A method and system for predicting and dispatching power load

Abstract

The present invention relates to the technical field of load forecasting and scheduling, and discloses a forecasting and scheduling method and system for electric load, including calculating the optimal compression frequency according to garbage filling data and comprehensive compression characteristic parameters, obtaining the estimated power consumption curve of the compressed garbage truck according to the compression power parameters, operation trajectory and optimal compression frequency; gridding the target area, calculating the distribution density of the compressed garbage truck in each grid, and obtaining the charging demand distribution heat map of each grid according to the distribution density and the estimated power consumption curve; predicting the facility load of the charging facility according to the charging demand distribution heat map; constructing an optimization scheduling model according to the estimated power consumption curve of the compressed garbage truck and the predicted load of the charging facility, and performing iterative calculation to obtain the optimal scheduling strategy. The present invention improves the working efficiency of the compressed garbage truck, realizes the refined management of vehicle charging scheduling, and ensures the efficient operation of urban sanitation.

Description

Technical Field

[0001] The present invention relates to the technical field of load forecasting and scheduling, and in particular to a method and system for forecasting and scheduling electric load. Background Art

[0002] With the development of urbanization and the requirements of environmental protection, electric compression garbage trucks are increasingly being used in urban sanitation work. In the process of garbage transportation, the garbage in the onboard garbage bin needs to be continuously compressed. In fact, the compression characteristics of different types of garbage vary greatly. For example, kitchen waste has a high water content, and a large amount of exudate will be produced during the compression process, resulting in reduced compression efficiency and increased compression frequency. However, for highly compressible garbage such as plastic bottles, the compression process is relatively easy and the compression frequency is relatively low. The compression frequency directly determines the energy consumption rate of the battery, and the battery energy consumption directly affects the charging needs of the compression garbage truck. The higher the compression frequency, the faster the battery consumption and the more frequent the charging needs.

[0003] In the current sanitation work, compressed garbage trucks mostly use the default compression frequency to work. The charging demand of compressed garbage trucks is mainly determined manually by sanitation workers based on the vehicle's power level, and the corresponding charging facilities of compressed garbage trucks are also fixed. This leads to the current low compression efficiency of compressed garbage trucks and a lack of refined management of the vehicle's power level. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a method and system for predicting and scheduling power loads, so as to achieve the technical effect of improving the working efficiency of compressed garbage trucks and realizing refined management of compressed garbage trucks.

[0005] In a first aspect, the present invention provides a method for predicting and dispatching electric loads, the method comprising:

[0006] Obtain garbage filling data of each compression garbage truck in the target area, and select corresponding comprehensive compression characteristic parameters from a pre-established compression model database according to the running trajectory of the compression garbage truck;

[0007] Calculating the optimal compression frequency according to the garbage filling data and the comprehensive compression characteristic parameters, and obtaining the estimated power consumption curve of each compression garbage truck according to the compression power parameters, the running trajectory and the optimal compression frequency of the compression garbage truck;

[0008] Divide the target area into grids, calculate the distribution density of compressed garbage trucks in each grid according to the running tracks of each compressed garbage truck, and obtain a charging demand distribution heat map of each grid according to the distribution density and the estimated power consumption curve;

[0009] According to the geographical location of the charging facilities in the target area and the charging demand distribution heat map, the facility load of each charging facility is predicted to obtain the predicted load of the charging facility;

[0010] An optimization scheduling model is constructed based on the battery power, operation trajectory, estimated power consumption curve, garbage filling data and the geographical location, real-time load and predicted load of the compressed garbage truck, and the optimization scheduling model is iteratively calculated to obtain the optimal scheduling strategy.

[0011] Furthermore, the compression model database is established by the following steps:

[0012] Perform compression tests on different types of garbage samples to obtain compression characteristic parameters and water content influence coefficients of each type of garbage sample, wherein the compression characteristic parameters include compression ratio and rebound coefficient, and the water content influence coefficient includes compression influence coefficient and rebound influence coefficient;

[0013] According to the historical garbage data of each functional area in the target area, the garbage composition structure of each functional area is determined, and the comprehensive compression characteristic parameters of each functional area are calculated according to the garbage composition structure and the compression characteristic parameters. According to the functional areas, the comprehensive compression characteristic parameters and the water content influence coefficient, a compression model database is constructed.

[0014] Furthermore, the step of calculating the optimal compression frequency according to the garbage filling data and the comprehensive compression characteristic parameters, and obtaining the estimated power consumption curve of each compression garbage truck according to the compression power parameters, operation trajectory and the optimal compression frequency of the compression garbage truck includes:

[0015] Inputting the garbage filling data and the comprehensive compression characteristic parameters into a pre-established frequency prediction model to obtain an optimal compression frequency, and adjusting the current compression frequency of the compression garbage truck according to the optimal compression frequency, wherein the frequency prediction model is constructed using a gradient boosting tree algorithm;

[0016] The operation trajectory of the compression garbage truck and the compression power parameters of the compression mechanism are obtained, and the compression power parameters, the operation trajectory and the optimal compression frequency are input into a pre-established power consumption association model to obtain an estimated power consumption curve of each compression garbage truck. The power consumption association model is constructed using the ARIMA algorithm.

[0017] Furthermore, the step of dividing the target area into grids, calculating the distribution density of compressed garbage trucks in each grid according to the running tracks of each compressed garbage truck, and obtaining the charging demand distribution heat map of each grid according to the distribution density and the estimated power consumption curve includes:

[0018] Using a hexagonal grid partitioning algorithm to grid the target area to obtain a grid data structure, wherein the grid data structure includes a grid number and grid boundary coordinates;

[0019] According to the running tracks of each compressed garbage truck, the compressed garbage truck is allocated to each grid, and according to the grid area of ​​each grid, the distribution density of the compressed garbage truck in each grid is obtained;

[0020] According to the estimated power consumption curve, the charging demand value of each compressed garbage truck is calculated, and according to the operation trajectory and the charging demand value, a spatiotemporal charging demand point data set is generated, and according to the spatiotemporal charging demand point data set, a charging demand distribution heat map of each grid is obtained.

[0021] Furthermore, the step of predicting the facility load of each charging facility according to the geographical location of the charging facilities in the target area and the charging demand distribution heat map to obtain the predicted load of the charging facilities includes:

[0022] Constructing a charging simulation model according to the geographical location of charging facilities in the target area and the charging demand distribution heat map;

[0023] According to the simulation results of the charging simulation model, the predicted load of the charging facility is obtained.

[0024] Furthermore, the steps of constructing an optimization scheduling model based on the battery power, operation trajectory, estimated power consumption curve, garbage filling data, and geographical location, real-time load, and predicted load of the compressed garbage truck, and iteratively calculating the optimization scheduling model to obtain the optimal scheduling strategy include:

[0025] According to the battery power, running trajectory, estimated power consumption curve, and garbage filling data of the compacting garbage truck, a preset battery exhaustion risk prediction model is used to evaluate the battery exhaustion risk of the compacting garbage truck to obtain a battery exhaustion risk value;

[0026] Taking the maximization of the working efficiency of the compressed garbage truck as the objective function, and the battery power, running trajectory, battery exhaustion risk value of the compressed garbage truck and the geographical location, real-time load, and predicted load of the charging facilities as constraints, an optimization scheduling model based on multiple vehicle objectives is constructed;

[0027] The optimization scheduling model is iteratively solved using a greedy algorithm to obtain an optimal scheduling strategy, which includes charging time, charging location, and charging duration.

[0028] In a second aspect, the present invention provides a power load forecasting and dispatching system, the system comprising:

[0029] A data acquisition module is used to obtain garbage filling data of each compression garbage truck in the target area, and select corresponding comprehensive compression characteristic parameters from a pre-established compression model database according to the running trajectory of the compression garbage truck;

[0030] A power consumption estimation module, used to calculate the optimal compression frequency according to the garbage filling data and the comprehensive compression characteristic parameters, and obtain an estimated power consumption curve of each compression garbage truck according to the compression power parameters, operation trajectory and the optimal compression frequency of the compression garbage truck;

[0031] A charging demand estimation module is used to divide the target area into grids, calculate the distribution density of compressed garbage trucks in each grid according to the running tracks of each compressed garbage truck, and obtain a charging demand distribution heat map of each grid according to the distribution density and the estimated power consumption curve;

[0032] A charging load prediction module, used to predict the facility load of each charging facility according to the geographical location of the charging facilities in the target area and the charging demand distribution heat map, so as to obtain the predicted load of the charging facilities;

[0033] The vehicle optimization scheduling module is used to build an optimization scheduling model based on the battery power, operation trajectory, estimated power consumption curve, garbage filling data and geographical location, real-time load and predicted load of the compressed garbage truck, and iterate the optimization scheduling model to obtain the optimal scheduling strategy.

[0034] Furthermore, the power consumption estimation module is further used to input the garbage filling data and the comprehensive compression characteristic parameters into a pre-established frequency prediction model to obtain an optimal compression frequency, and adjust the current compression frequency of the compression garbage truck according to the optimal compression frequency, wherein the frequency prediction model is constructed using a gradient boosting tree algorithm;

[0035] The operation trajectory of the compression garbage truck and the compression power parameters of the compression mechanism are obtained, and the compression power parameters, the operation trajectory and the optimal compression frequency are input into a pre-established power consumption association model to obtain an estimated power consumption curve of each compression garbage truck. The power consumption association model is constructed using the ARIMA algorithm.

[0036] Furthermore, the charging demand estimation module is further used to grid the target area using a hexagonal grid division algorithm to obtain a grid data structure, wherein the grid data structure includes a grid number and grid boundary coordinates;

[0037] According to the running tracks of each compressed garbage truck, the compressed garbage truck is allocated to each grid, and according to the grid area of ​​each grid, the distribution density of the compressed garbage truck in each grid is obtained;

[0038] According to the estimated power consumption curve, the charging demand value of each compressed garbage truck is calculated, and according to the operation trajectory and the charging demand value, a spatiotemporal charging demand point data set is generated, and according to the spatiotemporal charging demand point data set, a charging demand distribution heat map of each grid is obtained.

[0039] Furthermore, the vehicle optimization scheduling module is also used to evaluate the battery depletion risk of the compressed garbage truck using a preset battery depletion risk prediction model according to the battery power, running trajectory, estimated power consumption curve, and garbage filling data of the compressed garbage truck to obtain a battery depletion risk value;

[0040] Taking the maximization of the working efficiency of the compressed garbage truck as the objective function, and the battery power, running trajectory, battery exhaustion risk value of the compressed garbage truck and the geographical location, real-time load, and predicted load of the charging facilities as constraints, an optimization scheduling model based on multiple vehicle objectives is constructed;

[0041] The optimization scheduling model is iteratively solved using a greedy algorithm to obtain an optimal scheduling strategy, which includes charging time, charging location, and charging duration.

[0042] The present invention provides a method and system for predicting and scheduling power loads. The present invention can achieve optimal control of the compression frequency of a compression garbage truck by analyzing the compression characteristics of garbage and the garbage composition structure in the target area, and accurately estimate the power consumption of the compression garbage truck and the charging demand in the target area according to the compression frequency and operation trajectory of the compression garbage truck, thereby achieving optimized scheduling of vehicle charging of the compression garbage truck. The vehicle charging optimization scheduling method provided by the present invention can effectively improve the working efficiency of the compression garbage truck, realize the refined management of the charging scheduling of the compression garbage truck, and ensure the efficient operation of urban sanitation. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a flow chart of a method for predicting and dispatching electric load in an embodiment of the present invention;

[0044] Figure 2 It is a structural diagram of the power load prediction and dispatching system in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] See also Figure 1 The first embodiment of the present invention provides a method for predicting and dispatching power loads, which includes steps S10 to S50:

[0047] Step S10, obtaining garbage filling data of each compression garbage truck in the target area, and selecting corresponding comprehensive compression characteristic parameters from a pre-established compression model database according to the running track of the compression garbage truck;

[0048] Step S20, calculating the optimal compression frequency according to the garbage filling data and the comprehensive compression characteristic parameters, and obtaining the estimated power consumption curve of each compression garbage truck according to the compression power parameters, the running trajectory and the optimal compression frequency of the compression garbage truck;

[0049] Step S30, gridding the target area, calculating the distribution density of the compressed garbage trucks in each grid according to the running tracks of each compressed garbage truck, and obtaining a charging demand distribution heat map of each grid according to the distribution density and the estimated power consumption curve;

[0050] Step S40, predicting the facility load of each charging facility according to the geographical location of the charging facilities in the target area and the charging demand distribution heat map to obtain a predicted load of the charging facilities;

[0051] Step S50, constructing an optimization scheduling model according to the battery power, operation trajectory, estimated power consumption curve, garbage filling data and geographical location, real-time load and predicted load of the compressed garbage truck, and iterating the optimization scheduling model to obtain the optimal scheduling strategy.

[0052] The present invention provides a method for load prediction of charging facilities and vehicle charging scheduling management of electric compression garbage trucks. In this embodiment, before scheduling and controlling the compression garbage truck, a mapping relationship between garbage types and compression characteristics is first established according to the compression characteristics of different types of garbage, and a compression model database is constructed according to the garbage composition structure of the target area. The specific steps of constructing the compression model database include:

[0053] Perform compression tests on different types of garbage samples to obtain compression characteristic parameters and water content influence coefficients of each type of garbage sample, wherein the compression characteristic parameters include compression ratio and rebound coefficient, and the water content influence coefficient includes compression influence coefficient and rebound influence coefficient;

[0054] According to the historical garbage data of each functional area in the target area, the garbage composition structure of each functional area is determined, and the comprehensive compression characteristic parameters of each functional area are calculated according to the garbage composition structure and the compression characteristic parameters. According to the functional areas, the comprehensive compression characteristic parameters and the water content influence coefficient, a compression model database is constructed.

[0055] In this embodiment, compression test is performed on various types of garbage samples to determine the compression characteristic parameters of the garbage. Specifically, a compression mechanism is used to apply multiple pressure levels to different types of garbage samples, and the initial volume, compressed volume and rebound volume under each pressure level are recorded to calculate the compression ratio and rebound coefficient of each type of garbage, thereby determining the mapping relationship between garbage type and compression characteristics. In addition, this embodiment also takes into account the influence of garbage moisture content on compression characteristics, and determines the influence coefficient of moisture content on compression through moisture compression test, that is, the moisture content of the garbage is monitored through a humidity sensor, and through moisture compression test, it is determined that the moisture content is inversely proportional to the compression ratio and the rebound coefficient, respectively. For example, through moisture compression test, it is determined that when the moisture content of a certain type of garbage increases by 10%, the compression ratio will decrease by 5%, while the rebound coefficient will increase by 3%, thereby calculating the moisture influence coefficient of this type of garbage, that is, the compression influence coefficient and the rebound influence coefficient are 0.95 and 1.03, respectively.

[0056] At the same time, according to the functional area division in the target area, that is, the commercial area, living area, industrial area and other functional divisions, the garbage composition structure of different functional areas is counted respectively. This is because the garbage composition structure of different functional areas will be different. For example, the proportion of plastic garbage and paper in the living area is high, while the proportion of kitchen waste in the commercial area is high, and the difference in garbage composition structure will affect the final compression characteristics. Therefore, in this embodiment, the garbage composition structure is counted according to the functional area, and the weighted calculation is performed according to the garbage composition structure, that is, the proportion of different types of garbage, and the compression characteristic parameters of the garbage to obtain the comprehensive compression characteristic parameters of the garbage corresponding to each functional area, that is, the comprehensive compression ratio and the comprehensive rebound coefficient, and then the compression model database is constructed according to the compression characteristic parameters of the garbage, the comprehensive compression characteristic parameters of these functional areas, and the water content influence coefficient. Of course, the garbage composition structure statistics can also be performed according to administrative streets or specific roads, so that the data of the compression model database is more refined. In addition, in order to facilitate the acquisition of subsequent data, in a preferred embodiment, the present invention also adds a weather module to the compression model database, and obtains external weather forecast data through the weather module, so as to perform real-time prediction and update of the water content of the garbage in the current area.

[0057] After the compression model database is constructed, when the compression garbage truck starts working, the comprehensive compression characteristic parameters corresponding to the area or the street can be extracted from the compression model database based on its running trajectory. If the current garbage moisture content is not zero based on the current weather conditions, the comprehensive compression characteristic parameters will be updated according to the garbage moisture content. At the same time, the garbage filling height and garbage filling weight in the garbage truck are collected through the ultrasonic sensor and weight sensor inside the compression garbage truck, and the garbage filling volume is calculated based on the garbage filling height, garbage filling weight and the size of the garbage compartment, and the garbage filling speed is calculated based on the change of garbage filling volume over time.

[0058] After obtaining the above data, the optimal compression frequency of the compression garbage truck is calculated according to the garbage filling data and the extracted comprehensive compression characteristic parameters. The compression frequency is the number of compression operations of the compression mechanism per unit time, so as to predict the power consumption of the compression garbage truck. The specific steps include:

[0059] Inputting the garbage filling data and the comprehensive compression characteristic parameters into a pre-established frequency prediction model to obtain an optimal compression frequency, and adjusting the current compression frequency of the compression garbage truck according to the optimal compression frequency, wherein the frequency prediction model is constructed using a gradient boosting tree algorithm;

[0060] The operation trajectory of the compression garbage truck and the compression power parameters of the compression mechanism are obtained, and the compression power parameters, the operation trajectory and the optimal compression frequency are input into a pre-established power consumption association model to obtain an estimated power consumption curve of each compression garbage truck. The power consumption association model is constructed using the ARIMA algorithm.

[0061] This embodiment can be divided into two steps. The first step is to calculate the optimal compression frequency of the compression garbage truck, and the second step is to predict the power consumption of the compression garbage truck based on the calculated optimal compression frequency. Among them, the optimal compression frequency is calculated based on the frequency prediction model, and the frequency prediction model is constructed using the gradient boosting tree algorithm. The training data set is obtained by integrating the compression characteristic parameters, garbage filling data and compression frequency. In this embodiment, the construction of the model can be obtained by conventional construction methods, which will not be repeated here and in the following.

[0062] After the frequency prediction model is constructed, the garbage filling data and comprehensive compression characteristic parameters acquired in real time are input into the model, and the output is the predicted optimal compression frequency. The garbage filling data here include the garbage filling amount and the garbage filling speed, and the comprehensive compression characteristic parameters include the comprehensive compression ratio and the comprehensive rebound coefficient updated based on the water content influence coefficient. Furthermore, if the predicted optimal compression frequency deviates from the currently set compression frequency by more than a preset value, the compression frequency of the garbage truck is updated and set according to the deviation. Preferably, multiple threshold levels can be set. If the predicted compression frequency deviates from the currently set compression frequency by more than a preset threshold, different degrees of adjustment are taken according to the deviation size, and an exponential smoothing algorithm is introduced to smooth the adjustment result to avoid fluctuations caused by frequent adjustments, and finally the compression frequency setting of the compression mechanism of the compression garbage truck is automatically updated.

[0063] The second step is to predict the power consumption of the compressed garbage truck based on the optimal compression frequency obtained in the first step and the constructed power consumption association model. Specifically, firstly, the operating frequency, running trajectory, battery capacity, compression time, ambient temperature and garbage filling amount of the compressed garbage truck are obtained through historical data and simulation models, and converted into a structured time series data set. After data preprocessing such as missing value filling, outlier identification and data smoothing, the ARIMA algorithm is used to construct the association model between compression frequency and power consumption rate, and the parameters of the association model are optimized through maximum likelihood estimation to obtain the power consumption association model. Then, the optimal compression frequency, running trajectory and compression power parameters of the compressed garbage truck are input into the power consumption association model to predict the power consumption rate of the compressed garbage truck, so as to draw the estimated power consumption curve of the compressed garbage truck.

[0064] After obtaining the estimated power consumption curve of the compressed garbage truck, combined with the running trajectory of the compressed garbage truck, the charging demand of the target area can be analyzed. The specific steps include:

[0065] Using a hexagonal grid partitioning algorithm to grid the target area to obtain a grid data structure, wherein the grid data structure includes a grid number and grid boundary coordinates;

[0066] According to the running tracks of each compressed garbage truck, the compressed garbage truck is allocated to each grid, and according to the grid area of ​​each grid, the distribution density of the compressed garbage truck in each grid is obtained;

[0067] According to the estimated power consumption curve, the charging demand value of each compressed garbage truck is calculated, and according to the operation trajectory and the charging demand value, a spatiotemporal charging demand point data set is generated, and according to the spatiotemporal charging demand point data set, a charging demand distribution heat map of each grid is obtained.

[0068] In this embodiment, the target area is gridded, the distribution density of compressed garbage trucks in each grid is calculated, and the charging demand distribution heat map of each grid is obtained by combining the estimated power consumption curve obtained above. Specifically, based on the functional division or administrative division of the target area and the preset grid parameters, the target area is gridded using a hexagonal grid division algorithm to obtain a grid data structure containing grid numbers and grid boundary coordinates; then, the compressed garbage truck is determined to which grid the compressed garbage truck belongs according to its running trajectory. If the running trajectory of a compressed garbage truck covers two or more grid areas, the grid belonging to the compressed garbage truck is determined according to the proportion of the running trajectory in each grid and the weight of different trajectory stages; after the compressed garbage truck is assigned, the distribution density of the compressed garbage truck in each grid is calculated according to the grid area of ​​each grid. At the same time, according to the power consumption curve of the compressed garbage truck, the charging demand value of the compressed garbage truck is calculated. The charging demand value can be expressed per hour. The charging demand value is combined with the running trajectory to generate a spatiotemporal charging demand point data set with spatiotemporal characteristics. Then, the inverse distance weighted interpolation algorithm is used to perform spatial interpolation on the charging demand point dataset, and the interpolation result of each grid center point is calculated; regular grid data covering the target area is generated based on the interpolation results, and the interpolation results are normalized and converted into color values ​​to obtain a heat map of the battery charging demand distribution every hour within 24 hours.

[0069] Based on the charging demand distribution heat map and in combination with the geographical location of each charging facility in the target area, the facility load of each charging facility is predicted. The specific steps include:

[0070] Constructing a charging simulation model according to the geographical location of charging facilities in the target area and the charging demand distribution heat map;

[0071] According to the simulation results of the charging simulation model, the predicted load of the charging facility is obtained.

[0072] In this embodiment, the service range of the charging facility is generated according to the geographic coordinate information of the charging facility and the preset service radius, the charging demand curve is generated according to the charging demand distribution heat map, and a discrete time simulation model of the charging facility service process, namely the charging simulation model, is constructed according to the service range and the charging demand curve. The charging simulation model includes the entire process of the arrival of the compressed garbage truck, queue management and charging service. Based on the simulation results, the number of service vehicles of the charging facility, the average waiting time and the charging completion rate, and the fault conditions of the charging facility in each time period can be obtained. The facility load of each charging facility in each time period is predicted according to the simulation results, and the load curve is drawn and the load curve is smoothed by the moving average method to identify the peak and valley distribution of the load change, thereby predicting the load change law of the charging facility.

[0073] The reason why the power consumption of compressed garbage trucks and the charging load of charging facilities are predicted in the present invention is to optimize the charging scheduling of compressed garbage trucks through these predicted data. In conventional scheduling, the current location of the vehicle is not taken into consideration, but the charging scheduling of compressed garbage trucks is carried out completely according to the pre-set location. This method will cause uneven facility loads of various charging facilities and affect the working efficiency of vehicle operation. Whether to charge is also manually judged by sanitation personnel based on the current vehicle power, and there is a lack of refined management of vehicle power. In order to solve this problem, the present invention constructs an optimization scheduling model based on the estimated power consumption curve of the compressed garbage truck and the predicted load of the charging facility obtained above, and combines the battery power, operation trajectory of the compressed garbage truck, and the geographical location and real-time load of the charging facility, so as to optimize and regulate the charging scheduling of the compressed garbage truck. The specific steps include:

[0074] According to the battery power, running trajectory, estimated power consumption curve, and garbage filling data of the compacting garbage truck, a preset battery exhaustion risk prediction model is used to evaluate the battery exhaustion risk of the compacting garbage truck to obtain a battery exhaustion risk value;

[0075] Taking the maximization of the working efficiency of the compressed garbage truck as the objective function, and the battery power, running trajectory, battery exhaustion risk value of the compressed garbage truck and the geographical location, real-time load, and predicted load of the charging facilities as constraints, an optimization scheduling model based on multiple vehicle objectives is constructed;

[0076] The optimization scheduling model is iteratively solved using a greedy algorithm to obtain an optimal scheduling strategy, which includes charging time, charging location, and charging duration.

[0077] In this embodiment, the battery depletion risk value of the compressed garbage truck is first calculated by using a preset battery depletion risk prediction model, wherein the battery depletion risk prediction model is constructed using a random forest algorithm, and the data set consists of the battery power, operating trajectory, garbage filling amount, and geographical location and load level of the charging facilities of the compressed garbage truck. By inputting data such as the battery power, operating trajectory, estimated power consumption curve, and garbage filling data of the compressed garbage truck into the battery depletion risk prediction model, the probability of battery depletion of the compressed garbage truck within a preset time period can be obtained, thereby obtaining the battery depletion risk value.

[0078] In order to reduce the amount of calculation and improve the scheduling efficiency, in this embodiment, only for the compressed garbage trucks whose battery depletion risk value is greater than the risk threshold, the scheduling calculation will be performed through the optimization scheduling model. Specifically, the maximization of the working efficiency of the compressed garbage truck is taken as the objective function, and the battery power, operation trajectory, battery depletion risk value and the geographical location, real-time load and predicted load of the compressed garbage truck are taken as constraints to construct an optimization scheduling model based on multiple vehicle objectives. The constraints include that the battery power should be greater than or equal to the safe power and less than or equal to the maximum power, the operation trajectory is within the preset trajectory range, the battery depletion risk value is sorted by size as the scheduling constraint, the geographical location of the selected charging facility should be in the grid to which the compressed garbage truck belongs, the grid covered by the operation trajectory and the adjacent grid, and the real-time load should be less than the maximum load, the predicted load should be less than the load threshold, etc. It should be noted that only preferred constraints are given here rather than complete restrictions, and the specific constraints can be flexibly set according to actual conditions.

[0079] Based on the above-mentioned optimization scheduling model of multiple vehicle objectives, this embodiment uses a greedy algorithm to iteratively calculate the model, so as to obtain the optimal scheduling strategy for the compressed garbage truck. The optimal scheduling strategy here includes charging time, charging address and charging duration. For example, the current battery power of a compressed garbage truck is 75%, and the risk value of battery exhaustion within the preset time is 45%. Since the risk value is greater than the threshold of 35%, the compressed garbage truck participates in the scheduling control. The greedy algorithm is used to iteratively calculate the running trajectory of the compressed garbage truck, the battery power, the geographical location of the charging facility, the real-time load and the predicted load. Among the charging facilities, there is a charging facility with a real-time load of 60%, and the predicted load after 2 hours drops to 40%, and the geographical location is the nearest neighbor to the compressed garbage truck after 2 hours. The optimal charging plan obtained by the greedy algorithm is: it is recommended that the compressed garbage truck go to the above-mentioned charging facility for charging after 2 hours, and the charging time is 40 minutes. The optimal charging plan will be sent to the corresponding compressed garbage truck and charging facility respectively. During the scheduling execution process, if an emergency occurs, such as a failure of the charging facility, the scheduling plan will be re-performed to ensure the efficient operation of the compressed garbage truck and avoid the risk of power exhaustion.

[0080] The present embodiment provides a method for predicting and scheduling power loads. By analyzing the compression characteristics of different types of garbage and the garbage composition structure of a target area, optimal control of the compression frequency of a compressed garbage truck is achieved. The power consumption of the compressed garbage truck is accurately estimated according to the optimal compression frequency, thereby achieving precise analysis of the charging demand of the target area. The present invention optimizes and schedules the charging of the compressed garbage truck based on the power consumption of the compressed garbage truck and the charging demand distribution of the target area, thereby improving the working efficiency of the compressed garbage truck, achieving refined management of the vehicle power of the compressed garbage truck, and further ensuring the efficient operation of urban sanitation work.

[0081] See also Figure 2 Based on the same inventive concept, a power load forecasting and dispatching system proposed in the second embodiment of the present invention includes:

[0082] The data acquisition module 10 is used to acquire the garbage filling data of each compression garbage truck in the target area, and select the corresponding comprehensive compression characteristic parameters from the pre-established compression model database according to the running track of the compression garbage truck;

[0083] The power consumption estimation module 20 is used to calculate the optimal compression frequency according to the garbage filling data and the comprehensive compression characteristic parameters, and obtain the estimated power consumption curve of each compression garbage truck according to the compression power parameter, operation trajectory and the optimal compression frequency of the compression garbage truck;

[0084] The charging demand estimation module 30 is used to divide the target area into grids, calculate the distribution density of the compressed garbage trucks in each grid according to the running tracks of each compressed garbage truck, and obtain the charging demand distribution heat map of each grid according to the distribution density and the estimated power consumption curve;

[0085] A charging load prediction module 40, configured to predict the facility load of each charging facility according to the geographical location of the charging facilities in the target area and the charging demand distribution heat map, and obtain a predicted load of the charging facilities;

[0086] The vehicle optimization scheduling module 50 is used to construct an optimization scheduling model based on the battery power, operation trajectory, estimated power consumption curve, garbage filling data and geographical location, real-time load and predicted load of the compressed garbage truck, and iterate the optimization scheduling model to obtain the optimal scheduling strategy.

[0087] Furthermore, the power consumption estimation module 20 is further used to input the garbage filling data and the comprehensive compression characteristic parameters into a pre-established frequency prediction model to obtain an optimal compression frequency, and adjust the current compression frequency of the compression garbage truck according to the optimal compression frequency, wherein the frequency prediction model is constructed using a gradient boosting tree algorithm;

[0088] The operation trajectory of the compression garbage truck and the compression power parameters of the compression mechanism are obtained, and the compression power parameters, the operation trajectory and the optimal compression frequency are input into a pre-established power consumption association model to obtain an estimated power consumption curve of each compression garbage truck. The power consumption association model is constructed using the ARIMA algorithm.

[0089] Furthermore, the charging demand estimation module 30 is further used to grid the target area using a hexagonal grid division algorithm to obtain a grid data structure, wherein the grid data structure includes a grid number and grid boundary coordinates;

[0090] According to the running tracks of each compressed garbage truck, the compressed garbage truck is allocated to each grid, and according to the grid area of ​​each grid, the distribution density of the compressed garbage truck in each grid is obtained;

[0091] According to the estimated power consumption curve, the charging demand value of each compressed garbage truck is calculated, and according to the operation trajectory and the charging demand value, a spatiotemporal charging demand point data set is generated, and according to the spatiotemporal charging demand point data set, a charging demand distribution heat map of each grid is obtained.

[0092] Furthermore, the vehicle optimization scheduling module 50 is also used to evaluate the battery exhaustion risk of the compressed garbage truck using a preset battery exhaustion risk prediction model according to the battery power, running trajectory, estimated power consumption curve, and garbage filling data of the compressed garbage truck to obtain a battery exhaustion risk value;

[0093] Taking the maximization of the working efficiency of the compressed garbage truck as the objective function, and the battery power, running trajectory, battery exhaustion risk value of the compressed garbage truck and the geographical location, real-time load, and predicted load of the charging facilities as constraints, an optimization scheduling model based on multiple vehicle objectives is constructed;

[0094] The optimization scheduling model is iteratively solved using a greedy algorithm to obtain an optimal scheduling strategy, which includes charging time, charging location, and charging duration.

[0095] The technical features and technical effects of the power load prediction and dispatching system proposed in the embodiment of the present invention are the same as the method proposed in the embodiment of the present invention, and will not be described in detail here. Each module in the above-mentioned power load prediction and dispatching system can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0096] In summary, an embodiment of the present invention proposes a method and system for predicting and scheduling power loads. The method obtains garbage filling data of each compressed garbage truck in a target area, and selects corresponding comprehensive compression characteristic parameters from a pre-established compression model database according to the running trajectory of the compressed garbage truck; calculates the optimal compression frequency according to the garbage filling data and the comprehensive compression characteristic parameters, and obtains the estimated power consumption curve of each compressed garbage truck according to the compression power parameter, running trajectory and the optimal compression frequency of the compressed garbage truck; divides the target area into grids, calculates the distribution density of the compressed garbage trucks in each grid according to the running trajectory of each compressed garbage truck, and obtains the charging demand distribution heat map of each grid according to the distribution density and the estimated power consumption curve; predicts the facility load of each charging facility according to the geographical location of the charging facilities in the target area and the charging demand distribution heat map to obtain the predicted load of the charging facilities; constructs an optimization scheduling model according to the battery power, running trajectory, estimated power consumption curve, garbage filling data and the geographical location, real-time load and predicted load of the compressed garbage truck, and iterates the optimization scheduling model to obtain the optimal scheduling strategy. The present invention realizes optimal control of the compression frequency of the compressed garbage truck by analyzing the compression characteristics of different types of garbage and the garbage composition structure of the target area, accurately estimates the power consumption of the compressed garbage truck according to the optimal compression frequency, and then realizes accurate analysis of the charging demand of the target area. The present invention optimizes the charging of the compressed garbage truck based on the power consumption of the compressed garbage truck and the charging demand distribution of the target area, thereby improving the working efficiency of the compressed garbage truck, realizing the refined management of the compressed garbage truck, and further ensuring the efficient operation of urban sanitation work.

[0097] Each embodiment in this specification is described in a progressive manner, and the same or similar parts of each embodiment can be directly referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. It should be noted that the technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above-mentioned embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0098] The above-mentioned embodiments only express several preferred implementation modes of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in the technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be based on the protection scope of the claims.

Claims

1. A method for predicting and dispatching power load, characterized in that: include: Obtain garbage filling data of each compression garbage truck in the target area, and select corresponding comprehensive compression characteristic parameters from a pre-established compression model database according to the running trajectory of the compression garbage truck; Calculating the optimal compression frequency according to the garbage filling data and the comprehensive compression characteristic parameters, and obtaining the estimated power consumption curve of each compression garbage truck according to the compression power parameters, the running trajectory and the optimal compression frequency of the compression garbage truck; Divide the target area into grids, calculate the distribution density of compressed garbage trucks in each grid according to the running tracks of each compressed garbage truck, and obtain a charging demand distribution heat map of each grid according to the distribution density and the estimated power consumption curve; According to the geographical location of the charging facilities in the target area and the charging demand distribution heat map, the facility load of each charging facility is predicted to obtain the predicted load of the charging facility; According to the battery power, running trajectory, estimated power consumption curve, garbage filling data and geographical location, real-time load and predicted load of the compressed garbage truck, an optimization scheduling model is constructed, and the optimization scheduling model is iteratively calculated to obtain the optimal scheduling strategy; The step of calculating the optimal compression frequency according to the garbage filling data and the comprehensive compression characteristic parameters, and obtaining the estimated power consumption curve of each compression garbage truck according to the compression power parameters, the running trajectory and the optimal compression frequency of the compression garbage truck includes: Inputting the garbage filling data and the comprehensive compression characteristic parameters into a pre-established frequency prediction model to obtain an optimal compression frequency, and adjusting the current compression frequency of the compression garbage truck according to the optimal compression frequency, wherein the frequency prediction model is constructed using a gradient boosting tree algorithm; Obtaining the running trajectory of the compression garbage truck and the compression power parameters of the compression mechanism, and inputting the compression power parameters, the running trajectory and the optimal compression frequency into a pre-established power consumption association model to obtain an estimated power consumption curve of each compression garbage truck, wherein the power consumption association model is constructed using an ARIMA algorithm; The step of dividing the target area into grids, calculating the distribution density of compressed garbage trucks in each grid according to the running tracks of each compressed garbage truck, and obtaining the charging demand distribution heat map of each grid according to the distribution density and the estimated power consumption curve includes: Using a hexagonal grid partitioning algorithm to grid the target area to obtain a grid data structure, wherein the grid data structure includes a grid number and grid boundary coordinates; According to the running tracks of each compressed garbage truck, the compressed garbage truck is allocated to each grid, and according to the grid area of ​​each grid, the distribution density of the compressed garbage truck in each grid is obtained; According to the estimated power consumption curve, the charging demand value of each compressed garbage truck is calculated, and according to the operation trajectory and the charging demand value, a spatiotemporal charging demand point data set is generated, and according to the spatiotemporal charging demand point data set, a charging demand distribution heat map of each grid is obtained.

2. The method for predicting and dispatching electric power load according to claim 1, characterized in that: The compression model database is established by the following steps: Perform compression tests on different types of garbage samples to obtain compression characteristic parameters and water content influence coefficients of each type of garbage sample, wherein the compression characteristic parameters include compression ratio and rebound coefficient, and the water content influence coefficient includes compression influence coefficient and rebound influence coefficient; According to the historical garbage data of each functional area in the target area, the garbage composition structure of each functional area is determined, and the comprehensive compression characteristic parameters of each functional area are calculated according to the garbage composition structure and the compression characteristic parameters. According to the functional areas, the comprehensive compression characteristic parameters and the water content influence coefficient, a compression model database is constructed.

3. The method for predicting and dispatching electric load according to claim 1, characterized in that: The step of predicting the facility load of each charging facility according to the geographical location of the charging facilities in the target area and the charging demand distribution heat map to obtain the predicted load of the charging facilities includes: Constructing a charging simulation model according to the geographical location of charging facilities in the target area and the charging demand distribution heat map; According to the simulation results of the charging simulation model, the predicted load of the charging facility is obtained.

4. The method for predicting and dispatching electric load according to claim 1, characterized in that: The steps of constructing an optimization scheduling model according to the battery power, operation trajectory, estimated power consumption curve, garbage filling data and geographical location, real-time load and predicted load of the compressed garbage truck, and iteratively calculating the optimization scheduling model to obtain the optimal scheduling strategy include: According to the battery power, running trajectory, estimated power consumption curve, and garbage filling data of the compacting garbage truck, a preset battery exhaustion risk prediction model is used to evaluate the battery exhaustion risk of the compacting garbage truck to obtain a battery exhaustion risk value; Taking the maximization of the working efficiency of the compressed garbage truck as the objective function, and the battery power, running trajectory, battery exhaustion risk value of the compressed garbage truck and the geographical location, real-time load, and predicted load of the charging facilities as constraints, an optimization scheduling model based on multiple vehicle objectives is constructed; The optimization scheduling model is iteratively solved using a greedy algorithm to obtain an optimal scheduling strategy, which includes charging time, charging location, and charging duration.

5. A power load forecasting and dispatching system, characterized in that: A data acquisition module is used to obtain garbage filling data of each compression garbage truck in the target area, and select corresponding comprehensive compression characteristic parameters from a pre-established compression model database according to the running trajectory of the compression garbage truck; A power consumption estimation module, used to calculate the optimal compression frequency according to the garbage filling data and the comprehensive compression characteristic parameters, and obtain an estimated power consumption curve of each compression garbage truck according to the compression power parameters, operation trajectory and the optimal compression frequency of the compression garbage truck; A charging demand estimation module is used to divide the target area into grids, calculate the distribution density of compressed garbage trucks in each grid according to the running tracks of each compressed garbage truck, and obtain a charging demand distribution heat map of each grid according to the distribution density and the estimated power consumption curve; A charging load prediction module, used to predict the facility load of each charging facility according to the geographical location of the charging facilities in the target area and the charging demand distribution heat map, so as to obtain the predicted load of the charging facilities; The vehicle optimization scheduling module is used to construct an optimization scheduling model according to the battery power, running trajectory, estimated power consumption curve, garbage filling data and geographical location, real-time load and predicted load of the compressed garbage truck, and iterate the optimization scheduling model to obtain the optimal scheduling strategy; The power consumption estimation module is further used to input the garbage filling data and the comprehensive compression characteristic parameters into a pre-established frequency prediction model to obtain an optimal compression frequency, and adjust the current compression frequency of the compression garbage truck according to the optimal compression frequency, and the frequency prediction model is constructed using a gradient boosting tree algorithm; Obtaining the running trajectory of the compression garbage truck and the compression power parameters of the compression mechanism, and inputting the compression power parameters, the running trajectory and the optimal compression frequency into a pre-established power consumption association model to obtain an estimated power consumption curve of each compression garbage truck, wherein the power consumption association model is constructed using an ARIMA algorithm; The charging demand estimation module is further used to grid the target area using a hexagonal grid division algorithm to obtain a grid data structure, wherein the grid data structure includes a grid number and grid boundary coordinates; According to the running tracks of each compressed garbage truck, the compressed garbage truck is allocated to each grid, and according to the grid area of ​​each grid, the distribution density of the compressed garbage truck in each grid is obtained; According to the estimated power consumption curve, the charging demand value of each compressed garbage truck is calculated, and according to the operation trajectory and the charging demand value, a spatiotemporal charging demand point data set is generated, and according to the spatiotemporal charging demand point data set, a charging demand distribution heat map of each grid is obtained.

6. The power load forecasting and dispatching system according to claim 5, characterized in that: The vehicle optimization scheduling module is also used to evaluate the battery depletion risk of the compressed garbage truck using a preset battery depletion risk prediction model according to the battery power, running trajectory, estimated power consumption curve, and garbage filling data of the compressed garbage truck to obtain a battery depletion risk value; Taking the maximization of the working efficiency of the compressed garbage truck as the objective function, and the battery power, running trajectory, battery exhaustion risk value of the compressed garbage truck and the geographical location, real-time load, and predicted load of the charging facilities as constraints, an optimization scheduling model based on multiple vehicle objectives is constructed; The optimization scheduling model is iteratively solved using a greedy algorithm to obtain an optimal scheduling strategy, which includes charging time, charging location, and charging duration.

Images