bias is represented by M, and M is a mask tensor, and is an element-wise multiplication operation, and W represents a prediction linear layer.

[0047] In one example, the aforementioned preprocessing of the first data information to obtain the second data information can specifically include the following steps:

[0048] S210, cleaning the first data information, filling in missing values, identifying and removing abnormal data.

[0049] S220, different data is merged according to the needs to form a unified data set and data format.

[0050] S230, identify the time period, week and whether it is a holiday, identify the space position of the logistics park, etc.

[0051] S240, sliding window processing is performed on the time series data, the geographical position information is visualized, and the data set is divided into training set, validation set and test set.

[0052] S250, check whether the processed data set is balanced and whether there is a data leakage problem, and save the processed data as a format acceptable for model training to obtain the second data information.

[0053] In some embodiments, the spatio-temporal generative pre-training model is also used for customizing temporal pattern encoding, hierarchical spatial pattern encoding and downstream tasks.

[0054] In the embodiments of the present application, it can be understood that the stage corresponding to the downstream task occurs after the pre-training stage, and the spatio-temporal representation generated by the pre-trained model is used to promote the downstream prediction task; the downstream task stage is represented as:

[0055]

[0056] In the formula, ζ refers to the spatio-temporal features generated by f according to the first L timestamps before the Kth timestamp; the output is a prediction for the next P time intervals, and the DYffusion model is used as the prediction function g.

[0057] In some embodiments, the spatio-temporal prediction dynamic diffusion model for charging demand prediction comprises defining a problem, a diffusion process and a generation process; it can be understood that the present application fuses the spatio-temporal features generated by the spatio-temporal generative pre-training model with the relevant features of real-time traffic flow, real-time charging occupancy, real-time charging pricing and real-time weather conditions of new energy trucks; the fused features are used as the input of the spatio-temporal prediction dynamic diffusion model, and the spatio-temporal prediction dynamic diffusion model will use these features to predict the charging demand;

[0058] Defining a fused data set x t = Concat(ζ,η)

[0059] In the formula, ζ represents the spatio-temporal features generated by the pre-training model, and η represents the real-time spatio-temporal features, represents the space where the data is located, including the spatial dimension (charging station longitude and latitude) and the channel size (plot type, traffic flow, charging occupancy, charging pricing and weather conditions);

[0060] (1) Problem definition

[0061] The charging demand prediction of the new energy truck of the logistics enterprise is defined as a spatio-temporal probability prediction problem, and the charging demand of each charging station in a future time period is predicted; the task of probability prediction is to learn the conditional distribution P(x t+1：t+h |x t-l+1：t ), that is, to use the information from the past l data points to predict the charging demand of h data points;

[0062] (2) Diffusion process

[0063] The core idea of the diffusion model is to "destroy" the data by gradually adding noise, and then restore the data through a denoising process; in the standard diffusion model, the forward diffusion process gradually degrades the data by gradually increasing Gaussian noise, and the reverse diffusion process gradually removes noise to reconstruct the original data through a denoising network, which is trained to minimize the reconstruction error, thereby learning the generation process of the data; in the case of dynamic prediction, the diffusion model can be trained to minimize the prediction error:

[0064]

[0065] In the formula, is the data distribution, ‖·‖ is the norm, and s (0) = x t+1:t+h is the prediction target; describes the uniform distribution on the set {a, a+1, …, b}; in practice, R θthat has been added to the data points using score matching targets;

[0066] ① Forward process

[0067] Temporal interpolation as a forward process, to impose temporal bias, a temporal conditioned network is trained to interpolate between data; concretely, given a baseline h, the network is trained to predict for i∈{1,…,h-1}, the objective is:

[0068]

[0069] ② Backward process

[0070] In the second stage, the predictor network F θ is trained to predict x t+h such that for where S denotes a schedule that maps diffusion steps to interpolation time steps; the network is frozen, and inference randomness is enabled, denoted by a random variable, ξ represents the random dropout weights of the neural network;

[0071]

[0072] (3) Generation process

[0073] To incorporate F θ , the setting of the learned prediction of the initial condition is defined as i0:=0 and :=x t ; in the simplest case, the predictor network is supervised by all possible time steps given by the temporal resolution of the training data, N=h and In general, the interpolation time steps should satisfy 0=i0<i n m < h, where 0<n<m≤N-1; the equivalent role of the predictor and the denoising network in the diffusion model is called the diffusion backbone, and the temporal condition of the diffusion backbone is i n ; the generation process of DYffusion is as follows:

[0074]

[0075] where s (0) t and correspond to the prediction of the initial condition and the intermediate step, respectively; n=0 is the start of the backward process, and n=N is the output of the backward process;

[0076] Let s be the time variable, DYffusion will dynamically model as: ​​

[0077]

[0078] The initial condition is given by x(t) = x t x, and the objective function during the prediction process is:

[0079]

[0080] The prediction process is equivalent to evaluating at discrete points in the prediction window [t, t+h].

[0081] In some embodiments, the aforementioned customized temporal pattern encoding includes:

[0082] S310, normalizing the spatio-temporal data and constructing an embedding matrix, and using an embedding layer to convert discrete features into continuous embedding vectors.

[0083] S320, initializing the embedding vectors by random initialization or using a pre-trained model.

[0084] S330, performing periodic encoding on the temporal features and position encoding on the spatial features, and fusing the obtained periodic encoding result and position encoding result to obtain spatio-temporal embedding information.

[0085] S340, based on the spatio-temporal embedding information, optimizing the parameters of the embedding layer during model training, and fine-tuning according to task requirements, to obtain an effective representation that can capture the intrinsic features and structure of the spatio-temporal data.

[0086] In one example, the specific steps of the customized temporal pattern encoding are as follows:

[0087] ① Data preprocessing

[0088] The original data is normalized using the Z-Score function, and then masked using the mask operation; the calculation formula of the Z-Score function is as follows:

[0089]

[0090] where X is the original data point, μ is the mean of the data set, and σ is the standard deviation of the data set;

[0091] ② Constructing an embedding matrix

[0092] Initialization of the embedding matrix E: where V is the number of features and D is the dimension of the embedding;

[0093] ③ Initializing embedding vectors

[0094] Randomly initialize the embedding vectors: e i ~ Uniform(-1,1), where ei is the embedding vector of the i-th feature;

[0095] ④ Periodic encoding of temporal features

[0096] Temporal pattern encoding is performed using hypergraph neural networks; for each vertex (time point), a circular encoding is applied to capture its position within the time cycle; the circular encoding usually uses sine and cosine functions to represent the time point, as follows:

[0097]

[0098] where e t represents the encoding of time point t, and T is the cycle period.

[0099] In some embodiments, the aforementioned hierarchical spatial pattern encoding is based on a hypergraph capsule clustering network, and includes the following steps:

[0100] S410, constructing a hypergraph structure by initializing region embeddings and calculating the transfer information of regions to cluster centers.

[0101] S420, iteratively updating hyperedge representations and region hyperedge connections using the dynamic routing mechanism of the capsule network to enhance clustering capability.

[0102] S430, modeling class embeddings through a high-level hypergraph neural network to learn cross-class relationships.

[0103] S440, gradually increasing the difficulty of prediction based on a class-aware mask strategy to guide the model to learn robust spatiotemporal representations in the pre-training phase, and to realize spatial hierarchical pattern encoding from local to global.

[0104] S450, fusing the temporal encoding vector and the spatial encoding vector, as well as the embedding vector obtained by the hypergraph capsule clustering network, to form a comprehensive spatiotemporal representation.

[0105] In one example, the specific steps of hierarchical spatial pattern encoding are as follows:

[0106] ① Initialization of region embeddings

[0107] For the embedding of each region r at time point t, the following formula is used for initialization:

[0108] v r,t = squash(VΓ r,t +c)

[0109] where Γ r,t is the original feature embedding of region r at time t, V and c are learnable weight matrices and bias, and squash is a nonlinear activation function (such as softmax) to ensure the scale of the embedding;

[0110] ②Compute transfer information

[0111] Transfer information The formula from each region t to the cluster center (hyperedge) i is:

[0112]

[0113] In the formula, H' i,r,t represents the connection weight of region r to hyperedge i, represents the vector outer product;

[0114] ③Iterative hypergraph learning

[0115] Iteratively update the hyperedge representation s using the dynamic routing mechanism of the capsule network i,t and the region-hyperedge connection c i,r,t :

[0116]

[0117] In the formula, is the embedding of hyperedge i at time t in the jth iteration, is the weight in the jth iteration, is the logarithmic probability;

[0118] ④Cross-class relationship learning

[0119] Model the class embedding using an advanced hypergraph neural network:

[0120]

[0121] In the formula, H" represents the advanced hypergraph structure, and σ is the activation function;

[0122] ⑤Class-aware masking strategy

[0123] Design an adaptive masking strategy that combines the cluster information learned in the previous step to gradually increase the prediction difficulty:

[0124]

[0125] In the formula, M r,t is the mask matrix, and Mask is the information of the region at time t that is selectively masked according to the cluster information and the mask rate mask_rate;

[0126] ⑥Fusion of spatiotemporal features

[0127] Fuse the temporal encoding vector e t and the spatial encoding vector e s ​and the embedding vector v obtained by the hypergraph capsule clustering network r,t Fused together, forming a comprehensive spatiotemporal representation:

[0128] e st = Concat(e t ,e s ,v r,t )

[0129] In the formula, Concat represents the concatenation of vectors.

[0130] In some embodiments, the solution algorithm idea of the intelligent energy station site selection optimization model includes: combining the spatiotemporal distribution prediction results of the charging demand, using the fusion of the black widow idea to optimize the site selection of the intelligent energy station; in the algorithm initialization, a candidate solution population representing the possible charging station positions is generated; in each iteration of the generation, by imitating the behavior of the black widow, some poor candidate solutions are strategically abandoned, and the current solution is updated through the rolling strategy of the dung beetle to explore the solution space; the algorithm combines local search and global search, balances exploration and development, and realizes efficient search; through iterative updating and fitness evaluation, the population is gradually optimized, and finally the optimal or suboptimal charging station site selection scheme is output to complete the intelligent energy station site selection planning after meeting the convergence criteria.

[0131] In one example, referring to Figure 5 , the solution algorithm steps of the intelligent energy station site selection optimization model can specifically include the following steps:

[0132] 1. Initialize the population

[0133] ICMIC is used as the final chaotic mapping initial population generation method, and the specific expression of the ICMIC mapping is:

[0134]

[0135] In the formula, α is the mapping coefficient, in order to further explore the influence of the mapping parameter, the lyapunov index (λ) is used to measure the mapping effect, and the calculation formula is:

[0136]

[0137] 2. Update the position of the dung beetle

[0138] (1) Random number <δ

[0139] The black widow algorithm is used to replace the rolling behavior algorithm, and the black widow algorithm converts the motion model of the black widow spider in the spider web into linear and spiral forms, and the position update formula is as follows:

[0140]

[0141] where x * is the global optimal position, m is a random floating point number between 0.4 and 0.9, β is a random floating point number between -1 and 1, is other individuals in the population;

[0142] The pheromone defined by introducing the black widow algorithm is:

[0143]

[0144] where fitness max is the global optimal individual fitness value, fitness min is the global worst individual fitness value, and fitness(i) is the current individual fitness value;

[0145] ① pheromone≤0.1

[0146] When the pheromone is too small, the individual will be replaced by a new individual, and the position update formula is:

[0147]

[0148] where and are two different individuals in the population;

[0149] ② pheromone>0.1

[0150] Directly proceed to the next step;

[0151] (2) Random number≥δ

[0152] The mathematical model formula of using the rolling ball dance behavior of Onthophagus cookei is:

[0153] x i (t+1)=x i (t)+tan(θ)|x i (t)-x i (t-1)

[0154] where θ∈[0,π], when θ=0, π / 2, π, the position of the Onthophagus cookei will not be updated;

[0155] (3) Update the positions of the egg-laying Onthophagus cookei, small Onthophagus cookei, and the thief Onthophagus cookei

[0156] ① Egg-laying Onthophagus cookei

[0157] The best position is selected by imitating the egg-laying Onthophagus cookei, and a boundary selection strategy is adopted to simulate the egg-laying area of the female Onthophagus cookei, which is described as:

[0158] Lb *= max(X * *(1-R), Lb),

[0159] Ub * = min(X * *(1-R), Ub)

[0160] where X * Lb * , Ub * are the upper and lower bounds of the egg-laying region, and Lb, Ub are the upper and lower bounds of the optimization algorithm; t is the current round, and T max is the maximum iteration round.

[0161] After determining the egg-laying region, the dung beetle will lay an egg in the selected region. It should be noted that according to the above formula, the boundary range of the egg-laying region is dynamically changing and gradually shrinking. The specific position of the dung beetle's egg-laying is mathematically modeled as:

[0162] B i (t+1) = X * + b1*(B i (t) - Lb * ) + b2*(B i (t) - Ub * )

[0163] where B i (t) is the position information of the ith dung beetle at the tth iteration, and b1, b2 are independent random vectors of the same dimension. The egg-laying position is strictly limited within the egg-laying region.

[0164] ② Small dung beetle

[0165] The t-distribution variation disturbance factor with the iteration degree of freedom parameter is used to disturb the foraging behavior of the small dung beetle. The probability density function of the t-distribution is:

[0166]

[0167] where, is the second Euler integral, and the decision parameter is the degree of freedom parameter m. When m = 1, the t-distribution is Cauchy distribution. When m → ∞, the t-distribution is Gaussian distribution. The specific position update method is as follows:

[0168]

[0169] where t represents a random number under the t-distribution;

[0170] ③ Stealing cockroach

[0171] The behavior pattern of the stealing cockroach is simulated, and the mathematical model is expressed as:

[0172] x i (t+1) = X b +S*g*(|x i (t)-X * |+|x i (t)-X b |)

[0173] where g is a D-dimensional random vector obeying normal distribution, and S is a constant;

[0174] f(x i )→fitness value

[0175] The fitness of each individual is evaluated according to the objective function f;

[0176] 3. Black widow pheromone update

[0177] (1) Movement

[0178] x i (t+1) = x i (t) + a · (x * (t) - x i (t)) + β · Δx i (t)

[0179] where x * (t) is the current best individual position, a and β are random coefficients, and Δx i (t) represents the position change;

[0180] (2) Pheromone update

[0181]

[0182] where τ(x i ) is the pheromone concentration of the i-th individual, and δ is the pheromone evaporation rate;

[0183] 4. Determination of the position boundary of the dung beetle

[0184] The main purpose of the boundary determination for each dung beetle is to ensure that the position of the dung beetle in the search space does not exceed the predefined upper and lower boundaries. The purpose of the boundary determination is to maintain the feasibility of the algorithm and ensure that the solution after each iteration is valid. For the position x i (t) of the i-th dung beetle at the t-th iteration, the boundary determination formula can be expressed as:

[0185]

[0186] where x i (t+1) is the position of the i-th dung beetle after the (t+1)-th iteration, and Lbi Ub is the upper bound of the position of the ith dung beetle in the ith dimension; i Ub is the lower bound of the position of the ith dung beetle in the ith dimension;

[0187] 5. Calculate the fitness of all dung beetles and the optimal solution

[0188]

[0189] where N is the number of dung beetles, and the position of each dung beetle is represented as x i The globally optimal position is represented as x * f(x i ) is the fitness of the ith dung beetle, and f(x * ) is the globally optimal fitness;

[0190] 6. Repeat iteration

[0191] Determine whether t is less than the maximum number of iterations. If so, return to the random number determination. Otherwise, the iteration ends.

[0192] In some embodiments, the smart energy station site selection optimization model includes an objective function and an objective constraint condition corresponding to the objective function; the objective constraint condition includes an energy demand constraint, a technical parameter constraint, an environmental impact constraint, a power grid access and stability constraint, a land and geographical location constraint, an investment return rate constraint, and a user satisfaction constraint.

[0193] In one example, the objective function satisfies the expression:

[0194] min Z = C opex +C grid +C users +C env

[0195] where Z is the total cost to be minimized, C opex is the charging aggregator cost, C grid is the power grid stability cost, C users is the user cost, and C env is the environmental cost;

[0196] The energy demand constraint satisfies the expression:

[0197]

[0198] where E i is the supply of the ith energy module and includes photovoltaic power generation and energy storage release; D i is the demand of the ith energy module, E total is the total predicted energy demand;

[0199] The technical parameter constraint satisfies the expression:

[0200] P min ≤P i ≤P max

[0201] P i is the output power of the i-th energy module, P min and P max are the minimum and maximum output power of the module, respectively;

[0202] The environmental impact constraint satisfies the expression:

[0203] E enb,i ≤T env

[0204] E env,i is the environmental impact of the i-th energy module, T env is the maximum allowed value of the environmental impact;

[0205] The grid access and stability constraint satisfies the expression:

[0206] S grid,i ≤C grid

[0207] S grid,i is the contribution of the i-th energy module to the grid stability, C grid is the maximum allowed value of the grid stability;

[0208] The land and geographical location constraint satisfies the expression:

[0209] A i ≥A req,i

[0210] A i is the available land area for the i-th energy station, A req,i is the minimum land area required for the energy station;

[0211] The return on investment constraint satisfies the expression:

[0212] ROI≥T ROI

[0213] ROI is the return on investment, T ROI is the target return on investment;

[0214] The user satisfaction constraint satisfies the expression:

[0215] S user,i ≥T user

[0216] S user,iis the user satisfaction of the i-th energy station, T user is the minimum acceptable value of user satisfaction.

[0217] In some embodiments, referring to Figure 4 The smart energy station site optimization method further comprises constructing a smart energy station system, the smart energy station system comprising an energy supply module, a smart energy station optimization scheduling module, and a new energy truck support module; the smart energy station optimization scheduling module comprises the following constraint conditions: supply-demand balance constraint, energy flow stability constraint, capacity limitation constraint, device state constraint, device maintenance constraint, and cost optimization constraint; wherein the supply-demand balance constraint is used to ensure that at any given time, the energy supply amount is equal to the demand amount, while considering the charging and discharging states of the energy storage system.

[0218] In one example, the supply-demand balance constraint satisfies the expression:

[0219]

[0220] wherein P i (t) is the output power of supply source i at time t, P stocha (t) and P stodis (t) are the charging and discharging power of the energy storage system at time t, P j (t) is the power demand of load j at time t;

[0221] The energy flow stability constraint is used to ensure that the energy flow is within a predetermined safe range, avoiding drastic fluctuations; the energy flow stability constraint satisfies the expression:

[0222]

[0223] wherein P min and P max are the minimum and maximum output power of the supply source or load, sto_sys represents the energy storage system number library, and load represents the load system number library;

[0224] The capacity limitation constraint is used to ensure that the operation of all devices and energy storage systems does not exceed their capacity limitations; the capacity limitation constraint satisfies the expression:

[0225]

[0226] wherein E j (t) is the energy storage level of energy storage system j at time t, E min,j and E max,j are the minimum and maximum energy storage capacity of energy storage system j;

[0227] The device state constraint is used to consider the device operating state, ensuring that all devices are in operation or standby state; the device state constraint satisfies the expression:

[0228]

[0229] S i (t) is the state of device i at time t, RUN represents the running state, SBY represents the standby state, MNT represents the maintenance state, FLT represents the fault state, and EQU represents the device number library;

[0230] The device maintenance constraint is used to consider the periodic maintenance of the device to avoid failure and prolong the service life; the device maintenance constraint satisfies the expression:

[0231]

[0232] T mnt,i is the recommended time interval between two maintenances of device i, T nmnt,i is the time of the next maintenance of device i, and T max,i is the maximum allowed time interval between two maintenances of device i.

[0233] The cost optimization constraint considers optimizing the scheduling scheme to minimize the overall operating cost, and the overall operating cost includes the energy purchase cost, the device operation and maintenance cost; the cost optimization constraint satisfies the expression:

[0234]

[0235] C RUN, i (P i (t)) is the operation cost of device i at time t, C MNT, i (S i (t)) is the maintenance cost of device i, C BUY (P BUY i(t)) is the cost of purchasing energy from the outside for device i.

[0236] In some embodiments, the present application provides a smart energy station site selection optimization device 500, as shown in Figure 6 The device 500 can include the following modules:

[0237] The preprocessing module 510 is configured to obtain first data information of the new energy truck in a historical period, and pre-process the first data information to obtain second data information;

[0238] The analysis and determination module 520 is configured to analyze the operation mode of the new energy truck based on the second data information, and determine the main operation area and the potential growth area of the new energy truck; wherein the operation mode includes the driving route, the cargo type and the transportation frequency;

[0239] The spatio-temporal graph construction module 530 is configured to construct a spatio-temporal graph to represent the charging behavior of the truck by using a spatio-temporal mask autoencoder in the spatio-temporal generative pre-training model; wherein the spatio-temporal graph takes the truck and the charging station as nodes and takes the spatio-temporal relationship between the truck and the charging station as edges.

[0240] The pre-training module 540 is configured to pre-train the spatio-temporal graph by using the spatio-temporal generative pre-training model, learn the internal spatio-temporal pattern of the charging behavior of the truck by using an adaptive mask strategy, and obtain a spatio-temporal representation.

[0241] The learning and prediction module 550 is configured to take the spatio-temporal representation as input information, train a spatio-temporal prediction dynamic diffusion model to learn the charging demand change from a current state to a future state, and perform charging demand prediction.

[0242] The model construction module 560 is configured to construct a smart energy station site selection optimization model to perform optimization site selection of the smart energy station based on the charging demand prediction of the spatio-temporal prediction dynamic diffusion model, and take the minimum comprehensive cost as an objective function; wherein the smart energy station site selection optimization model is a multi-objective optimization model integrating hydrogenation, charging, photovoltaic, and energy storage.

[0243] According to embodiments of the present application, any of the modules of the pre-processing module 510, the analysis and determination module 520, the spatio-temporal graph construction module 530, the pre-training module 540, the learning and prediction module 550, and the model construction module 560 can be combined in one module, or any of the modules can be split into multiple modules. Alternatively, at least part of the function of one or more of the modules can be combined with at least part of the function of the other modules, and implemented in one module.

[0244] Figure 6 Each module in the device has the function of implementing each step in the foregoing smart energy station site selection optimization method, and can achieve the corresponding technical effects. For brevity, the foregoing will not be described again.

[0245] In some embodiments, the present application provides an electronic device, a structural schematic diagram of which is shown in Figure 7

[0246] The electronic device can include a processor 610 and a memory 620 storing computer program instructions.

[0247] Specifically, the processor 610 described above can include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or can be configured as one or more integrated circuits that implement embodiments of the present application.

[0248] ​The memory 620 can include mass storage for data or instructions. As an example and not by way of limitation, the memory 620 can include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disc (e.g., a compact disc (CD) or a digital versatile disc (DVD)), a solid-state drive (SSD), a USB drive, or a combination of two or more of these. Where appropriate, the memory 620 can include removable or non-removable (or fixed) media. Where appropriate, the memory 620 can be internal or external to the integrated gateway disaster recovery appliance. In particular embodiments, the memory 620 is non-volatile, solid-state memory.

[0249] The memory 620 can include read-only memory (ROM), random-access memory (RAM), a disk storage medium, an optical storage medium, flash memory, electrical, optical, or other physical / tangible memory storage device. Thus, in general, the memory 620 includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software that, when executed (by one or more processors), is capable to perform the operations described above with respect to any of the embodiments of the method of intelligent energy station siting optimization.

[0250] The processor 610 implements the method of intelligent energy station siting optimization described above in any of the embodiments by, e.g., accessing and executing computer program instructions stored in the memory 620.

[0251] In one example, the electronic device can also include a communication interface 630 and a bus 600. As shown, the processor 610, the memory 620, and the communication interface 630 are connected by the bus 600 and complete communication among each other. Figure 7

[0252] The communication interface 630 is mainly used to realize the communication between the modules, devices, units and / or equipment in the embodiments of the present application.

[0253] ​Bus 600 includes a hardware, software, or both that couples components of the online data traffic metering device to each other. As an example but not a limitation, the bus can include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand (IB) interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or another suitable bus or a combination of two or more of these. Where suitable, bus 600 can include one or more buses. Although particular buses have been described and shown in the embodiments of the present application, the present application contemplates any suitable bus or interconnect.

[0254] In addition, in combination with the intelligent energy station site selection optimization method in the above embodiments, the embodiments of the present application can provide a computer storage medium for implementation. The computer storage medium has computer program instructions stored thereon; the computer program instructions are executed by a processor to implement any of the intelligent energy station site selection optimization methods in the above embodiments.

[0255] It needs to be clear that the present application is not limited to the specific configurations and processes described above and shown in the drawings. For the sake of brevity, detailed descriptions of well-known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between steps, after understanding the spirit of the present application.

[0256] The functional blocks shown in the above structural block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, etc. When implemented in software, the elements of the present application are program or code segments used to perform the required tasks. The program or code segments can be stored in a machine-readable medium or transmitted through a data signal carried in a carrier wave in a transmission medium or communication link. The "machine-readable medium" can include any medium capable of storing or transmitting information. Examples of the machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segments can be downloaded via a computer network such as the Internet, an intranet, etc.

[0257] It is also important to note that the example embodiments described herein can be based on a series of steps or stages to describe some methods or systems. However, the present application is not limited to the order of steps described in the embodiments, that is, the steps can be performed in the order mentioned in the embodiments, or in an order different from the embodiments, or several steps can be performed simultaneously.

[0258] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0259] In summary, compared with the prior art, the present application has the following beneficial effects:

[0260] 1、The present application can determine the optimal energy station location to meet the energy charging needs of new energy trucks for logistics enterprises through precise data analysis and optimization algorithms. This method not only considers the efficiency and cost of energy supply, but also takes into account environmental protection and grid stability. Compared with the prior art, the present application can more accurately predict energy charging needs, thereby reducing over-construction or insufficient construction of energy stations, avoiding resource waste, improving the overall efficiency of energy supply, and reducing construction and operation costs.

[0261] 2、The present application pays more attention to environmental protection in site selection decision-making, optimizes energy structure and improves energy utilization efficiency by introducing photovoltaic power generation and energy storage equipment. This comprehensive consideration of site selection optimization of charging and hydrogenation and other energy supply modes helps to reduce the impact on the environment and promote the development of the logistics industry towards a greener and more intelligent direction. Compared with the background technology, the present application realizes the overall optimization of the site selection scheme through a multi-objective optimization model, not only improves the efficiency of new energy truck energy charging facility layout, but also promotes the green and sustainable development of the logistics industry.

[0262] 3、The application considers the power grid access conditions and stability when constructing the intelligent energy station site optimization model, optimizes the layout of the energy supply station, helps to reduce the impact on the power grid, and improves the stability of the power grid. In addition, by predicting the energy demand of new energy trucks and combining real-time data, the application can realize dynamic management and optimized distribution of energy, and improve energy utilization efficiency. Compared with the prior art, the application completes the optimization of the intelligent energy station by fusing the black widow thought of the dung beetle optimization algorithm, and improves the contribution to the stability of the power grid.

[0263] The above examples are only used to illustrate the technical solutions of the present application, but not to limit it; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that the technical solutions recorded in the foregoing examples can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for optimizing the site selection of a smart energy station, characterized in that: include: Acquire first data information of new energy trucks in a historical period, and preprocess the first data information to obtain second data information; Analyzing the operating patterns of new energy trucks based on the second data information, and determining the primary operating areas and potential growth areas for new energy trucks; wherein the operating patterns include driving routes, cargo types, and transportation frequencies; A spatiotemporal graph is constructed using a spatiotemporal masked autoencoder from a spatiotemporal generative pre-trained model to represent truck charging behavior. The spatiotemporal graph uses trucks and charging stations as nodes and the spatiotemporal relationships between trucks and charging stations as edges. Pre-training the spatiotemporal graph using the spatiotemporal generative pre-training model, learning the intrinsic spatiotemporal pattern of the truck charging behavior through an adaptive masking strategy, and obtaining a spatiotemporal representation; Taking the spatiotemporal representation as input information, training a spatiotemporal prediction dynamic diffusion model to learn the change of charging demand from the current state to the future state to perform charging demand prediction; Based on the charging demand prediction of the spatiotemporal prediction dynamic diffusion model, and with the lowest comprehensive cost as the objective function, a smart energy station site selection optimization model is constructed to optimize the site selection of smart energy stations; wherein the smart energy station site selection optimization model is a multi-objective optimization model that integrates hydrogen refueling, charging, photovoltaics, and energy storage; The spatiotemporal prediction dynamic diffusion model for charging demand prediction includes problem definition, diffusion process, and generation process. The spatiotemporal generative pre-training model is also used for customized temporal pattern coding, hierarchical spatial pattern coding, and downstream tasks. The customized temporal pattern coding includes: Normalize the spatiotemporal data and construct an embedding matrix, using the embedding layer to convert discrete features into continuous embedding vectors; Initializing the embedding vector by random initialization or using a pre-trained model; Perform periodic encoding on the temporal features and position encoding on the spatial features, and fuse the periodic encoding results and position encoding results to obtain spatiotemporal embedding information; Based on the spatiotemporal embedding information, the parameters of the embedding layer are optimized during model training and fine-tuned according to task requirements to obtain an effective representation that can capture the intrinsic characteristics and structure of the spatiotemporal data; The hierarchical spatial pattern coding is performed based on a hypergraph capsule clustering network and includes the following steps: The hypergraph structure is constructed by initializing region embedding and calculating the transfer information from region to cluster center; The dynamic routing mechanism of capsule network is used to iteratively update hyperedge representation and regional hyperedge connection to enhance clustering ability; Modeling category embeddings through advanced hypergraph neural networks for cross-category relationship learning; Gradually increase the prediction difficulty based on the category-aware mask strategy to guide the model to learn robust spatiotemporal representations during the pre-training phase, achieving spatial hierarchical pattern encoding from local to global. The temporal encoding vector and the spatial encoding vector are combined with the embedding vector obtained by the hypergraph capsule clustering network to form a comprehensive spatiotemporal representation; The smart energy station site selection optimization model includes an objective function and objective constraints corresponding to the objective function; the objective constraints include energy demand constraints, technical parameter constraints, environmental impact constraints, grid access and stability constraints, land and geographical location constraints, investment return constraints, and user satisfaction constraints; The objective function satisfies the expression: Where Z is the total cost to be minimized, is the charging aggregator cost, is the grid stabilization cost, is the user cost, It is the environmental cost; The energy demand constraint satisfies the expression: Where, It is The supply of each energy module includes photovoltaic power generation and energy storage release; It is The demand for energy modules, is the total forecast energy demand; The technical parameter constraints satisfy the expression: Where, It is The output power of each energy module is and are the minimum and maximum output power of the module respectively; The environmental impact constraint satisfies the expression: Where, It is The environmental impact of each energy module, It is the maximum permissible value of environmental impact; The grid access and stability constraints satisfy the expression: Where, It is The contribution of each energy module to grid stability, is the maximum permissible value for grid stability; The land and geographic location constraints satisfy the expression: Where, It is The land area available for each energy station, is the minimum land area required for the energy station; The ROI constraint satisfies the expression: Where, is the return on investment, is the target return on investment; The user satisfaction constraint satisfies the expression: Where, It is User satisfaction of energy stations, is the minimum acceptable value of user satisfaction.

2. The smart energy station site selection optimization method according to claim 1, characterized in that: The preprocessing of the first data information to obtain the second data information includes: Cleaning the first data information, filling missing values, and identifying and removing abnormal data; Merge different data into a unified data set and data format as needed; Identify the time period, day of the week, and whether the timestamp is a holiday, and identify the spatial location of the logistics park; Perform sliding window processing on time series data, visualize geographic location information, and divide the dataset into training, validation, and test sets; Check whether the processed data set is balanced and whether there is any data leakage problem, and save the processed data in a format acceptable to model training to obtain second data information.

3. The smart energy station site selection optimization method according to claim 1, characterized in that: It also includes building a smart energy station system, which includes an energy supply module, a smart energy station optimization and scheduling module, and a new energy truck support module; The smart energy station optimization and scheduling module includes the following constraints: supply and demand balance constraint, energy flow stability constraint, capacity limit constraint, equipment status constraint, equipment maintenance constraint, and cost optimization constraint. The supply and demand balance constraint is used to ensure that the energy supply is equal to the demand at any given time, while taking into account the charge and discharge status of the energy storage system. The supply and demand balance constraint satisfies the expression: Where, Is a source of supply In time The output power, and The energy storage system is The charging and discharging power, is the load In time Power requirements; The energy flow stability constraint is used to ensure that energy flow is within a predetermined safety range and avoid violent fluctuations; the energy flow stability constraint satisfies the expression: Where, and are the minimum and maximum output power of the supply source or load, respectively, Indicates the energy storage system number library, Indicates the load system number library; The capacity limit constraint is used to ensure that the operation of all devices and energy storage systems does not exceed their capacity limits; the capacity limit constraint satisfies the expression: Where, It is an energy storage system In time The energy storage level, and Energy storage systems Minimum and maximum energy storage capacity; The device status constraint is used to consider the device operating status and ensure that all devices are in operation or standby state; the device status constraint satisfies the expression: Where, It is a device In time Status, Indicates the running status. Indicates standby status. Indicates maintenance status. Indicates a fault condition. Indicates the equipment number library; The equipment maintenance constraint is used to consider regular equipment maintenance to avoid failures and extend service life; the equipment maintenance constraint satisfies the expression: Where, It is a device The recommended time interval between maintenance, It is a device The time of next maintenance, It is a device The maximum permissible time interval between two maintenances; The cost optimization constraint considers optimizing the scheduling scheme to minimize the overall operating cost, which includes energy purchase cost, equipment operation and maintenance cost; the cost optimization constraint satisfies the expression: Where, It is a device In time operating costs, It is a device maintenance costs, It is a device The cost of purchasing energy from outside sources.

4. A smart energy station site selection optimization device, based on the smart energy station site selection optimization method according to any one of claims 1 to 3, characterized in that: include: a preprocessing module, configured to obtain first data information of new energy trucks in a historical period, and preprocess the first data information to obtain second data information; an analysis and determination module, configured to analyze the operating mode of new energy trucks based on the second data information and determine the main operating areas and potential growth areas of new energy trucks; wherein the operating mode includes driving routes, cargo types, and transportation frequencies; A spatiotemporal graph construction module, configured to construct a spatiotemporal graph to represent truck charging behavior using a spatiotemporal masked autoencoder from a spatiotemporal generative pre-trained model; wherein the spatiotemporal graph includes trucks and charging stations as nodes and the spatiotemporal relationships between trucks and charging stations as edges; a pre-training module for pre-training the spatiotemporal graph using the spatiotemporal generative pre-training model, learning the intrinsic spatiotemporal pattern of the truck charging behavior through an adaptive masking strategy, and obtaining a spatiotemporal representation; a learning prediction module, configured to use the spatiotemporal representation as input information and train a spatiotemporal prediction dynamic diffusion model to learn the change in charging demand from a current state to a future state to perform charging demand prediction; A model building module is used to predict charging demand based on the spatiotemporal prediction dynamic diffusion model, with the lowest comprehensive cost as the objective function, to build a smart energy station site selection optimization model to optimize the site selection of smart energy stations; wherein, the smart energy station site selection optimization model is a multi-objective optimization model integrating hydrogen refueling, charging, photovoltaics and energy storage.

5. An electronic device, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the method for optimizing the site selection of a smart energy station as described in any one of claims 1 to 3 is implemented.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the smart energy station site selection optimization method according to any one of claims 1 to 3 is implemented.

Images