A traffic flow and charging station load prediction method based on deep learning

Abstract

The present invention provides a deep learning-based traffic flow and charging station load forecasting method, which aims to improve the accuracy of traffic flow forecasting and accurately predict the load of electric vehicle charging stations. The method includes the following steps: First, a spatial-temporal graph convolutional network model based on the attention mechanism is used to predict future traffic flow and traffic speed. Secondly, based on the probability distribution of the vehicle's daily travel distance, a hybrid model and an expectation-maximization algorithm are used to calculate the charging demand of electric vehicles, and the energy consumption of electric vehicles is predicted using a polynomial regression model. Finally, based on the driving behavior of electric vehicles, an electric vehicle queuing model is constructed. The model comprehensively considers behaviors such as charging station capacity limitations, long waiting times, and impatience to leave, and calculates the load forecast of the charging station using a random Markov chain analysis method. This method can effectively capture the spatiotemporal characteristics of traffic flow and electric vehicle charging demand, and improve the accuracy of charging station load forecasting.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic flow prediction and electric vehicle charging load prediction, and in particular to a traffic flow and electric vehicle charging load prediction method based on deep learning. Background Art

[0002] As global climate change and environmental pollution become increasingly serious, electric vehicles (EVs) are gaining increasing attention due to their environmental and energy-saving advantages. Compared to traditional fuel vehicles, EVs reduce reliance on fossil fuels and lower greenhouse gas emissions. However, the widespread adoption of EVs also presents new challenges, one of which is how to effectively predict traffic flow and charging load to optimize traffic management and the layout and operation of charging stations.

[0003] Traditional traffic flow forecasting methods typically rely on historical data and statistical models, such as time series analysis and regression analysis. While these methods perform well in certain scenarios, they often struggle to capture the complex spatiotemporal dependencies in traffic flow, resulting in low prediction accuracy, especially in the face of emergencies and changes in traffic patterns.

[0004] Similarly, traditional methods for predicting EV charging load rely primarily on simple demand forecasting models. These models typically assume that charging demand is uniformly distributed and ignore the complexity and randomness of EV charging behavior. For example, EV charging behavior is affected not only by the vehicle's battery status and remaining charge, but also by multiple factors such as traffic flow, driver behavior, and charging station service capacity.

[0005] In recent years, with the development of artificial intelligence (AI), especially deep learning's advantages in handling complex nonlinear problems, more and more research has attempted to introduce deep learning into traffic flow and charging load prediction. For example, convolutional neural networks (CNNs) and recurrent neural networks (RNNs) excel in processing image and sequence data. However, these models alone still struggle to fully capture the spatiotemporal correlations in traffic data.

[0006] Attention-based deep learning models, such as those combining graph convolutional networks (GCNs) with attention mechanisms, have shown great potential in capturing global and local dependencies in data. These models can dynamically adjust the relevance weights between nodes, enabling them to more accurately capture the spatiotemporal dynamics of traffic flow and charging behavior. Summary of the Invention

[0007] The present invention aims to solve the problems existing in the prior art and proposes a traffic flow and charging station load prediction method based on deep learning. By combining the spatial-temporal graph convolutional network model with the attention mechanism and the hybrid model, the traffic flow and electric vehicle charging load are accurately predicted, providing support for intelligent traffic management and optimization of charging infrastructure.

[0008] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0009] A spatial-temporal graph convolutional network model based on an attention mechanism is used to predict future traffic flow and speed. The model defines the traffic network as an undirected graph and uses the feature values ​​of each node in the traffic network in historical time slices to predict traffic flow and speed for multiple future time slices.

[0010] Based on the actual data, a hybrid model is used to fit the distribution of daily driving distance of electric vehicles and the distribution of daily driving of electric vehicles. The parameters of the hybrid model corresponding to the distribution of daily driving distance of electric vehicles and the distribution of daily driving of electric vehicles are optimized respectively through the expectation maximization algorithm.

[0011] According to the actual energy consumption data, a polynomial regression model is used to fit the mapping relationship between electric vehicle speed and energy consumption;

[0012] Using the predicted future traffic volume and speed, the distribution of daily EV distance traveled, the distribution of daily EV travel, and the mapping between EV speed and energy consumption, combined with EV battery capacity and EV penetration data, the arrival rate of EVs at charging stations is estimated.

[0013] An electric vehicle charging queue model is established that takes into account service capacity limitations and driver charging behavior. The estimated arrival rate of electric vehicles at charging stations is corrected to obtain the corrected average arrival rate and average departure rate.

[0014] Combining the average arrival rate and the average departure rate, a random Markov chain is used to calculate the probability distribution of the number of electric vehicles in the charging station;

[0015] The overall load of the charging station is calculated by combining the probability distribution of the number of electric vehicles in the charging station and the power of the charging piles.

[0016] Preferably, the attention-based spatial-temporal graph convolutional network model includes three independent components, which are used to model the temporal correlation of the recent period, daily cycle and weekly cycle respectively. Each component includes several spatiotemporal blocks and a fully connected layer, and each spatiotemporal block consists of a spatiotemporal attention module and a spatiotemporal convolution module.

[0017] Preferably, the spatiotemporal attention module is used to calculate the spatial correlation between different nodes in the traffic network, can calculate the relative importance of each node to other nodes, extract the node features of the input data through the fully connected layer, and calculate the spatial attention weights between nodes based on the node feature vectors.

[0018] Preferably, the spatiotemporal convolution module is used to perform graph convolution operations on the node features output by the spatiotemporal attention module, capturing the spatial relationships in the transportation network through the relative importance weights between nodes.

[0019] Preferably, the estimating the arrival rate of electric vehicles at charging stations includes: estimating the distance traveled in a day based on the distribution of electric vehicles in daily driving by using the driving distance of the electric vehicles at a certain moment; estimating the daily driving distance of the electric vehicles to reach the charging station at this moment based on the relationship between the charging status of the electric vehicles, the driving energy consumption of the electric vehicles, the battery capacity of the electric vehicles and the driving distance; then estimating the probability of the electric vehicles choosing to charge when passing the charging station at this moment based on the distribution of the daily driving distance of the electric vehicles; and finally calculating the arrival rate of electric vehicles at charging stations in combination with the predicted results of traffic flow and the penetration rate of electric vehicles.

[0020] Preferably, the electric vehicle charging queue model comprehensively considers three behaviors of electric vehicles: leaving due to capacity limitations of charging stations, long waiting queues, and impatience, and corrects the arrival rate of electric vehicles at charging stations to obtain the average arrival rate and average leaving rate of electric vehicles at charging stations.

[0021] Preferably, the use of a random Markov chain to calculate the probability distribution of the number of electric vehicles in the charging station includes analyzing the state transitions in the charging station according to random process theory, the states including arrival and departure, establishing a balance equation, and calculating the probability distribution of the number of electric vehicles in the charging station based on the average arrival rate and average departure rate of electric vehicles at the charging station.

[0022] The present invention proposes a traffic flow and charging station load prediction method based on deep learning, which has the following features:

[0023] Beneficial effects:

[0024] A spatial-temporal graph convolutional network model based on the attention mechanism is used to more accurately capture the spatiotemporal dependencies of traffic flow and traffic speed, thereby improving prediction accuracy.

[0025] By utilizing the spatial and temporal attention mechanism, the correlation weights of nodes and time slices in the traffic network are dynamically adjusted to enhance the robustness and adaptability of the spatial-temporal graph convolutional network model based on the attention mechanism.

[0026] The spatial-temporal graph convolutional network model based on the attention mechanism contains three components: recent periodicity, daily periodicity, and weekly periodicity, which comprehensively captures the changes in traffic flow and traffic speed at different time scales.

[0027] Establish an electric vehicle charging queuing model that takes into account service capacity limitations and driver charging behavior to more accurately simulate the arrival and departure behavior of electric vehicles at charging stations and improve the accuracy of charging load forecasting.

[0028] The mapping relationship between electric vehicle speed and energy consumption is established through a polynomial regression model. Combined with the traffic flow and traffic speed prediction results, the energy consumption of electric vehicles is accurately estimated, providing reliable data for charging load prediction.

[0029] Combining deep learning with probabilistic models improves the accuracy and stability of traffic flow and charging load predictions, achieving an effective integration of the two, and has high practical value and promotion prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 Flowchart of the traffic flow and charging station load prediction method based on deep learning and probabilistic modeling.

[0031] Figure 2 It is a spatial-temporal graph convolutional network model framework based on the attention mechanism. DETAILED DESCRIPTION

[0032] The present invention will be described in further detail below with reference to the accompanying drawings.

[0033] like Figure 1 As shown, the present invention provides a method for predicting traffic flow and charging station load based on deep learning, comprising the following steps:

[0034] Step S1: Use a spatial-temporal graph convolutional network model based on an attention mechanism to predict future traffic flow and speed. Define the traffic network as an undirected graph G = (V, E, A), where V is the set of nodes, |V| = N nodes; E is the set of edges, representing the connectivity between nodes; Represents the adjacency matrix of the undirected graph G. Each node on the traffic network undirected graph G detects F measurement values ​​with the same sampling frequency, that is, each node generates a feature vector of length F in each time slice, which contains traffic flow, traffic occupancy, traffic speed, etc. Assume that the f-th and s-th time series recorded by each node on the traffic network undirected graph G are traffic flow series and traffic speed series, respectively, f,s∈(1,...,F). Use represents the cth eigenvalue of node i at time t, Represents all eigenvalues ​​of node i at time t. represents all eigenvalues ​​of all nodes at time t. represents all the eigenvalues ​​of all nodes in the past τ time slices. In addition, let represents the traffic flow of node i at future time t, let represents the traffic speed of node i at the future time t. The following describes how to use the historical measurement values ​​in the past τ time slices to predict the traffic speed of all nodes in the traffic network after T p Future traffic flow in time slices and traffic speed in represents the future traffic flow of node i starting from τ+1, represents the future traffic speed of node i starting from τ+1.

[0035] The spatial-temporal graph convolutional network model framework based on the attention mechanism is as follows: Figure 2 As shown, it consists of three independent components with the same structure, which are used to model the recent, daily periodicity and weekly periodicity dependencies of historical data respectively.

[0036] Assume that the sampling frequency is q times per day, the current time is t0, and the size of the prediction window is T p . The length of the intercept along the time axis is T h 、T d and T w The three time series segments of , are used as input for the recent, daily and weekly components, respectively, where T h 、T d and T w All T p An integer multiple of .

[0037] Recent inputs are is the historical time series segment directly adjacent to the forecast period. The input for the daily period is Consists of segments from the past few days for the same period as the forecast period. The input for the weekly period is It consists of segments with the same weekly attributes and time intervals from the past few weeks. These three components share the same network structure, each consisting of several spatiotemporal blocks and a fully connected layer. Each spatiotemporal block contains a spatiotemporal attention module and a spatiotemporal convolution module. The following describes the spatial attention module, temporal attention module, and graph convolution module in detail.

[0038] To effectively model the spatial correlation between different nodes, a spatial attention module is designed. This module can calculate the relative importance of each node in the traffic network compared to all other nodes. Specifically, the calculation process of the spatial attention module is as follows:

[0039] First, the input sequence X is passed through the first fully connected layer Projected into a d-dimensional space to extract higher-level features. Then, the spatial attention weights between nodes are calculated

[0040]

[0041] Among them, the intermediate variables are calculated by the input feature sequence and the fully connected layer, H S =XW S . H S,j Indicates H S Finally, A S Perform weighted summation with the input sequence X to obtain the weighted node features:

[0042] Z S =A S X

[0043] In order to capture the temporal dependency in traffic data, a temporal attention module is introduced. The calculation process of the temporal attention module is as follows:

[0044] First, the input sequence X is passed through the second fully connected layer Projected into a d-dimensional space to extract higher-level features. Then, calculate the temporal attention weights between different time slices

[0045]

[0046] Among them, H T =XW T , H T,j Indicates H T Finally, A T Perform weighted summation with the input sequence X to obtain the weighted time slice features:

[0047] Z T =A T X

[0048] In order to further extract the spatial relationship between nodes, a graph convolution module is introduced after the spatial attention module. Specifically, the calculation process of the graph convolution module is as follows:

[0049] First, the weighted node feature Z S Through a graph convolution layer Projected into a d-dimensional space. Then, perform graph convolution on the node features:

[0050] Z G =A S Z S WG

[0051] Among them, A S is the relative importance weight between nodes calculated in the spatial attention module. Through graph convolution operations, the spatial relationship between nodes in the transportation network can be better captured.

[0052] After processing multiple spatiotemporal blocks, the final feature representation is passed through the third fully connected layer Project it into a scalar space to get the traffic flow prediction value of each node in the future time slice:

[0053] Y=Z G W F

[0054] The mean square error loss function is used to train the spatial-temporal graph convolutional network model based on the attention mechanism. After training, the traffic flow and traffic speed are predicted by inputting the corresponding recent, daily and weekly cycle inputs.

[0055] Step S2: Calculate the probability distribution of the number of electric vehicles in the charging station.

[0056] To obtain the probability distribution of the actual daily distance traveled by electric vehicles, a method based on a mixture model is used to fit the distribution of the daily distance traveled by electric vehicles based on the actual data. The mixture model uses a combination of selected probability density functions to model the random variable:

[0057]

[0058] Where U is the set of random variables, Θ is the probability density parameter, and π m is the weight, M is the number of probability density function types selected, p m (u i ∣θ m ) is the chosen probability density function.

[0059] The expectation maximization algorithm is used to obtain the parameters of the hybrid model through two steps of iteration to maximize the expectation of likelihood:

[0060]

[0061] Where N is the number of data samples, V is the set of auxiliary variables, and v m,i is an indicator variable (often called a latent variable) that represents the i-th data point u i The probability of coming from the mth distribution.

[0062] Before applying the expectation-maximization algorithm, the parameters and auxiliary variable set V are initialized using the K-means clustering method. The number of probability density functions M is another key indicator that can be obtained using the Akaike Information Criterion (AIC) and the Bayesian Information Criterion (BIC), which are expressed as follows:

[0063] AIC=2M-2lnargmax Θ L(Θ|U)

[0064] BIC=Mln(N)-2lnargmax Θ L(Θ|U)

[0065] The expectation-maximization algorithm is performed in an iterative manner, selecting the best M by increasing M one by one until BIC(M)-BIC(M+1) and AIC(M)-AIC(M+1) are less than the preset termination criteria.

[0066] In the qth iteration, the first step is to calculate the current estimate Θ (q) The expected value of the lower likelihood function is:

[0067] Q(Θ|Θ (q) )=E[lnL(Θ|U,V)|(V,Θ (q) )]

[0068] The second step is to determine the parameters to maximize the expected value in this iteration:

[0069] Θ (q+1) =argmax Θ Q(Θ|Θ (q) )

[0070] The two-step algorithm is executed in an iterative manner until a preset stopping criterion is reached, and the parameters are optimally estimated using the proposed hybrid model to obtain the probability distribution of the daily travel distance of EVs.

[0071] The same method can also be used to obtain the daily driving distribution of electric vehicles, that is, the probability of whether the electric vehicle is driving at the current moment.

[0072] The above steps have completed the acquisition of the probability distribution of the daily distance traveled by electric vehicles and the distribution of vehicles in daily driving. The following is to estimate the arrival rate of electric vehicles at charging stations.

[0073] Whether the electric vehicle driver is willing to use the charging station along the driving route determines the arrival rate and is highly correlated with the state of charge (SOC) of the electric vehicle, while the charging time μ is determined by the SOC and the charging power. ev It is a key data source for estimating the SOC of electric vehicles and has the following relationship:

[0074] SOC=1-p ev D ev / E ev

[0075] Among them, E ev represents the battery capacity of electric vehicles, p ev Indicates the driving energy consumption of electric vehicles.

[0076] Driving energy consumption of electric vehicles ev The relationship between electric vehicle speed and energy consumption is modeled using a polynomial regression model. The energy consumption data of electric vehicles at different speeds is collected through the electric vehicle onboard data recording system, specialized test experiments, or data provided by manufacturers. The collected energy consumption data is cleaned to remove outliers and noise; the data is smoothed to reduce data fluctuations; and the data is normalized to process the data on a uniform scale. The polynomial regression model is selected, assuming that the energy consumption p ev With speed v speed The relationship between can be expressed as:

[0077] p ev =a0+a1v speed +a2v speed 2 +...+a n v speed n

[0078] where (a0, a1, …, a n ) is a constant of the polynomial.

[0079] The polynomial regression model is trained using the training set data, and the model parameters are estimated using the least squares method. The model parameters are further adjusted by gradient descent to minimize the model fitting error. Finally, p is obtained. ev With speed v speed The relationship between the traffic speed and the vehicle speed can be used to predict the energy consumption of the electric vehicle.

[0080] Use the distance D traveled at time t ev,t Estimated daily driving distance

[0081]

[0082] In the energy consumption p ev Distance from the sun Then, the estimated daily distance of the electric vehicle to reach the charging station at time t can be calculated. Assume that EV drivers prefer to operate at SOC lower than the standard SOC min When charging, and their average SOC is SOCm (0≤SOC min ≤SOC min ). Estimated daily driving distance of an electric vehicle arriving at the charging station at time t for:

[0083]

[0084] The probability P of an electric vehicle choosing to charge when it passes a charging station at time t t The daily distance traveled distribution p(X) can be used to estimate:

[0085]

[0086] Therefore, at time t, the arrival rate of electric vehicles at the charging station is:

[0087]

[0088] in is the penetration rate of electric vehicles in the total traffic flow; f t is the predicted result of traffic flow at time t.

[0089] The arrival rate obtained in this case is not entirely accurate. This paper proposes an electric vehicle charging queuing model that considers service capacity limitations and driver charging behavior. Sometimes electric vehicles leave a charging station without charging. This driver behavior can be caused by factors such as insufficient available chargers or capacity limitations at the charging station. Assuming the total number of available chargers at a charging station is C and the maximum capacity of the charging station is K, the root causes of electric vehicle departure behavior are categorized into three types: forced departure; refusal to join; and impatience to request leave.

[0090] 1. Forced departure: If the charging station has already accommodated K EVs, the other EVs will be forced to leave the charging station because there is no space in the queue.

[0091] 2. Refusing to join: When arriving at a charging station, an EV finds the queue too long and therefore refuses to join the queue, even if the total number of EVs in the charging station is less than K. According to categories 1 and 2, the probability of an EV choosing to queue is related to the number of EVs w in the charging station and is assumed to be

[0092]

[0093] where the exponential function indicates that the probability of selecting an EV in the queue decreases faster when the number of EVs in the charging station w increases, and σ is a parameter that defines the probability decrease rate.

[0094] 3. Impatient departure: Even if the waiting queue is not too long, EVs in the queue may still choose to leave the charging station when they are too impatient. The number of EVs remaining in the queue at each time interval is related to the number of EVs in the charging station w and is assumed to be

[0095]

[0096] Considering categories 1-3, the average arrival rate and average departure rate can be expressed as λ w =α w λ and μ w =μ-b λ .

[0097] Based on the described electric vehicle charging queue model, the charging station load can be obtained using random Markov chain analysis. According to the theory of random processes, the steady-state probability of the Markov chain in state e should satisfy the equilibrium equation:

[0098]

[0099] The formula indicates that the sum of all state probabilities should be 1. In addition, the probability of entering and exiting each state should be equal, q eg is the transition rate from state e to g, and S is the state space.

[0100] The state transitions in a charging station are of only two types: arrival and departure. Therefore, the charging station balance equation can be expressed as

[0101] (λ w +μ w )P w =λ w-1 P w-1 +μ w+1 P w+1

[0102] Combining the above electric vehicle departure behavior and charging station balance equation, the probability that a charging station has w electric vehicles is

[0103]

[0104] in,

[0105]

[0106] Among them, ρ=λ / μ, η=δ / μ.

[0107] Therefore, the number of charging electric vehicles in the charging station can be expressed as

[0108]

[0109] Step S3: Calculate the overall load of the charging station based on the probability distribution of the number of electric vehicles charging in the charging station and the charging power of each vehicle.

[0110] The total load P of the charging station FCS You can use N ch and charging pile power p EV To determine:

[0111] P FCS =N ch p EV .

Claims

1. A traffic flow and charging station load prediction method based on deep learning, characterized in that: The steps include: A spatial-temporal graph convolutional network model based on an attention mechanism is used to predict future traffic flow and speed. The model defines the traffic network as an undirected graph and uses the feature values ​​of each node in the traffic network in historical time slices to predict traffic flow and speed for multiple future time slices. Based on the actual data, a hybrid model is used to fit the distribution of daily driving distance of electric vehicles and the distribution of daily driving of electric vehicles. The parameters of the hybrid model corresponding to the distribution of daily driving distance of electric vehicles and the distribution of daily driving of electric vehicles are optimized respectively through the expectation maximization algorithm. According to the actual energy consumption data, a polynomial regression model is used to fit the mapping relationship between electric vehicle speed and energy consumption; Using the predicted future traffic volume and speed, the distribution of daily EV distance traveled, the distribution of daily EV travel, and the mapping between EV speed and energy consumption, combined with EV battery capacity and EV penetration data, the arrival rate of EVs at charging stations is estimated. An electric vehicle charging queue model is established that takes into account service capacity limitations and driver charging behavior. The estimated arrival rate of electric vehicles at charging stations is corrected to obtain the corrected average arrival rate and average departure rate. Combining the average arrival rate and the average departure rate, a random Markov chain is used to calculate the probability distribution of the number of electric vehicles in the charging station; The overall load of the charging station is calculated by combining the probability distribution of the number of electric vehicles in the charging station and the power of the charging piles.

2. The method for predicting traffic flow and charging station load based on deep learning according to claim 1, characterized in that: The attention-based spatial-temporal graph convolutional network model contains three independent components, which are used to model the temporal correlation of the recent, daily and weekly cycles respectively. Each component includes several spatiotemporal blocks and a fully connected layer, and each spatiotemporal block consists of a spatiotemporal attention module and a spatiotemporal convolution module.

3. The method for predicting traffic flow and charging station load based on deep learning according to claim 2, characterized in that: The spatiotemporal attention module is used to calculate the spatial correlation between different nodes in the traffic network. It can calculate the relative importance of each node to other nodes, extract the node features of the input data through the fully connected layer, and calculate the spatial attention weights between nodes based on the node feature vectors.

4. The method for predicting traffic flow and charging station load based on deep learning according to claim 2, characterized in that: The spatiotemporal convolution module is used to perform graph convolution operations on the node features output by the spatiotemporal attention module, capturing the spatial relationships in the transportation network through the relative importance weights between nodes.

5. The method for predicting traffic flow and charging station load based on deep learning according to claim 1, characterized in that: The method for estimating the arrival rate of electric vehicles at charging stations includes estimating the daily distance traveled by electric vehicles using the distance traveled by electric vehicles at a certain moment based on the distribution of daily driving of electric vehicles; estimating the daily distance traveled by electric vehicles to the charging station at that moment based on the relationship between the charging status of electric vehicles, driving energy consumption of electric vehicles, battery capacity of electric vehicles and driving distance; then estimating the probability that the electric vehicle will choose to charge when passing by the charging station at that moment based on the distribution of daily driving distance of electric vehicles; and finally calculating the arrival rate of electric vehicles at charging stations by combining the predicted results of traffic flow and the penetration rate of electric vehicles.

6. The method for predicting traffic flow and charging station load based on deep learning according to claim 1, characterized in that: The electric vehicle charging queue model comprehensively considers three behaviors of electric vehicles: capacity limitations of charging stations, long waiting queues, and leaving due to impatience. It corrects the arrival rate of electric vehicles at charging stations and obtains the average arrival rate and average leaving rate of electric vehicles at charging stations.

7. The method for predicting traffic flow and charging station load based on deep learning according to claim 1, characterized in that: The method of using a random Markov chain to calculate the probability distribution of the number of electric vehicles in a charging station includes analyzing state transitions in the charging station based on random process theory, where the states include arrival and departure, establishing a balance equation, and calculating the probability distribution of the number of electric vehicles in the charging station based on the average arrival rate and average departure rate of electric vehicles at the charging station.

Images