Two-stage energy consumption prediction path planning method based on deep learning

Abstract

The invention discloses a two-stage energy consumption prediction path planning method based on deep learning, which predicts and optimizes the energy consumption of an electric vehicle by using a deep learning technology, not only considers various factors such as road gradient, traffic condition and vehicle load, but also combines historical driving data and real-time traffic data, so that the energy consumption of the electric vehicle is predicted and optimized. Therefore, accurate prediction of energy consumption of a specific route is realized. Besides, through a two-stage solution, the initial stage mainly focuses on prediction before departure, and the subsequent stage focuses on prediction after departure in a journey, so that the energy consumption can be roughly predicted before the journey starts, and dynamic adjustment can be performed according to real-time traffic data in the journey, so that the energy consumption can be effectively reduced. Therefore, more accurate energy consumption prediction is realized.

Description

Technical Field

[0001] The present invention belongs to the field of logistics path planning, and specifically belongs to a method for two-stage energy consumption prediction path planning based on deep learning. Background Art

[0002] Logistics path planning is a key link in optimizing the cargo transportation process in many fields such as freight and express delivery. It is committed to reducing costs and significantly improving transportation efficiency through detailed planning. This field uses a series of classic algorithms - including Dijkstra and A* algorithms for finding the shortest path, as well as the Traveling Salesman Problem (TSP) and Vehicle Routing Problem (VRP) that consider more complex constraints - they solve problems through precise and heuristic methods, forming the basis of logistics path planning.

[0003] With the development of technology, modern methods such as heuristic algorithms and deep learning technology are widely used in real-time path planning in dynamic environments, making logistics path planning more flexible to adapt to complex and changing transportation needs. In addition, logistics path planning also focuses on multi-objective optimization, not only pursuing cost minimization, but also considering factors such as time efficiency and energy consumption, striving to find the best balance between multiple goals.

[0004] With the help of IoT technology, real-time traffic data, weather information, vehicle status and other data can be effectively utilized, and dynamic planning methods can be used to adjust the route planning in real time to cope with the immediate changes in the environment. Accompanying these technologies is the support of various software and platforms, which integrate the above algorithms and methods and provide user-friendly interfaces to help enterprises and individuals manage logistics route planning problems efficiently and conveniently.

[0005] Logistics route planning continuously adapts to and solves challenges in logistics and transportation through interdisciplinary technology integration. With the advancement of technology, its methods and tools are also constantly evolving, aiming to provide more efficient, reliable and economical logistics and transportation solutions to meet the growing logistics needs.

[0006] In recent years, the research on logistics path planning mainly includes:

[0007] Chinese patent "A logistics route planning method based on deep learning" (CN110929149A): This patent discloses a method for logistics route planning using deep learning technology. The method obtains traffic information in real time and combines the time cost factor of the vehicle arriving at the intersection to plan the optimal route for the logistics vehicle. This method can effectively improve the efficiency and accuracy of logistics transportation.

[0008] Chinese patent "A method for implementing path planning in real-time logistics scenarios" (CN109241413A): This patent discloses a path planning method suitable for real-time logistics scenarios. The method uses a two-layer path selection mechanism to match the rider with the path with the minimum delivery cost, and predicts the time for the rider to arrive at each node and the timeout situation, thereby improving the rider's delivery efficiency and service quality.

[0009] Chinese Patent "Route Planning and Distribution Patent Applied by JD Logistics" (CN110929149A): This patent discloses a route planning and distribution method applied by JD Logistics. The method obtains the historical paths of the current station and the preset time period, determines the repetition rate between the stations covered by the historical paths and the current station, and selects the template path assigned to the current station. This method can effectively improve the efficiency and accuracy of logistics distribution.

[0010] The above inventions have all played a certain role in promoting the improvement of logistics distribution efficiency by considering the impact of real-time traffic information or historical traffic trajectories on logistics, but there are still deficiencies in adopting efficient mechanisms to integrate historical and real-time traffic information: 1) The accuracy of real-time traffic information is crucial for logistics route planning. However, obtaining accurate real-time traffic information may face many challenges, such as the update frequency of traffic information, the coverage of information, and the reliability of information. 2) Current patented technologies may lack an effective mechanism to integrate historical and real-time traffic information. For example, if a route has often experienced traffic congestion in the past period of time, but the traffic conditions are good at the current point in time, how should these two types of information be weighed for optimal route planning? Summary of the invention

[0011] The purpose of the present invention is to provide a two-stage energy consumption prediction path planning method based on deep learning, so as to improve the distribution efficiency of cold chain electric vehicles while reducing the energy consumption of electric vehicles.

[0012] The object of the present invention is to achieve a two-stage energy consumption prediction path planning method based on deep learning by the following technical means, comprising the following steps:

[0013] Step 1: Data collection: collect data on the actual operation of cold chain distribution vehicles in the past, including historical driving data, vehicle parameter data and real-time traffic data;

[0014] Step 2: Data preprocessing: normalizing and standardizing the data, and performing feature engineering to select and construct features that are informative for energy consumption prediction;

[0015] Step 3: Energy consumption model construction, constructing driving energy consumption and cooling energy consumption calculation formulas, and extracting feature sets through convolutional neural network models and collected data;

[0016] Input the feature set into the long short-term memory network LSTM to generate an energy consumption prediction model;

[0017] Step 4: Long-term energy consumption prediction: Based on the historical data of vehicles in similar delivery tasks, extract the features related to the current task that affect energy consumption, input them into the energy consumption prediction model, predict the energy consumption of possible future sections, and obtain the driving energy consumption and cooling energy consumption prediction between every two nodes;

[0018] Step 5: Short-term energy consumption prediction: During the driving process of the vehicle, data affecting energy consumption is collected in real time and input into the energy consumption prediction model to predict the driving energy consumption and cooling energy consumption between every two nodes of the current and future road sections, and correct the long-term energy consumption prediction;

[0019] Step six, path planning and optimization, with the goal of minimizing total energy consumption and time constraints, that is, the planned route time does not exceed the delivery time limit, path planning is carried out, and the non-dominated sorting genetic algorithm NSGA-II is used to optimize the delivery path. In the subsequent driving process, the obtained delivery path is optimized and corrected according to real-time data and new short-term energy consumption forecasts.

[0020] The data is data that affects the delivery time and refrigeration energy consumption, and the historical driving data includes the actual driving speed, driving route, time and date, external environmental conditions and road slope of the vehicle on each road section;

[0021] The vehicle parameter information is the physical and mechanical parameters of the vehicle, including fully loaded and unloaded weight, battery type and capacity, and specifications of the refrigeration system;

[0022] Real-time traffic data includes current traffic flow, road information, traffic accident data, and road topology.

[0023] In the step 2, the features that are informative for energy consumption prediction are selected and constructed, including speed change rate, slope characteristics and environmental characteristics.

[0024] The driving energy consumption calculation formula is:

[0025] n is the mass of the vehicle, g is the acceleration of gravity, θ is the road slope, C d is the air resistance coefficient, ρ is the air density, K is the shape factor of the vehicle, v is the vehicle speed, Cr is the rolling resistance coefficient, P tract is the traction power of the electric vehicle;

[0026] The average speed and energy consumption during comprehensive driving μ eled Energy conversion efficiency for electric vehicles;

[0027] The calculation formula for cooling energy consumption is E cool =γ·d. Where γ is the cooling energy consumption per unit distance and d is the driving distance.

[0028] In the step three, the convolutional neural network model and the collected data are used to extract the feature set. Specifically, the pre-processed historical driving data is input into the CNN network. The data format is a multi-dimensional matrix. The feature map of the data is extracted through multiple convolutional layers to reveal the correlation and spatial pattern between different features. The convolutional feature map is reduced in dimension using a pooling layer to reduce the amount of calculation while retaining key features. The final output feature set retains the key information of the data and provides input for the subsequent LSTM network.

[0029] In step 6, the total energy consumption minimization objective function is:

[0030]

[0031] Among them, E drive (i,i+1) represents the energy consumption of the vehicle from node i to node i+1, E cool (i, i+1) represents the cooling energy consumption of the same section, N is the total number of distribution nodes in the path, E total is the total energy consumption;

[0032] The time constraint objective function is Among them, t i Indicates that the vehicle is at node i and from node i

[0033] The travel time to node i+1, T is the total time limit of the delivery task.

[0034] The specific steps of optimizing the delivery path using the non-dominated sorting genetic algorithm NSGA-II are as follows:

[0035] Initial population generation: Each individual in the initial population represents a possible delivery path. The path is represented by a set of node sequences. For the delivery points P1, P2, ..., P N , the path can be encoded as a sequence [P11,P2,P3,…,P N ],

[0036] By randomly disrupting the order of distribution nodes, multiple different paths are generated. Each path corresponds to an individual, and each individual represents a possible distribution plan in the decision variable space.

[0037] Fitness evaluation: For each individual, that is, path, the total energy consumption is calculated through the energy consumption prediction model, including the driving energy consumption Edrive and cooling energy consumption E cool , use the objective function to calculate the fitness of the individual,

[0038]

[0039] Calculate the total delivery time for each route and use it as the second objective function:

[0040]

[0041] If f2(P)>T, the path does not meet the time constraint and the fitness value will be adjusted penalistically;

[0042] Non-dominated sorting and selection: In the population, each individual is sorted according to energy consumption f1(P) and time f2(P), and the crowding distance of the individual is calculated in each non-dominated layer;

[0043] Selection operation: Use the binary tournament selection method based on non-dominated sorting and crowding distance to select individuals from the current population to generate the next generation population.

[0044] Crossover operation: Use sequential crossover or partial mapping crossover method to cross selected individuals and generate new path individuals. The crossover operation helps explore new path combinations in order to find a better path.

[0045] Mutation operation: Use point mutation or neighbor exchange method to randomly change the order of one or more nodes in the path to increase the diversity of the population and avoid local optimal solutions;

[0046] The parent and child populations are merged to form a new population, and then the merged population is subjected to non-dominated sorting and crowding distance calculation again. Individuals with the best fitness values ​​are selected from the merged population to form a new population. These individuals will enter the next generation of evolution, i.e. iteration;

[0047] Repeat the above process of selection, crossover, mutation and production of new populations until the predetermined number of iterations is reached or the population fitness converges. At this time, the optimal solution is the best delivery path under the current conditions.

[0048] The beneficial effect of the present invention is that it uses deep learning technology, namely the CNN-LSTM model, to predict and optimize the energy consumption of electric vehicles. The uniqueness of this method is that it not only takes into account multiple factors such as road slope, traffic conditions and vehicle load, but also combines historical driving data and real-time traffic data to achieve accurate prediction of energy consumption for a specific route.

[0049] In addition, a two-stage solution is adopted, in which the initial stage focuses on the prediction before departure, while the subsequent stage focuses more on the prediction after departure during the journey. This enables a rough prediction of energy consumption before the journey begins, and dynamic adjustments can be made during the journey based on real-time traffic data, thereby achieving more accurate energy consumption prediction.

[0050] Finally, the NSGA-II algorithm is used to optimize the route to further reduce the energy consumption of electric vehicles and extend their driving range. This optimization not only takes into account the current traffic conditions, but also predicts possible traffic changes in the future, so that electric vehicles can choose the optimal driving route under any traffic conditions.

[0051] Ultimately, it can effectively reduce the energy consumption of electric vehicles, extend the driving range of electric vehicles, and provide important reference information for cold chain distribution, thereby improving the efficiency and quality of cold chain distribution. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A flow chart of a two-stage energy consumption prediction path planning method based on deep learning;

[0053] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. DETAILED DESCRIPTION

[0054] [Example 1]

[0055] A two-stage energy consumption prediction path planning method based on deep learning, comprising the following steps:

[0056] Step 1: Data collection: collect data on the actual operation of cold chain distribution vehicles in the past, including historical driving data, vehicle parameter data and real-time traffic data;

[0057] The data is data that affects the delivery time and refrigeration energy consumption, and the historical driving data includes the actual driving speed, driving route, time and date, external environmental conditions and road slope of the vehicle on each road section;

[0058] The vehicle parameter information is the physical and mechanical parameters of the vehicle, including fully loaded and unloaded weight, battery type and capacity, and specifications of the refrigeration system;

[0059] Real-time traffic data includes current traffic flow, road information, traffic accident data, and road topology.

[0060] First, we actively collect rich historical driving data, covering various indicators from vehicle speed to road slope, and build a historical data framework to support model training and improve prediction accuracy. This data provides a solid historical foundation for the model, helping to improve the accuracy and reliability of predictions.

[0061] Advanced sensing technologies (on-board sensors, traffic cameras, and online traffic information services, etc.) are used to monitor and collect detailed data on road conditions and traffic in real time, ensuring that the information obtained is both real-time and comprehensive, providing data support for immediate route adjustments, thereby playing a key role in real-time decision-making, namely short-term energy consumption forecasting.

[0062] Specifically, historical driving data includes delivery time, delivery location, customer address, and delivery route information, etc. These data provide vehicle operation records at different times and under different road conditions, providing a basis for the subsequent training of energy consumption prediction models.

[0063] Including but not limited to the following:

[0064] Driving speed: record the actual driving speed of the vehicle on each road section.

[0065] Driving route: Track the path your vehicle takes to get detailed information on different road segments.

[0066] Time and date: Mark the specific time period and date corresponding to the data, and consider the impact of time on energy consumption.

[0067] External environmental conditions: including weather, temperature, humidity, road conditions, etc., which may significantly affect energy consumption.

[0068] Traffic network data: including road topology, road slope, speed limit information, etc. This information is used to accurately calculate the energy consumption of vehicles on different road sections and provide data support for route planning.

[0069] Vehicle parameter data, collecting key physical and mechanical parameters of the vehicle, such as:

[0070] Vehicle weight: includes both fully loaded and unloaded weight.

[0071] Battery type and capacity: The type of battery used in the vehicle and its capacity, which determines the vehicle's range.

[0072] Refrigeration system specifications: The power consumption parameters and operating characteristics of the refrigeration equipment, which directly affect the energy consumption in cold chain transportation.

[0073] Real-time traffic data, which obtains and processes the current traffic flow, road conditions, traffic accidents and other data from the traffic management system in real time. The introduction of real-time traffic data can significantly improve the real-time and accuracy of energy consumption prediction, especially in the face of urban road networks with complex and changeable traffic conditions, real-time data is particularly important;

[0074] Traffic flow: The density and flow of vehicles on a road.

[0075] Road information: current road conditions, such as closures, construction, accidents, etc.

[0076] Traffic accident data: unexpected traffic incidents, which may affect driving speed and energy consumption.

[0077] Step 2: Data preprocessing: normalizing and standardizing the data, and performing feature engineering to select and construct features that are informative for energy consumption prediction;

[0078] In the step 2, the features that are informative for energy consumption prediction are selected and constructed, including speed change rate, slope characteristics and environmental characteristics.

[0079] Sophisticated data cleaning algorithms are used to accurately remove noise and redundancy from unstructured data sets, ensuring high-quality data input for analysis.

[0080] Apply a series of statistical standardization techniques and machine learning methods to normalize the data and optimize the data structure to ensure that data from different sources can be seamlessly connected and processed in the model, laying a solid foundation for subsequent in-depth analysis

[0081] Specifically, remove duplicate values: delete duplicate records to ensure data uniqueness.

[0082] Handling missing values: Handle missing data through interpolation, mean filling, etc. to avoid model errors caused by incomplete data.

[0083] Remove outliers: Identify and remove obvious anomalous data, such as extreme speed or energy consumption values.

[0084] In order to improve the efficiency and accuracy of model training, the data needs to be standardized or normalized:

[0085] Standardization: Transform the data into a standard normal distribution with mean 0 and variance 1.

[0086] Normalization: Adjust the data values ​​to the range of 0 to 1 to eliminate the dimensional differences between different features.

[0087] Select and construct the most informative features for energy consumption prediction:

[0088] Speed ​​change rate: Based on historical speed data, calculate the rate of change of vehicle speed to capture the characteristics of acceleration or deceleration during driving.

[0089] Slope characteristics: Utilize road network information to calculate the slope changes of each road section, which has a direct impact on driving energy consumption.

[0090] Environmental characteristics: Based on weather and road condition data, relevant characteristics are extracted, such as the impact of humidity, temperature, etc. on vehicle driving and refrigeration system energy consumption.

[0091] Step 3: Energy consumption model construction, construct driving energy consumption and cooling energy consumption calculation formulas, and extract feature sets through convolutional neural network models and collected data;

[0092] Input the feature set into the long short-term memory network LSTM to generate an energy consumption prediction model;

[0093] The energy consumption model is the core of the system, covering the calculation of driving energy consumption and cooling energy consumption.

[0094] Driving energy consumption refers to the energy consumed by a vehicle when overcoming rolling resistance, air resistance and slope. The driving energy consumption calculation formula is: m is the mass of the vehicle (kg), g is the acceleration due to gravity (9.81 m / s 2 ), θ is the road slope (degrees), C d is the air resistance coefficient, ρ is the air density (kg / m 3 ), K is the shape factor of the vehicle, v is the vehicle speed (m / s), Cr is the rolling resistance coefficient, P tract is the traction power of the electric vehicle (kw);

[0095] The average speed and energy consumption during comprehensive driving μ eled Energy conversion efficiency for electric vehicles;

[0096] Refrigeration energy consumption is the electrical energy consumed to maintain the low temperature environment required for the goods. Its calculation formula is simplified to multiply the energy consumption per kilometer by the driving distance.

[0097] The calculation formula for cooling energy consumption is E cool =γ·d. Where γ is the cooling energy consumption per unit distance and d is the driving distance.

[0098] After completing data collection and preprocessing, the next step is to train the energy consumption prediction model through deep learning methods.

[0099] In the step three, the convolutional neural network model and the collected data are used to extract the feature set. Specifically, the pre-processed historical driving data is input into the CNN network. The data format is a multi-dimensional matrix. The feature map of the data is extracted through multiple convolutional layers to reveal the correlation and spatial pattern between different features. The convolutional feature map is reduced in dimension using a pooling layer to reduce the amount of calculation while retaining key features. The final output feature set retains the key information of the data and provides input for the subsequent LSTM network.

[0100] Apply convolutional neural network (CNN) to conduct in-depth analysis of complex road images, and use its powerful feature extraction capabilities to accurately capture and analyze road condition details;

[0101] Use long short-term memory (LSTM) networks to explore and learn time series patterns of distance, load, speed, and energy consumption to predict future conditions and respond in real time;

[0102] Integrate the analysis results of CNN and LSTM, build a comprehensive prediction model through precise algorithm tuning, and train and strictly verify large amounts of data on high-performance servers;

[0103] Convolutional Neural Network (CNN) is used to extract the spatial features of input data. The specific process is as follows:

[0104] Input data formatting

[0105] The preprocessed historical driving data is input into CNN, and the data format includes multi-dimensional matrix form, such as vehicle speed, environmental conditions, road slope, etc.

[0106] Convolution Operation

[0107] Feature maps of the data are extracted through multiple convolutional layers, revealing the correlations and spatial patterns between different features.

[0108] Feature Mapping and Pooling

[0109] The pooling layer is used to reduce the dimension of the convolutional feature map, reducing the amount of calculation while retaining the key features.

[0110] Feature Output

[0111] The final output feature set retains the key information of the data and provides input for the subsequent LSTM network.

[0112] Step 3.2: LSTM model training

[0113] Long short-term memory (LSTM) networks are used to process time series data and capture the temporal dependencies in the data.

[0114] Input time series data

[0115] The feature set extracted by CNN is converted into a time series and input into the LSTM model.

[0116] Construction of LSTM layer

[0117] The LSTM network captures the temporal dynamics of input data through multiple memory units and learns the complex relationship between energy consumption and time.

[0118] Fully connected layer and output layer

[0119] After the LSTM layer, fully connected layers are added to map the learned features to the energy consumption prediction values, and finally the prediction results are output.

[0120] Model Validation

[0121] Use the validation data set to test the model, calculate the prediction accuracy and error of the model, and optimize the model performance by adjusting the network parameters when necessary.

[0122] Step 4: Long-term energy consumption prediction: Based on the historical data of vehicles in similar delivery tasks, extract the features related to the current task that affect energy consumption, input them into the energy consumption prediction model, predict the energy consumption of possible future sections, and obtain the driving energy consumption and cooling energy consumption prediction between every two nodes;

[0123] Step 5: Short-term energy consumption prediction: During the driving process of the vehicle, data affecting energy consumption is collected in real time and input into the energy consumption prediction model to predict the driving energy consumption and cooling energy consumption between every two nodes of the current and future road sections, and correct the long-term energy consumption prediction;

[0124] Energy consumption prediction is the core part of this method. Through a two-stage energy consumption prediction method, the energy consumption of each possible distribution path is evaluated. Energy consumption prediction includes two stages: long-term prediction and short-term prediction.

[0125] Phase 1: Long-term energy consumption forecast

[0126] In this phase, the system uses historical logistics delivery data to predict the energy consumption required for a vehicle to complete a specific delivery route. Long-term prediction is intended to provide a preliminary energy consumption estimate based on historical data to help identify high-energy consumption routes.

[0127] Phase 2: Short-term energy consumption forecast

[0128] Short-term energy consumption forecasting is initiated during the actual driving process of the vehicle. The system incorporates real-time delivery data into the energy consumption forecasting model to dynamically forecast the energy consumption of the vehicle's remaining journey. This short-term forecast combines real-time traffic conditions and the current state of the vehicle to ensure the accuracy and timeliness of the energy consumption forecast.

[0129] Through the above two-stage energy consumption prediction, the system can conduct multi-dimensional analysis of energy consumption at different time scales, thereby improving the prediction accuracy and optimizing path selection.

[0130] Long-term energy consumption forecast is a preliminary energy consumption assessment of the entire delivery task based on the vehicle's historical delivery data. It aims to provide a general energy consumption trend and guide the initial selection of route planning.

[0131] Historical data analysis

[0132] The system first analyzes the historical data of the vehicle in similar delivery tasks and extracts features related to the current task, such as the vehicle's driving speed on different road sections, average energy consumption, and the impact of ambient temperature on the energy consumption of the refrigeration system.

[0133] These features are input into the energy consumption prediction model to infer the overall energy consumption trend of the current task. Especially for long-distance delivery tasks, this prediction based on historical data can provide a preliminary energy consumption assessment.

[0134] Long-term energy consumption trend forecast

[0135] After analyzing historical data, the system uses deep learning models (including CNN and LSTM) to predict long-term energy consumption trends. Through this prediction, the system can identify which sections of the road are likely to consume more energy, so as to avoid these high-energy consumption sections in advance.

[0136] For example, vehicles tend to consume more energy on roads with steep slopes or heavy traffic. Through trend analysis of historical data, the system can identify and mark these roads in the early stages of planning, providing data support for subsequent route optimization.

[0137] Short-term energy consumption forecast

[0138] Short-term energy consumption forecasting is carried out after the vehicle begins the actual delivery task. It is a refinement and adjustment of the long-term forecast and mainly relies on the input of real-time data. The goal of short-term forecasting is to dynamically respond to various changes in the delivery process, such as real-time traffic conditions, emergencies, etc.

[0139] Real-time data collection and input

[0140] When the vehicle starts a delivery mission, the system will continuously collect real-time data, including current traffic conditions (such as traffic flow, congestion level), road information (such as road closures, construction information), vehicle status (such as current battery power, temperature, refrigeration system operating status), etc.

[0141] These real-time data are immediately input into the energy consumption forecasting model to correct the energy consumption estimates obtained in the long-term forecasting stage. The frequency and accuracy of real-time data collection directly affect the accuracy of short-term energy consumption forecasts.

[0142] Dynamic energy consumption calculation and correction

[0143] Combined with real-time data, the system will dynamically calculate the energy consumption of the remaining delivery routes. By capturing short-term changes in time series data through the LSTM network, the system can update the energy consumption forecast in real time to ensure that the forecast results are highly consistent with the actual situation.

[0144] For example, if the system detects a traffic accident on the road ahead, which may cause the vehicle to travel at a low speed for a long time on that road, the system will immediately re-evaluate the energy consumption of that road and adjust the path planning to avoid excessive energy consumption.

[0145] Real-time energy consumption feedback and adjustment

[0146] In the process of short-term energy consumption forecasting, the system will not only continuously correct the energy consumption calculation, but also compare and analyze the actual energy consumption with the predicted energy consumption. If deviations are found, the system will adaptively adjust the model parameters to improve the forecast accuracy.

[0147] The real-time feedback mechanism allows the system to gradually optimize energy consumption prediction and route planning during driving, ensuring that each adjustment can more accurately reflect the current delivery environment.

[0148] Step six, path planning and optimization, with the goal of minimizing total energy consumption and time constraints, that is, the planned route time does not exceed the delivery time limit, path planning is carried out, and the non-dominated sorting genetic algorithm NSGA-II is used to optimize the delivery path. In the subsequent driving process, the obtained delivery path is optimized and corrected according to real-time data and new short-term energy consumption forecasts.

[0149] After completing the energy consumption forecast, the delivery route needs to be optimized based on the energy consumption forecast results. The core goal of route planning is to select the route with the lowest energy consumption while meeting the delivery time requirements.

[0150] The path planning problem can be formalized as an optimization problem with multi-objective constraints. The goal is to start from the distribution center ψ in a given urban transportation network Ω, pass through multiple distribution nodes and return to ψ, so that the distribution vehicle completes the task within the specified time T while minimizing energy consumption. The following is the specific construction of the mathematical model.

[0151] In step 6, the total energy consumption minimization objective function is:

[0152]

[0153] Among them, E drive (i,i+1) represents the energy consumption of the vehicle from node i to node i+1, E cool (i, i+1) represents the cooling energy consumption of the same section, and N is the total number of distribution nodes in the path;

[0154] The time constraint objective function is Among them, t i represents the driving time of the vehicle at node i and from node i to node i+1, and T is the total time limit of the delivery task.

[0155] NSGA-II is a multi-objective optimization algorithm suitable for solving problems such as path planning that involve multiple conflicting objectives.

[0156] The specific steps of optimizing the delivery path using the non-dominated sorting genetic algorithm NSGA-II are as follows:

[0157] Initial population generation:

[0158] Path encoding,

[0159] Each individual in the initial population represents a possible delivery path, which is represented by a set of node sequences. N , the path can be encoded as a sequence [P11,P2,P3,…,P N ],

[0160] Randomly generate the initial population:

[0161] By randomly disrupting the order of the delivery nodes, multiple different paths are generated, each path corresponds to an individual. Each individual represents a possible delivery plan in the decision variable space;

[0162] Fitness evaluation:

[0163] Energy consumption calculation:

[0164] For each individual, i.e., path, the total energy consumption is calculated through the energy consumption prediction model, including the driving energy consumption E drive and cooling energy consumption E cool , use the objective function to calculate the fitness of the individual,

[0165]

[0166] Time Assessment:

[0167] Calculate the total delivery time for each route and use it as the second objective function:

[0168]

[0169] If f2(P)>T, the path does not meet the time constraint and the fitness value will be adjusted penalistically;

[0170] Non-dominated sorting and selection:

[0171] Non-dominated sorting:

[0172] In the population, each individual is sorted according to energy consumption f1(P) and time f2(P); path P a Dominant Path P b The conditions are:

[0173] f1(P a )≤f1(P b ) and f2(P a )≤f2(P b )

[0174] And at least one inequality sign is a strict inequality.

[0175] Crowding distance calculation, in order to maintain the diversity of the population, the crowding distance of individuals is calculated in each non-dominated layer. The crowding distance indicates the degree of isolation of individuals in the target space, and the calculation formula is:

[0176]

[0177] Among them, f k (i+1) and f k (i-1) are the neighboring individual values ​​of individual i on the kth target.

[0178] Selection, Crossover, and Mutation

[0179] Selection operation: Use the binary tournament selection method based on non-dominated sorting and crowding distance to select individuals from the current population to generate the next generation population, giving priority to individuals with lower non-dominated levels or larger crowding distances.

[0180] Crossover operation: Use the sequential crossover (OX) or partial mapping crossover (PMX) method to cross the selected individuals and generate new path individuals. The crossover operation helps explore new path combinations in order to find a better path.

[0181] Mutation operation: Use point mutation or neighbor exchange method to randomly change the order of one or more nodes in the path to increase the diversity of the population and avoid local optimal solutions;

[0182] Environmental selection and generation of new populations,

[0183] The parent and child populations are merged to form a new population, and then the merged population is subjected to non-dominated sorting and crowding distance calculation again. The individuals with the best fitness values ​​(usually the first N) are selected from the merged population to form a new population. These individuals will enter the next generation of evolution, i.e. iteration;

[0184] Repeat the above process of selection, crossover, mutation and production of new populations until the predetermined number of iterations is reached or the population fitness converges. At this time, the optimal solution is the best delivery path under the current conditions.

[0185] When the optimal solution of the population no longer improves significantly in several consecutive generations, the algorithm is considered to have converged. At this time, the optimal solution is the best delivery path under the current conditions.

[0186] Before the delivery begins, the non-dominated sorting genetic algorithm NSGA-II is used to optimize the delivery path based on the results of long-term energy consumption prediction to obtain a preliminary delivery path.

[0187] During driving, short-term energy consumption prediction is performed based on the collected real-time data, and energy consumption prediction is performed on the road sections between subsequent nodes to obtain the energy consumption of each road section (i.e., between two nodes) that may be involved in the subsequent driving. The delivery path is then optimized using the non-dominated sorting genetic algorithm NSGA-II to obtain the optimized delivery path.

[0188] During subsequent driving, new real-time data is collected and short-term energy consumption forecasts are repeated, thereby continuously optimizing the previous delivery route.

[0189] After the path planning is completed and the optimal path is selected, the system also needs to perform data processing and feedback after the task is completed.

[0190] After completing the delivery task, the actual driving data (such as actual energy consumption, driving time, changes in environmental conditions, etc.) are fed back to the database. These data are used to evaluate the accuracy and effectiveness of the current energy consumption prediction model and path planning algorithm.

[0191] Based on the feedback data, the parameters of the energy consumption prediction model are automatically adjusted, especially the weights in the CNN and LSTM networks are fine-tuned to adapt to different delivery environments and task requirements. The updated model will be applied in future delivery tasks to improve the accuracy of prediction and the efficiency of planning.

[0192] The total energy consumption of each delivery task is evaluated and summarized, and the main components of energy consumption (the ratio of driving energy consumption to cooling energy consumption) are analyzed.

[0193] The pathfinding algorithm is optimized and iteratively learned through feedback. Specifically, based on actual delivery data, key parameters in the NSGA-II algorithm are optimized and adjusted, such as crossover rate, mutation rate, population size, etc., to improve the applicability and convergence speed of the algorithm in different delivery tasks.

[0194] Through the execution and feedback of multiple delivery tasks, the performance of the model and algorithm is gradually improved to make it more adaptable to the complex and changeable urban road network environment and the special requirements of cold chain transportation.

[0195] In summary, if Figure 1 As shown, in specific use, data is first collected and processed, and the processed data is input into the energy consumption prediction model to obtain energy consumption data between each node;

[0196] When the destination is reached and the delivery is completed, the path optimization ends. If the delivery is not completed, the data of this trip will be fed back to the entire system, the energy consumption prediction model and the non-dominated sorting genetic algorithm NSGA-II will be optimized, and the process from collecting real-time data to path planning will be repeated until the delivery is completed.

[0197] When planning a route, first make a long-term prediction and plan a long-term route. During driving, adjust the long-term route based on the real-time data collected and plan the remaining mileage route. For example, based on traffic information, if an accident occurs on a road in the long-term route, the energy consumption of this section will increase. When planning the route later, since the energy consumption here is too high, the section will be bypassed and replanned to obtain a new route. Repeat the above steps until the delivery is completed.

Claims

1. A two-stage energy consumption prediction path planning method based on deep learning, characterized in that: The following steps are involved: Step 1: Data collection: collect data on the actual operation of cold chain distribution vehicles in the past, including historical driving data, vehicle parameter data and real-time traffic data; Step 2: Data preprocessing: normalizing and standardizing the data, and performing feature engineering to select and construct features that are informative for energy consumption prediction; Step 3: Energy consumption model construction, construct driving energy consumption and cooling energy consumption calculation formulas, and extract feature sets through convolutional neural network models and collected data; Input the feature set into the long short-term memory network LSTM to generate an energy consumption prediction model; Step 4: Long-term energy consumption prediction: Based on the historical data of vehicles in similar delivery tasks, extract the features related to the current task that affect energy consumption, input them into the energy consumption prediction model, predict the energy consumption of possible future sections, and obtain the driving energy consumption and cooling energy consumption prediction between every two nodes; Step 5: Short-term energy consumption prediction: During the driving process of the vehicle, data affecting energy consumption is collected in real time and input into the energy consumption prediction model to predict the driving energy consumption and cooling energy consumption between every two nodes of the current and future road sections, and correct the long-term energy consumption prediction; Step six, path planning and optimization, with the goal of minimizing total energy consumption and time constraints, that is, the planned route time does not exceed the delivery time limit, path planning is carried out, and the non-dominated sorting genetic algorithm NSGA-II is used to optimize the delivery path. In the subsequent driving process, the obtained delivery path is optimized and corrected according to real-time data and new short-term energy consumption forecasts.

2. The method for two-stage energy consumption prediction path planning based on deep learning according to claim 1 is characterized in that: The data is data that affects the delivery time and refrigeration energy consumption, and the historical driving data includes the actual driving speed, driving route, time and date, external environmental conditions and road slope of the vehicle on each road section; The vehicle parameter information is the physical and mechanical parameters of the vehicle, including fully loaded and unloaded weight, battery type and capacity, and specifications of the refrigeration system; Real-time traffic data includes current traffic flow, road information, traffic accident data, and road topology.

3. The method for two-stage energy consumption prediction path planning based on deep learning according to claim 1 is characterized in that: In the step 2, the features that are informative for energy consumption prediction are selected and constructed, including speed change rate, slope characteristics and environmental characteristics.

4. The method for two-stage energy consumption prediction path planning based on deep learning according to claim 1 is characterized in that: The driving energy consumption calculation formula is: n is the mass of the vehicle, g is the acceleration of gravity, θ is the road slope, C d is the air resistance coefficient, ρ is the air density, K is the shape factor of the vehicle, v is the vehicle speed, C r is the rolling resistance coefficient, P tract is the traction power of the electric vehicle; The average speed and energy consumption during comprehensive driving μ eled Energy conversion efficiency for electric vehicles; The formula for calculating cooling energy consumption is E cool =γ·d. Where γ is the cooling energy consumption per unit distance and d is the driving distance.

5. The method for two-stage energy consumption prediction path planning based on deep learning according to claim 1 is characterized in that: In the step three, the convolutional neural network model and the collected data are used to extract the feature set. Specifically, the pre-processed historical driving data is input into the CNN network. The data format is a multi-dimensional matrix. The feature map of the data is extracted through multiple convolutional layers to reveal the correlation and spatial pattern between different features. The convolutional feature map is reduced in dimension using a pooling layer to reduce the amount of calculation while retaining key features. The final output feature set retains the key information of the data and provides input for the subsequent LSTM network.

6. The method for two-stage energy consumption prediction path planning based on deep learning according to claim 1, characterized in that: In step 6, the total energy consumption minimization objective function is: Among them, E drive (i,i+1) represents the energy consumption of the vehicle from node i to node i+1, E cool (i, i+1) represents the cooling energy consumption of the same section, N is the total number of distribution nodes in the path, E total is the total energy consumption; The time constraint objective function is Among them, t i represents the driving time of the vehicle at node i and from node i to node i+1, and T is the total time limit of the delivery task.

7. The method for two-stage energy consumption prediction path planning based on deep learning according to claim 1, characterized in that: The specific steps of optimizing the delivery path using the non-dominated sorting genetic algorithm NSGA-II are as follows: Initial population generation: Each individual in the initial population represents a possible delivery path. The path is represented by a set of node sequences. For the delivery points P1, P2, ..., P N , the path can be encoded as a sequence [P11,P2,P3,…,P N ], By randomly disrupting the order of distribution nodes, multiple different paths are generated. Each path corresponds to an individual, and each individual represents a possible distribution plan in the decision variable space. Fitness evaluation: For each individual, that is, path, the total energy consumption is calculated through the energy consumption prediction model, including the driving energy consumption E drive and cooling energy consumption E cool , use the objective function to calculate the fitness of the individual, Calculate the total delivery time for each route and use it as the second objective function: If f2(P)>T, the path does not meet the time constraint and the fitness value will be adjusted penalistically; Non-dominated sorting and selection: In the population, each individual is sorted according to energy consumption f1(P) and time f2(P), and the crowding distance of the individual is calculated in each non-dominated layer; Selection operation: Use the binary tournament selection method based on non-dominated sorting and crowding distance to select individuals from the current population to generate the next generation population. Crossover operation: Use sequential crossover or partial mapping crossover method to cross selected individuals and generate new path individuals. The crossover operation helps explore new path combinations in order to find a better path. Mutation operation: Use point mutation or neighbor exchange method to randomly change the order of one or more nodes in the path to increase the diversity of the population and avoid local optimal solutions; The parent and child populations are merged to form a new population, and then the merged population is subjected to non-dominated sorting and crowding distance calculation again. Individuals with the best fitness values ​​are selected from the merged population to form a new population. These individuals will enter the next generation of evolution, i.e. iteration; The above process of selection, crossover, mutation and production of new populations is repeated until the predetermined number of iterations is reached or the population fitness converges. At this time, the optimal solution is the best delivery path under the current conditions.

Images