Mobile power supply scheduling optimization method, system and device

Abstract

The present invention discloses a mobile power scheduling optimization method, system and device. The method determines a user's time-series load trend curve through a user's power consumption monitoring log to predict the power consumption load in a future time period, and determines the spatiotemporal distribution of power shortage in the future time period based on the power load prediction data. According to the spatiotemporal distribution of power shortage and the power consumption priority of each power-scarce user, the power supply support sequence of the mobile power supply is determined, and the shortest path planning is performed on the power supply support sequence of the mobile power supply to generate a support path chain of the mobile power supply. By performing path energy consumption prediction on the support path chain of the mobile power supply, the support path chain of the mobile power supply is optimized according to the path energy consumption prediction result, so that the remaining charge of the mobile power supply meets the path energy consumption prediction result. The remaining unexecuted energy consumption support path chains are also optimized in real time according to the minimum power load of each power-scarce user, thereby improving the energy storage resource utilization rate of the mobile power supply.

Description

Technical Field

[0001] The present invention relates to the technical field of mobile power supplies, and in particular to a method, system and device for optimizing mobile power supply scheduling. Background Art

[0002] With the popularity of mobile devices and the widespread use of various smart devices, the demand for electricity is increasing. While traditional power supply methods can meet most of this demand, the diversification of user needs, geographical dispersion, and sudden power shortages have gradually exposed the shortcomings of traditional power grids and fixed energy storage devices in terms of flexibility, efficiency, and emergency response. Therefore, developing a self-propelled energy storage power source that can intelligently dispatch and plan routes based on the user's multi-objective needs has become an important technical direction for improving power supply efficiency, ensuring power safety, and reducing energy consumption.

[0003] As an emerging energy transmission system, self-propelled energy storage power supplies are characterized by their ability to dynamically adjust their location and flexibly provide power support based on changing demand. Compared to traditional static energy storage devices, self-propelled energy storage power supplies not only address the spatial limitations of power supply but also optimize power supply based on real-time demand changes. However, current mobile power supply scheduling methods struggle to provide timely and effective power support to users, and the utilization rate of mobile power supply storage resources is poor, resulting in wasted power resources. Summary of the Invention

[0004] In view of this, the present invention provides a mobile power scheduling optimization method, system and device to solve the technical problems in the current mobile power scheduling, such as the difficulty in providing power support to users in a timely and effective manner, the poor utilization rate of the mobile power storage resources, and the waste of power resources.

[0005] A first aspect of the present invention provides a mobile power scheduling optimization method, comprising:

[0006] Obtaining user electricity consumption monitoring logs within the target dispatching area, and determining user time series load trend curves based on the user electricity consumption monitoring logs;

[0007] Predicting the electricity load for a future period based on the user time-series load trend curve to obtain electricity load prediction data, and determining the spatiotemporal distribution of electricity shortages within the future period based on the electricity load prediction data; wherein the spatiotemporal distribution of electricity shortages is used to characterize the geographical distribution of each electricity shortage user in each period within the future period;

[0008] Determining a power supply support sequence for the mobile power source based on the temporal and spatial distribution of power shortages and the power priority of each power-scarce user; wherein the power supply support sequence for the mobile power source is a user support order generated from high to low based on the power priority of each power-scarce user;

[0009] Performing shortest path planning on the power supply support sequence of the mobile power source to generate a support path chain of the mobile power source;

[0010] Performing a path energy consumption prediction on the support path chain of the mobile power supply, and optimizing the support path chain of the mobile power supply according to the path energy consumption prediction result to obtain an energy consumption support path chain in which the remaining charge of the mobile power supply satisfies the path energy consumption prediction result;

[0011] During the process of the mobile power supply performing real-time mobile power support according to the energy consumption support path chain, the remaining unexecuted energy consumption support path chains are optimized according to the minimum power load of each of the power-scarce users, and real-time mobile power support is continued to be performed for the remaining power-scarce users according to the optimized energy consumption support path chains.

[0012] Preferably, obtaining the user electricity consumption monitoring log in the target dispatching area and determining the user time series load trend curve according to the user electricity consumption monitoring log includes:

[0013] Obtain user electricity consumption monitoring logs within the target dispatching area;

[0014] Filtering the user's electricity consumption monitoring log to generate a filtered and optimized electricity consumption monitoring log;

[0015] Identify all electricity users in the filtered and optimized electricity monitoring log, and calculate the real-time electricity load of each electricity user to obtain the real-time electricity load parameters of each user;

[0016] Calculate the transient load change of each user's real-time power load parameters and generate the transient load change value of each user at multiple time points;

[0017] The load characteristics of the transient load change values ​​of each user at multiple time points are extracted, and time series fitting is performed based on the load characteristics and the power consumption cycle pattern to obtain the user time series load trend curve.

[0018] Preferably, predicting the power load in a future period based on the user time series load trend curve to obtain power load prediction data, and determining the spatiotemporal distribution of power shortage in the future period based on the power load prediction data includes:

[0019] Performing a power consumption cycle pattern analysis on the real-time power load parameters of each user to obtain a power consumption cycle pattern for each user; wherein the power consumption cycle pattern is used to characterize the periodic regularity of the user's power consumption behavior changing over time;

[0020] Performing power load forecasting for future periods on the user's time series load trend curve according to the power consumption cycle pattern to obtain power load forecast data for each user;

[0021] Based on the electricity load forecast data of each user, the electricity demand characteristics of each user in the future period are determined, and the electricity demand characteristics of each user in the future period are clustered to identify the electricity demand characteristics of each user in different time periods;

[0022] The spatiotemporal distribution of power shortage is fitted according to the power demand characteristics of each user in different time periods to obtain the spatiotemporal distribution of power shortage in the future time period.

[0023] Preferably, fitting the spatiotemporal distribution of power shortage according to the power demand characteristics of each user in different time periods to obtain the spatiotemporal distribution of power shortage in the future time period includes:

[0024] Determine the power supply load peaks corresponding to the target dispatching area in multiple time periods according to the user power consumption monitoring log;

[0025] Determine the power demand deviation of each user in different time periods based on the power supply load peaks and power demand characteristics corresponding to multiple time periods;

[0026] Determine power-shortage users and power-shortage periods for the power-shortage users based on the power supply demand deviation of each user;

[0027] Determine the spatial distribution of power-scarce users based on the geographical locations of the power-scarce users within the target dispatching area;

[0028] According to the power shortage period, the spatial distribution of the power shortage users is mapped throughout a future period to obtain the spatiotemporal distribution of power shortage in the future period.

[0029] Preferably, determining the power supply support sequence of the mobile power source according to the temporal and spatial distribution of power shortage and the power priority of each power shortage user includes:

[0030] Determine the power urgency of each power-scarce user based on their power demand characteristics and types;

[0031] Determine the actual power demand difference value of each power-scarce user based on the power demand characteristics and actual power load of each power-scarce user;

[0032] Determine the power demand emergency value of each power-scarce user based on the power demand emergency degree of each power-scarce user and the actual power demand emergency difference value;

[0033] Compare the power demand urgency value of each power-scarce user with multiple preset priority thresholds to determine the power priority of each power-scarce user;

[0034] Based on the power priority of each power-scarce user, a power supply sequence is planned for each power-scarce user within the power-scarce spatiotemporal distribution, and a mobile power supply support sequence is constructed.

[0035] Preferably, performing the shortest path planning on the power supply support sequence of the mobile power source to generate the support path chain of the mobile power source includes:

[0036] Performing three-dimensional environmental modeling on the three-dimensional environmental data and environmental obstacle data of the target dispatching area to obtain a three-dimensional environmental structure map of the target dispatching area; wherein the three-dimensional environmental structure map includes distance information between various power-scarce users;

[0037] Based on the path planning algorithm, according to the distance information between each power-scarce user, the shortest path planning is performed for multiple power-scarce users to obtain the support path chain of the mobile power supply under the multiple power-scarce users.

[0038] Preferably, performing path energy consumption prediction on the support path chain of the mobile power supply, optimizing the support path chain of the mobile power supply according to the path energy consumption prediction result, and obtaining an energy consumption support path chain in which the remaining charge of the mobile power supply satisfies the path energy consumption prediction result, includes:

[0039] Calculating the full moving slope of the support path chain to generate the full moving slope of the support path chain;

[0040] Predicting the path energy consumption of the mobile power source according to the full moving slope to obtain a predicted energy consumption value of the mobile power source;

[0041] Obtaining the remaining charge of the mobile power supply in real time;

[0042] Determining whether the remaining charge is less than the energy consumption prediction value;

[0043] If it is determined that the remaining charge is less than the energy consumption prediction value, readjusting the support path chain to obtain an updated support path chain;

[0044] Based on the updated support path chain, the full-range moving slope calculation of the support path chain is performed again to generate the full moving slope of the support path chain until the remaining charge amount is not less than the energy consumption prediction value, thereby obtaining the energy consumption support path chain.

[0045] Preferably, during the process of the mobile power supply performing the real-time mobile power support according to the energy consumption support path chain, the remaining unexecuted energy consumption support path chains are optimized according to the minimum power load of each of the power-scarce users, and the real-time mobile power support is continued to be performed for the remaining power-scarce users according to the optimized energy consumption support path chains, including:

[0046] During the process of the mobile power supply performing the real-time mobile power support according to the energy consumption support path chain, obtaining in real time the real-time power load of the power-scarce user being supported by the mobile power supply;

[0047] Comparing the real-time power load with the lowest power load of the power-scarce user;

[0048] When the real-time power load is greater than the minimum power load, the power priority of the power-scarce user is updated and lowered by one level, and the remaining unexecuted energy consumption support path chain is readjusted according to the updated power priority of the power-scarce user;

[0049] Control the mobile power supply to continue to perform real-time mobile power support for the remaining power-shortage users according to the readjusted remaining unexecuted energy consumption support path chain, and switch to the process of the mobile power supply performing real-time mobile power support according to the energy consumption support path chain, and obtain the real-time power load of the power-shortage users being supported by the mobile power supply in real time until all power-shortage users have completed the real-time mobile power support.

[0050] In a second aspect, the present invention further provides a mobile power scheduling optimization system, comprising:

[0051] A load trend determination module is used to obtain user power consumption monitoring logs in the target dispatching area and determine user time series load trend curves based on the user power consumption monitoring logs;

[0052] A power shortage distribution module is configured to predict the power load in a future time period based on the user time-series load trend curve, obtain power load prediction data, and determine the spatiotemporal distribution of power shortage in the future time period based on the power load prediction data; wherein the spatiotemporal distribution of power shortage is used to characterize the geographical distribution of each power shortage user in each time period in the future time period;

[0053] a power supply support determination module, configured to determine a power supply support sequence for the mobile power source based on the spatiotemporal distribution of power shortages and the power priority of each power shortage user; wherein the power supply support sequence for the mobile power source is a user support order generated from high to low based on the power priority of each power shortage user;

[0054] a support path planning module, configured to perform shortest path planning on the power supply support sequence of the mobile power source and generate a support path chain for the mobile power source;

[0055] a path energy consumption optimization module, configured to perform path energy consumption prediction on the support path chain of the mobile power supply, and optimize the support path chain of the mobile power supply according to the path energy consumption prediction result to obtain an energy consumption support path chain in which the remaining charge of the mobile power supply satisfies the path energy consumption prediction result;

[0056] The path real-time optimization module is used to optimize the remaining unexecuted energy consumption support path chains according to the minimum power load of each of the power-scarce users during the process of the mobile power supply performing real-time mobile power support according to the energy consumption support path chain, and continue to perform real-time mobile power support for the remaining power-scarce users according to the optimized energy consumption support path chains.

[0057] In a third aspect, the present invention further provides an electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the mobile power scheduling optimization method as described in the first aspect.

[0058] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the steps of the mobile power scheduling optimization method as described in the first aspect.

[0059] In a fifth aspect, the present invention also provides a computer program product, comprising a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program comprises program instructions, wherein when the program instructions are executed by a computer, the computer is caused to execute the steps of the mobile power scheduling optimization method as described in the first aspect.

[0060] It can be seen from the above technical solutions that the present invention determines the user's time-series load trend curve through the user's electricity consumption monitoring log to predict the electricity load in the future period, and determines the spatiotemporal distribution of electricity shortage in the future period based on the electricity load prediction data. According to the spatiotemporal distribution of electricity shortage and the electricity priority of each electricity-scarce user, the power supply support sequence of the mobile power supply is determined, thereby ensuring that the users who are most in urgent need of electricity support receive timely power supply, and performing the shortest path planning for the power supply support sequence of the mobile power supply to generate a support path chain of the mobile power supply, thereby improving the efficiency and response speed of power dispatch and reducing the waste of power resources. By performing path energy consumption prediction on the support path chain of the mobile power supply, according to The path energy consumption prediction results optimize the support path chain of the mobile power supply so that the remaining charge of the mobile power supply meets the path energy consumption prediction results, thereby improving energy utilization efficiency and ensuring the stability of power support. In the process of real-time mobile power support by the mobile power supply, the remaining unexecuted energy consumption support path chain is optimized according to the minimum power load of each power-scarce user. Through minimum power load analysis, it can ensure that the minimum power demand of each user is always met, and respond to changes in the needs of different users in real time, make fast and accurate adjustments, improve the utilization rate of the mobile power supply's energy storage resources, avoid waste of power resources, and ensure the stability and reliability of power supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0062] Figure 1 A diagram illustrating an application environment of a mobile power supply scheduling optimization method provided by an embodiment of the present invention;

[0063] Figure 2 A flowchart of a mobile power supply scheduling optimization method provided by an embodiment of the present invention;

[0064] Figure 3 A schematic diagram of the structure of a mobile power scheduling optimization system provided by an embodiment of the present invention;

[0065] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0066] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only 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 making creative efforts shall fall within the scope of protection of the present invention.

[0067] The mobile power scheduling optimization method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 101 communicates with the server 102 through the network. The data storage system can store the data that the server 102 needs to process. The data storage system can be integrated on the server 102, or it can be placed on the cloud or other network servers. The terminal 101 or the server 102 obtains the user electricity consumption monitoring log in the target dispatching area, and determines the user's time-series load trend curve based on the user's electricity consumption monitoring log; based on the user's time-series load trend curve, the electricity load in the future time period is predicted to obtain the electricity load prediction data, and based on the electricity load prediction data, the temporal and spatial distribution of electricity shortage in the future time period is determined; wherein, the temporal and spatial distribution of electricity shortage is used to characterize the geographical distribution of each electricity-shortage user in each time period in the future time period; according to the temporal and spatial distribution of electricity shortage and the electricity priority of each electricity-shortage user, the power supply support sequence of the mobile power supply is determined; wherein, the power supply support sequence of the mobile power supply is based on the electricity priority of each electricity-shortage user. The user support sequence is generated from high to low priority; the shortest path planning is performed on the power supply support sequence of the mobile power supply to generate the support path chain of the mobile power supply; the path energy consumption of the support path chain of the mobile power supply is predicted, and the support path chain of the mobile power supply is optimized according to the path energy consumption prediction result to obtain the energy consumption support path chain in which the remaining charge of the mobile power supply meets the path energy consumption prediction result; in the process of the mobile power supply executing real-time mobile power support according to the energy consumption support path chain, the remaining unexecuted energy consumption support path chains are optimized according to the minimum power load of each power-scarce user, and the real-time mobile power support is continued to be executed for the remaining power-scarce users according to the optimized energy consumption support path chain.

[0068] The terminal 101 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and the like.

[0069] The server 102 may be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0070] like Figure 2 As shown, the embodiment of the present application provides a mobile power scheduling optimization method, which is applied to Figure 1The terminal 101 or the server 102 in the embodiment is used as an example to illustrate the method, which includes the following steps S1 to S6.

[0071] Step S1: Obtain user power consumption monitoring logs within the target dispatching area, and determine user time series load trend curves based on the user power consumption monitoring logs.

[0072] The target dispatch area refers to a specific power supply area where mobile power dispatch optimization is required. This area typically includes multiple users, and each user's electricity usage is recorded in a user electricity monitoring log. This log details each user's electricity usage over different time periods. The user time-series load trend curve is a graph that analyzes and summarizes this electricity usage data, reflecting the changes in user electricity usage over time. This curve can intuitively demonstrate the fluctuations and periodic patterns of user electricity usage.

[0073] In this embodiment, the sources of user electricity consumption monitoring logs generally include: smart meters, distribution system monitoring, and user-end devices. In order to ensure that these devices can provide high-frequency real-time electricity consumption data, it is generally recommended to collect data at a frequency of once per minute to capture instantaneous load changes. Use a data acquisition system (such as a data logger, IoT platform, etc.) to collect electricity consumption data in the area from various monitoring points. Electricity consumption data should include timestamps, electricity load (such as kilowatt-hours), and device characteristics (such as user ID, device type, etc.). Store the collected electricity consumption monitoring logs in a centralized database. Select a suitable database management system (such as an SQL database or a NoSQL database) to ensure that the data can be quickly queried and efficiently managed. Data should be organized by timestamp to facilitate subsequent real-time analysis. Ensure data integrity and consistency, and perform data backup and integrity verification regularly.

[0074] Step S2: predict the electricity load in the future time period based on the user's time-series load trend curve to obtain electricity load prediction data, and determine the spatiotemporal distribution of electricity shortage in the future time period based on the electricity load prediction data; wherein the spatiotemporal distribution of electricity shortage is used to characterize the geographical distribution of each electricity shortage user in each time period in the future time period.

[0075] Select an appropriate forecasting model based on the user's time-series load trend curve. Common models include time series analysis models (such as ARIMA and SARIMA), machine learning models (such as support vector machines and random forests), and deep learning models (such as long short-term memory networks (LSTMs). These models use the user's time-series load trend curve to predict future electricity load.

[0076] When selecting a model, the linear and nonlinear characteristics of the data should be considered. Determine the model parameter settings, such as the order of the time series model, the feature selection of the machine learning model, and the network structure of the deep learning model, to ensure the accuracy of the model. Before performing load forecasting, preprocess the user's time series load trend curve, including removing outliers, smoothing, and normalization. Use the sliding average method or exponential smoothing method to process the data to eliminate short-term fluctuations and extract long-term trends. Record each step of the preprocessing to facilitate subsequent analysis and model verification. Use a verified load forecasting model to predict the electricity load for future time periods. Based on the user's historical electricity consumption data, generate a forecast value for the electricity load for a period of time in the future (such as the next 24 hours, 48 ​​hours).

[0077] Record the predicted values ​​for each time period and compare them with the actual load to verify the model's accuracy. Visualize the predicted results to generate a predicted load curve to visually illustrate future load trends. Comparing actual and predicted loads ensures the model's reliability. Store the predicted results in a database to facilitate subsequent analysis and processing.

[0078] Among them, the definition of electricity shortage is usually determined by the user's electricity load being lower than a certain threshold (such as the minimum electricity load).

[0079] The spatiotemporal distribution of power shortages describes power shortages based on time and location, identifying which users or regions are likely to experience power loads below the minimum load in the future. This distribution information is generated by comprehensively considering power load forecast data and the geographic distribution of power-scarce users, clearly demonstrating the severity and distribution of power shortages. Based on the spatiotemporal distribution of power shortages, targeted mobile power scheduling strategies can be developed to ensure that mobile power supplies can provide timely and effective power support to power-scarce users during power shortage periods.

[0080] Step S3: Determine the power supply support sequence of the mobile power source based on the temporal and spatial distribution of power shortages and the power priority of each power-scarce user; wherein the power supply support sequence of the mobile power source is a user support order generated from high to low based on the power priority of each power-scarce user.

[0081] The priority of power-scarce users is determined based on factors such as their power load, historical power usage patterns, power supply capacity, and the severity of the power shortage period. Users with higher power priorities generally have more urgent power needs or occupy a more critical position in the power system. Therefore, when mobile power resources are limited, the power needs of these users should be met first.

[0082] The power supply support sequence is generated based on the power demand priority of power-scarce users, from high to low. This sequence ensures that the mobile power supply can provide power support to power-scarce users in order of priority.

[0083] By combining the temporal and spatial distribution of power shortages and the power priorities of each power-scarce user, a power supply support sequence that meets the power priorities is generated. Each power-scarce user in the power supply support sequence is accompanied by its corresponding geographical location.

[0084] The allocation of mobile power supplies can be more effectively scheduled and optimized, ensuring that the needs of high-priority users are prioritized during the power supply process, and guaranteeing the timeliness and effectiveness of power support. In specific implementation, mobile power supplies can be dispatched one by one to power-starved users according to the power supply support sequence, and real-time mobile power support can be performed according to the readjusted remaining unexecuted energy consumption support path chain. During this process, the system will also obtain and update the real-time power load of power-starved users in real time, so that the support path can be optimized immediately based on the latest power consumption situation, ensuring the maximum efficiency of mobile power supply and support effect.

[0085] Step S4: perform shortest path planning on the power supply support sequence of the mobile power source to generate a support path chain of the mobile power source.

[0086] The support path chain is based on the geographic locations of power-demanding users in the power supply support sequence. A path planning algorithm (such as Dijkstra or A*) is used to calculate the shortest path from the power bank's current location to each power-demanding user. These shortest paths are sequentially connected to form a support path chain, which allows the power bank to sequentially support each power-demanding user. The generation of the support path chain takes into account the power bank's mobility efficiency and path optimization, ensuring that the power bank can reach each power-demanding user as quickly as possible within a limited timeframe, providing timely power support. Furthermore, the generation of the support path chain also takes into account actual road conditions, traffic congestion, and other factors to ensure that the power bank can successfully reach each user in need of support along the planned path.

[0087] Step S5: perform path energy consumption prediction on the support path chain of the mobile power supply, optimize the support path chain of the mobile power supply according to the path energy consumption prediction result, and obtain an energy consumption support path chain in which the remaining charge of the mobile power supply meets the path energy consumption prediction result.

[0088] Path energy consumption prediction is based on the energy consumption required by the mobile power bank to travel along the support path chain. This includes the distance the mobile power bank will travel and road conditions (such as slope). This path energy consumption prediction estimates the energy required by the mobile power bank before reaching each power-starved user, thereby determining whether its remaining charge is sufficient to complete the entire support mission.

[0089] Optimizing the support path chain of the mobile power supply based on the path energy consumption prediction results is necessary to ensure that the mobile power supply can successfully complete the task according to the planned path.

[0090] In the energy support path chain, the location of each power-starved user and the order in which they will be supported by power banks are determined. The power bank's energy consumption during movement is also considered to ensure the remaining charge in the power bank can meet the needs of the entire support mission. This optimization process not only improves the efficiency of power banks but also ensures the timeliness and reliability of power support. During implementation, the system dispatches power banks in real time based on the energy support path chain, sending them to each power-starved user along the planned route to provide power support.

[0091] Step S6: When the mobile power supply performs real-time mobile power support according to the energy consumption support path chain, the remaining unexecuted energy consumption support path chains are optimized according to the minimum power load of each power-scarce user, and real-time mobile power support is continued to be performed for the remaining power-scarce users according to the optimized energy consumption support path chains.

[0092] During real-time mobile power support, the system continuously monitors the real-time power load of each power-starved user and compares it with a pre-set minimum load. If a user's real-time load falls below the minimum, the system immediately triggers an optimization mechanism to re-evaluate the support order for that user. This dynamic optimization process ensures that the power bank can flexibly adjust its support strategy based on actual power usage, prioritizing users with more urgent power needs. This allows for immediate adjustment and optimization of support paths based on the latest situation, ensuring maximum power bank efficiency and support effectiveness.

[0093] During implementation, the system comprehensively optimizes the remaining unexecuted energy support paths based on the real-time power load of each power-hungry user, the remaining charge of the power bank, and the predicted path energy consumption. This optimized path not only considers the mobility efficiency and energy consumption of the power bank, but also fully incorporates the user's real-time power needs, ensuring the accuracy and efficiency of power support.

[0094] Following the optimized energy support path chain, the power bank will continue to provide power support to the remaining power-starved users. During the support process, the system will continuously record the power bank's usage and the user's power consumption data, providing data support for subsequent analysis and optimization. At the same time, the system will also make real-time adjustments to the support path based on real-time traffic and road conditions to ensure that the power bank can successfully reach every user in need.

[0095] It should be noted that the embodiment of the present application determines the user's time-series load trend curve through the user's electricity consumption monitoring log to predict the electricity load in the future time period, and determines the temporal and spatial distribution of electricity shortage in the future time period based on the electricity load prediction data. According to the temporal and spatial distribution of electricity shortage and the electricity priority of each electricity-shortage user, the power supply support sequence of the mobile power supply is determined, thereby ensuring that the users who are most in need of electricity support receive timely power supply, and performing the shortest path planning for the power supply support sequence of the mobile power supply to generate a support path chain of the mobile power supply, thereby improving the efficiency and response speed of power dispatch and reducing the waste of power resources. By performing path energy consumption prediction on the support path chain of the mobile power supply, according to the path The support path chain of the mobile power supply is optimized based on the path energy consumption prediction results, so that the remaining charge of the mobile power supply meets the path energy consumption prediction results, thereby improving the energy utilization efficiency and ensuring the stability of power support. In the process of real-time mobile power support by the mobile power supply, the remaining unexecuted energy consumption support path chain is optimized according to the minimum power load of each power-scarce user. Through the analysis of the minimum power load, it can ensure that the minimum power demand of each user is always met, and respond to changes in the needs of different users in real time, make fast and accurate adjustments, improve the utilization rate of the energy storage resources of the mobile power supply, avoid the waste of power resources, and ensure the stability and reliability of the power supply.

[0096] In some embodiments, obtaining a user power consumption monitoring log in a target dispatching area and determining a user time series load trend curve based on the user power consumption monitoring log include:

[0097] Step S101: Obtain the user electricity consumption monitoring log in the target dispatching area.

[0098] In this embodiment, user electricity usage monitoring logs are extracted from the regional electricity monitoring system. These logs typically include the time of use, user ID, power consumption, power factor, and other relevant parameters. Data integrity is ensured for subsequent analysis. The data collection period is recorded to ensure that it covers the required analysis period, such as daily, weekly, or monthly. The acquired monitoring logs are formatted and converted into a unified structure (such as CSV or database format), ensuring that the type of each field is consistent.

[0099] Step S102: Filter the user's electricity usage monitoring log to generate a filtered and optimized electricity usage monitoring log.

[0100] Among them, filtering processing includes filtering abnormal and repeated values, and selecting appropriate anomaly detection methods, such as the statistical-based Z-score test, IQR (interquartile range) method, or machine learning methods (such as isolation forest). These methods can effectively identify and filter out abnormal values ​​and duplicate values. Determine the parameter settings for outlier detection, such as the Z-score threshold or the multiple of the IQR, to accurately identify anomalies. Apply the selected anomaly detection method to the regional electricity consumption monitoring log to identify and filter abnormal and duplicate electricity consumption records. Ensure that only normal electricity consumption records are retained in the filtered data set. Record data changes during the filtering process, including the amount of data before and after filtering and the number of abnormal values, for subsequent analysis. Extract information of all electricity users from the electricity consumption monitoring log after filtering optimization, including user ID and electricity consumption records. Ensure that the electricity consumption of different users can be accurately identified.

[0101] Step S103: Identify all electricity users in the filtered and optimized electricity monitoring logs, and perform real-time electricity load calculation on each electricity user to obtain real-time electricity load parameters for each user.

[0102] The real-time power load calculation is obtained by the following formula:

[0103] Real-time power load (kW) = current (A) × voltage (V) × power factor.

[0104] Record each user's real-time power load parameters, including power usage time, user ID, and load value, for subsequent analysis. Record each user's real-time power load parameters to ensure that each user's load information accurately reflects their power usage.

[0105] Step S104: Calculate the transient load change of each user's real-time power load parameters to generate transient load change values ​​of each user at multiple time points.

[0106] The transient load change value is calculated using the load difference method at adjacent time points. This method calculates the difference between the current load and the previous load. A time window is set, such as every minute, every hour, or every power cycle, to ensure that detailed load changes are captured. The transient load change calculation is performed on each user's real-time load data, generating transient load change values ​​for each user at multiple time points.

[0107] Step S105: extract the load characteristics of the transient load change values ​​of each user at multiple time points, and perform time series fitting based on the load characteristics and the power consumption cycle pattern to obtain the user's time series load trend curve.

[0108] Load features are extracted based on statistical analysis of transient load changes, identifying representative load variation patterns such as peaks, valleys, averages, and fluctuation ranges. These features reflect user electricity usage patterns and load variation trends. Based on the extracted load features and known electricity usage cycles (such as daily, weekly, or monthly), a time series fitting method is used to model the user's electricity load. Time series fitting methods can include linear regression, nonlinear regression, time series analysis models (such as ARIMA and SARIMA), or machine learning models (such as LSTM and GRU). The appropriate fitting method should be selected based on the characteristics of the user's electricity load data and analysis requirements. Through time series fitting, a user's time series load trend curve is generated. This curve describes the user's electricity load changes at different time points and reflects the user's electricity demand and usage patterns. The parameter settings and results of the fitting process should be recorded for subsequent analysis and verification.

[0109] The fitting parameters, including the fitting order and error requirements, are determined to ensure the accuracy of the fitting results. Based on the user's load trend characteristics and power usage cycle patterns, a discrete load fit is performed over multiple time periods to generate the user's time-series load trend curve. The fitting results, including the curve equation and goodness of fit, are recorded. The fit between the fitting results and the actual load data is evaluated to ensure that the fitting curve accurately reflects the user's power usage characteristics. The user's time-series load trend curve is recorded to ensure that the load variation characteristics of each user are detailed.

[0110] In some embodiments, the power load in a future period is predicted based on a user's time-series load trend curve to obtain power load prediction data, and the temporal and spatial distribution of power shortage in the future period is determined based on the power load prediction data, including:

[0111] Step S201: Perform power consumption cycle pattern analysis on the real-time power load parameters of each user to obtain the power consumption cycle pattern of each user; wherein the power consumption cycle pattern is used to characterize the periodic regularity of the user's power consumption behavior changing over time.

[0112] Among them, the power consumption cycle pattern analysis is performed on the real-time power load parameters of each user.

[0113] Time series analysis techniques, such as the Autoregressive Integrated Moving Average (ARIMA) model or the Seasonal Autoregressive Integrated Moving Average (SARIMA) model, can be used. These models can capture the trend, seasonality, and cyclical characteristics of a customer's electricity load over time. By fitting historical load data, the cyclical pattern of each customer's electricity consumption can be determined, including daily, weekly, or monthly cycles.

[0114] For example, the real-time power load parameters of each user are collected. For example, the power consumption data of a user is as follows:

[0115] Time: 2023-05-13 00:00, load: 1500 W.

[0116] Time: 2023-05-13 01:00, load: 1600 W.

[0117] Using time series analysis techniques, such as FFT (Fast Fourier Transform) or periodic analysis (such as STL decomposition), we process electricity load data to identify cyclical patterns in electricity usage. For example, suppose analysis reveals that a user has distinct daily and weekly cycles, with the daily peak occurring at 7 p.m. and the weekly peak occurring on weekends. The analysis results are recorded as the user's electricity usage cycle pattern, including the cycle length and corresponding load characteristics.

[0118] Step S202: predict the power load of the future time period based on the user's time series load trend curve according to the power consumption cycle pattern to obtain power load prediction data for each user.

[0119] Based on electricity consumption cycle patterns, appropriate forecasting models are used to predict electricity load for future periods. These models can be time series forecasting models such as ARIMA, SARIMA, and Prophet, or machine learning models such as support vector machines (SVMs), random forests, and gradient boosted tree models (GBDTs). These models can learn user electricity usage patterns based on historical electricity load data and electricity consumption cycle patterns, and accurately predict electricity load for future periods.

[0120] During implementation, an appropriate forecasting model is selected and parameterized based on the characteristics of the user's electricity load data and analysis requirements. The electricity usage cycle pattern is used as input, and the forecasting model is used to predict each user's future electricity load, generating forecasted data for each user's electricity load.

[0121] For example, using an LSTM model, we first normalize the electricity consumption data, then split the data into a training set and a test set. The model is trained on the training set. After training, the model is used to make predictions for future time periods. Assume that the prediction results for the next 24 hours are as follows:

[0122] Forecast time: 2023-05-14 00:00, load forecast: 1550 W.

[0123] Forecast time: 2023-05-14 01:00, load forecast: 1620 W.

[0124] Finally, the electricity load forecast value of each user is generated to form an electricity consumption forecast data set.

[0125] Step S203: Determine the electricity demand characteristics of each user in the future period based on the electricity load forecast data of each user, cluster the electricity demand characteristics of each user in the future period, and identify the electricity demand characteristics of each user in different periods.

[0126] Clustering each user's electricity demand characteristics for future time periods can be performed using unsupervised learning methods such as K-means clustering, hierarchical clustering, or DBSCAN clustering. These clustering methods can divide users into different groups based on their electricity demand characteristics, with each group having similar electricity usage patterns and demand characteristics. Cluster analysis can identify the electricity demand characteristics of different users at different time periods, such as peak and off-peak hours.

[0127] For example, the daily load forecast value is divided into time periods, such as hourly, daytime and nighttime, or weekday and weekend. Assuming the hourly division, the power demand characteristics can be expressed as follows:

[0128] Daytime (6:00-18:00): Average load 1500 W.

[0129] Night (18:00-6:00): Average load 1600W.

[0130] Next, cluster analysis (such as K-means) is used to cluster electricity demand during different time periods to identify user electricity usage characteristics during different time periods. For example, it may be possible to identify that electricity demand is higher during the morning and evening peak hours on weekdays, while electricity demand is lower on weekends.

[0131] Finally, a data set of electricity demand characteristics for each user in different time periods is generated, providing a basis for the subsequent fitting of the spatiotemporal distribution of electricity shortage.

[0132] Step S204: fitting the spatiotemporal distribution of power shortage according to the power demand characteristics of each user in different time periods to obtain the spatiotemporal distribution of power shortage in the future time period.

[0133] Among them, the spatiotemporal distribution fitting of electricity shortage is based on the electricity consumption characteristics of each user in different time periods. The spatial statistics and time series analysis methods are used to fit the spatiotemporal distribution of electricity shortage of individual users in different time periods.

[0134] The temporal and spatial distribution of power shortages can be visualized using heat maps or 3D charts. For example, Python libraries like Seaborn or Matplotlib can be used to generate heat maps that identify high-load periods and corresponding users.

[0135] Specifically, the spatiotemporal distribution of power shortage is fitted based on the electricity demand characteristics of each user in different time periods, and the spatiotemporal distribution of power shortage in the future period is obtained, including:

[0136] Step S2041: Determine the power supply load peaks corresponding to the target dispatching area in multiple time periods according to the user power consumption monitoring log.

[0137] The peak load is the maximum load that the target dispatching substation can withstand during a specific time period. Historical data analysis can identify peak loads for each time period (e.g., daily, weekly, or monthly). These peaks reflect the upper limit of the substation's power supply capacity during these different time periods.

[0138] For example, collect electricity usage monitoring logs from users within the region, ensuring that the data covers all relevant time periods. Logs should include information such as user ID, timestamp, and electricity load values. Perform data cleaning and filtering to remove outliers and missing values. Use the mean or median method to fill missing values, and use the standard deviation or IQR method to identify and address outliers to improve data quality. Calculate the total electricity load in the region based on the filtered electricity monitoring logs. The regional load can be obtained by summing the electricity load of all users during a specific time period. Record power load data for each time period, including peak values, average values, and fluctuations. Pay particular attention to peak load periods to provide a foundation for subsequent analysis. Select appropriate peak analysis methods, such as time series analysis, moving average, or fluctuation analysis. These methods can effectively identify peak load values ​​in different time periods. Determine the analysis time period, such as hourly, daily, or weekly, to capture the characteristics of electricity usage variations in different time periods. Perform multi-period peak analysis on the recorded regional power load data to extract the peak load value for each time period. A sliding window method can be used to calculate the maximum load value within each time period. Record the peak load values ​​for different time periods, including the specific time and corresponding load values, for subsequent analysis. Record the analysis results to ensure that the peak load values ​​for each time period accurately reflect the regional electricity demand.

[0139] Step S2042: Determine the power demand deviation of each user in different time periods according to the power supply load peaks and power demand characteristics corresponding to the multiple time periods.

[0140] Power demand deviation is the difference between a user's actual power demand and the substation's power supply capacity, calculated using peak load and demand characteristics. This deviation reflects whether a user's power demand exceeds the substation's power supply capacity during different time periods, potentially leading to power shortages.

[0141] In this embodiment of the present application, a user's electricity demand characteristics are compared with the peak power supply load during the corresponding time period. If the user's electricity demand characteristics (such as average load) are close to or exceed the peak power supply load, a power supply demand deviation is considered to exist. The difference between the electricity demand characteristics and the peak power supply load is used as the power supply demand deviation. The power supply demand deviation value of each user in different time periods is recorded, including the magnitude and direction of the deviation (i.e., whether the user's electricity demand is higher or lower than the power supply capacity of the substation).

[0142] Step S2043: Determine the power shortage users and their power shortage periods according to the power supply demand deviation of each user.

[0143] The power shortage period refers to a specific time period when a user's electricity demand exceeds the power supply capacity of the substation. By comparing each user's power supply demand deviation with the preset power shortage threshold, if the power supply demand deviation is greater than the preset power shortage threshold, the current period is identified as a power shortage period. This allows the identification of power shortage users and their corresponding power shortage periods. The ID, power shortage period, and corresponding power supply demand deviation value of each power shortage user are recorded to ensure that the power shortage situation that the substation may face in the future period can be accurately reflected.

[0144] Step S2044: Determine the spatial distribution of power-scarce users based on their geographical locations within the target dispatching area.

[0145] For each identified power-demanding user, calculate the supply-demand gap over different time periods. Record the gap between each user's load demand and power supply capacity, identifying the specific time period of the gap. Record information about the gap period, including the start and end time of the gap and the magnitude of the gap.

[0146] Collect the geographic location of each power-demanding user within the target dispatch area, typically including the user's address or geographic coordinates. This data can be obtained through user registration information or smart meter positioning information. Ensure the accuracy and completeness of spatial location data.

[0147] The spatial distribution of power-starved users is determined based on their geographic location information and supply-demand gap data. Spatial analysis methods, such as geographic information systems (GIS) or spatial statistical models, are used to determine their distribution across different geographic regions. These analytical methods combine user location information with electricity demand characteristics to generate intuitive spatial distribution maps, demonstrating the distribution of power shortages across different regions.

[0148] Specifically, the geographic location data of electricity-scarce users are imported into the GIS system, and map visualization tools are used to output the spatial distribution of electricity-scarce users.

[0149] Step S2045: Perform full-cycle mapping of the spatial distribution of power-scarce users in the future period according to the power-scarce period to obtain the spatiotemporal distribution of power shortage in the future period.

[0150] Among them, full-cycle mapping is the process of continuously displaying the changes in the spatial distribution of power-scarce users over time. This process combines the time dimension and the space dimension, and can comprehensively reflect the spatiotemporal evolution of power shortages in future time periods. You can choose an appropriate full-cycle shortage mapping method, such as spatiotemporal clustering, time series analysis, or spatial regression models. These methods can effectively identify and map users' power shortages. Determine the parameter settings in the mapping process, such as the selection of the time window and the spatial resolution, to ensure the accuracy of the mapping. Based on the power shortage period of each user, perform full-cycle power shortage mapping on the spatial distribution map of power-scarce users. Record the shortage situation in each time period and combine it with the spatial distribution.

[0151] In implementation, the mapping timeframe is first determined, typically coinciding with the predicted power shortage timeframe. Then, based on the spatial distribution of power-scarce users in each timeframe, a geographic information system (GIS) or spatiotemporal data analysis software is used to continuously display the power shortage situation over different timeframes on a map. This display can be animated, with scrolling through the timeline to visually demonstrate the dynamic changes in power shortages across different geographic regions.

[0152] Through full-cycle mapping, we can determine the spatiotemporal distribution of power shortages in the future. This clearly demonstrates the distribution of power shortages across different time periods and geographical regions, allowing us to identify high-risk areas and time periods for power shortages so we can take proactive countermeasures. Furthermore, by analyzing the spatiotemporal distribution map, we can uncover potential patterns and trends in power shortages.

[0153] In some embodiments, determining a power supply support sequence for a mobile power source based on the temporal and spatial distribution of power shortages and the power priority of each power-scarce user includes:

[0154] Step S301: Determine the power urgency of each power-scarce user based on the power demand characteristics and power demand type of each power-scarce user.

[0155] Among them, the electricity demand type is based on the characteristics of the user's electricity demand, which can be divided into different types, such as residential electricity demand, commercial electricity demand, industrial electricity demand, etc. Each electricity demand type may have its own specific urgency. For example, the user's electricity demand type can be divided into the following categories:

[0156] High demand: Power load exceeds 2000W.

[0157] Medium demand: Power load is between 1500W and 2000W.

[0158] Low demand type: power load is less than 1500W.

[0159] After obtaining the user electricity demand types, we conduct a quantitative analysis of the electricity urgency based on these types to generate an electricity urgency value for each user. The purpose of this step is to assess the urgency of each user's electricity demand so that power resources can be allocated efficiently.

[0160] First, set a quantitative standard for the degree of electricity urgency. For example, it can be calculated using the following formula:

[0161] Urgency value = (power demand type weight) × (power demand characteristics).

[0162] Set the weights for different types of electricity demand:

[0163] High demand type: Weight 3.

[0164] Medium demand type: Weight 2.

[0165] Low demand type: Weight 1.

[0166] If the user's power demand type in time period 2 is high demand and the load is 2000 W, then:

[0167] User urgency value = 3 × 2000 = 6000.

[0168] Step S302: Determine the actual power demand shortage difference value of each power-scarce user based on the power demand characteristics and actual power load of each power-scarce user.

[0169] The actual power demand shortage difference value assesses the degree of power shortage faced by a user when their power demand is unmet. This difference value is calculated by comparing a user's power demand characteristics with their actual power load. If a user's actual power load is lower than the expected load indicated by their power demand characteristics, power shortage is present. The magnitude of the shortage difference value reflects the degree of unmet power demand and is an important factor in determining the priority of mobile power supply support.

[0170] In the specific calculation, when the actual power load is lower than the user's demand load, the shortage difference value is calculated. Assume that the demand load of each user has been recorded, for example:

[0171] User demand load: User A = 2000 W, actual power load = 1500 W.

[0172] The formula for calculating the scarcity variance is:

[0173] Actual electricity demand shortage difference = demand load - actual electricity load.

[0174] For user A, the actual electricity demand shortage difference value is calculated as:

[0175] The actual power demand shortage difference = 2000 - 1500 = 500 W.

[0176] Then, similar calculations are performed on all users to form a dataset of scarce difference values ​​for each user.

[0177] Step S303: Determine the power demand urgency value of each power-scarce user according to the power demand urgency degree of each power-scarce user and the actual power demand shortage difference value.

[0178] The power demand urgency value is obtained by adding the power demand urgency and the actual power demand shortage difference value. For example, for user A, assuming that its urgency value is 6000 and the shortage difference value is 500, then:

[0179] Emergency value of electricity demand = 6000 + 500 = 6500.

[0180] Next, the electricity priority values ​​of all users are calculated by programming, and the results are stored in a database. The electricity demand urgency values ​​are then normalized to obtain the normalized electricity demand urgency values.

[0181] Step S304: Compare the power demand urgency value of each power-scarce user with a plurality of preset priority thresholds to determine the power priority of each power-scarce user.

[0182] By setting multiple preset priority thresholds, the power demand urgency values ​​of power-scarce users can be divided into different priority levels. For example, the priority thresholds can be set to low, medium, and high, and the corresponding urgency value ranges can also be set accordingly.

[0183] If the urgency value of electricity demand exceeds the highest threshold, the user is classified as the highest priority, indicating that his electricity demand is extremely urgent and mobile power support is required as soon as possible; if the urgency value is within the middle threshold range, it is classified as medium priority; if the urgency value is lower than the lowest threshold, it is classified as low priority.

[0184] In practice, different power supply support strategies can be developed based on the priority levels. For example, for the highest-priority users, mobile power banks can be dispatched for emergency support to ensure their power needs are met. For medium-priority users, support can be provided in a timely manner based on the availability of mobile power banks. For low-priority users, support can be considered if sufficient resources are available.

[0185] High-priority users are those with a high degree of power urgency and a large difference between actual power demand and shortage. They should be given priority for power support from mobile power banks. Medium-priority users are those with a medium degree of power urgency or a medium difference between actual power demand and shortage. They should also receive timely support if resources permit. Low-priority users are those with a low degree of power urgency and a small difference between actual power demand and shortage. They can receive support if resources are sufficient.

[0186] This prioritization method based on the difference between the urgency of electricity demand and the actual shortage of electricity demand can ensure that electricity resources are allocated in the most reasonable way under limited circumstances, giving priority to meeting the needs of the most urgent and scarce users.

[0187] Step S305: Based on the power priority of each power-scarce user, a power supply sequence is planned for each power-scarce user within the power-scarce spatiotemporal distribution, and a mobile power supply support sequence is constructed.

[0188] Power supply sequencing prioritizes power supply to power-starved users based on their priority. First, power-starved users are ranked from highest to lowest priority. Users with higher priority receive power from power-starved users first, ensuring that even in power-scarce situations, the most critical users receive timely power.

[0189] In some embodiments, performing shortest path planning on the power supply support sequence of the mobile power supply to generate a support path chain of the mobile power supply includes:

[0190] Step S401: Perform three-dimensional environmental modeling on the three-dimensional environmental data and environmental obstacle data of the target dispatching area to obtain a three-dimensional environmental structure map of the target dispatching area; wherein the three-dimensional environmental structure map includes distance information between various power-scarce users.

[0191] In this embodiment, sensors in the power bank (such as GPS, LiDAR, and ultrasonic sensors) are used to collect environmental data. Assume that the power bank is equipped with a GPS module and a LiDAR. The GPS is used to obtain the current location coordinates, while the LiDAR is used to measure the distance to surrounding objects.

[0192] For example, the data collected by a mobile power bank at a certain location is as follows:

[0193] GPS coordinates: Latitude 37.7749, Longitude -122.4194.

[0194] LiDAR data: distance 1.5m (obstacle in front), distance 3.2m (obstacle on the right).

[0195] The aforementioned sensor data is integrated to generate a real-time environmental perception dataset, including location information and its corresponding environmental features. After obtaining this real-time location environmental perception data, the data is used to identify and extract 3D road structure features. First, a 3D point cloud is generated using LiDAR data. By processing the distance data acquired by the LiDAR, a 3D point cloud model is constructed to represent objects and road structures in the environment. Open-source libraries such as PCL (PointCloud Library) can be used for point cloud processing.

[0196] For example, the processed point cloud data may show features such as the road's boundaries, slope, and width. Then, algorithms such as RANSAC (Random Sample Consensus Algorithm) are applied to segment the point cloud and identify the planar parts of the road.

[0197] After identifying the 3D road structure, the system detects environmental obstacles based on real-time location and environmental perception data, marking multiple environmental obstacle nodes. First, using the point cloud data acquired by the LiDAR, a clustering algorithm (such as DBSCAN) is used to group surrounding objects and identify potential obstacles. For example, suppose the detected obstacles include pedestrians, vehicles, and buildings. Next, feature extraction is performed on each obstacle, recording its location and shape. Finally, multiple environmental obstacle nodes are marked.

[0198] After completing the environmental obstacle detection, three-dimensional environmental modeling is performed based on the three-dimensional structural characteristics of the road and multiple environmental obstacle nodes to construct a three-dimensional environmental structure map of the target dispatching area.

[0199] Step S402: Based on a path planning algorithm and according to the distance information between the power-scarce users, the shortest path is planned for the multiple power-scarce users to obtain a support path chain of the mobile power supply under the multiple power-scarce users.

[0200] The choice of path planning algorithm is crucial for achieving the shortest path planning. In this embodiment, classic path planning algorithms such as the Dijkstra algorithm, the A* algorithm, or a genetic algorithm can be used. These algorithms can calculate the shortest path from the current location of the power bank to each power-scarce user based on known distance information and obstacle distribution.

[0201] The Dijkstra algorithm is a typical single-source shortest path algorithm applicable to directed or undirected graphs with non-negative weights. It gradually finds the shortest path from the starting point to all other nodes by continuously selecting the unvisited nodes closest to the starting point and expanding them. In this application, the location of the power bank can be used as the starting point, and the locations of power-scarce users can be used as the end points. The Dijkstra algorithm can then be used to calculate the shortest path.

[0202] The A* algorithm is a heuristic search algorithm that improves search efficiency by introducing a heuristic function to guide the search direction. In this embodiment, a heuristic function can be designed based on the power priority and distance information of power-starved users, making path planning more responsive to actual needs. For example, the heuristic function can be set as a weighted sum of the power-starved user priority and distance, so that the algorithm prioritizes users with high priority and close proximity during the search process.

[0203] A genetic algorithm is an optimization algorithm based on biological evolution and is suitable for solving complex optimization problems. In this application, the path planning problem can be transformed into an optimization problem. The genetic algorithm is used to perform operations such as encoding, selection, crossover, and mutation on the path, gradually optimizing it to obtain the shortest path.

[0204] For example, when using the A* algorithm, the following objective function is set:

[0205] f(v)=g(v)+h(v).

[0206] Where f(v) is the objective function value, g(v) is the actual path cost (distance) from the starting point ss to the current node v, and h(v) is the heuristic estimated cost (estimated remaining distance + priority penalty) from the current node v to the target node t.

[0207] In order to make path planning more inclined to give priority to users with high priority and close distance, the following heuristic function can be designed:

[0208] ;

[0209] in: is the estimated distance from node v to target node t (such as Euclidean distance or Manhattan distance); p^(t) is the normalized priority value of node t; is the distance weight factor, which controls the influence of search distance; β is the priority weight factor, which controls the inclination of priority (standing +β=1);

[0210] If high priority (emergency users) are given priority, α=0.4, β=0.6 can be set;

[0211] If the shortest path is given priority (e.g., if the battery power is limited), α=0.7, β=0.3 can be set;

[0212] After synthesis, the final objective function used for path search is:

[0213] .

[0214] After determining the path planning algorithm, the shortest path is planned for multiple power-starved users based on the distance information and obstacle distribution between them. First, the power supply support sequence is sorted according to the priority of the power-starved users, ensuring that high-priority users receive support first. Then, for this sorted list of power-starved users, the shortest path from the power bank's current location to each user is calculated. This calculation takes into account the impact of the three-dimensional road structure and obstacle distribution on the path to ensure that the planned path is feasible.

[0215] In some embodiments, a path energy consumption prediction is performed on a support path chain of a mobile power source, and the support path chain of the mobile power source is optimized based on the path energy consumption prediction result to obtain an energy consumption support path chain in which the remaining charge of the mobile power source satisfies the path energy consumption prediction result, including:

[0216] Step S501: Calculate the full moving slope of the support path chain to generate the full moving slope of the support path chain.

[0217] The supported path chain is composed of multiple coordinate points (x, y, z). By calculating the height difference and horizontal distance between adjacent coordinate points, the slope of each path segment can be obtained. The slope calculation formula is:

[0218] Moving slope = (z2 - z1) / √((x2 - x1)² + (y2 - y1)²).

[0219] Assume that the supported path chain contains the following coordinate points:

[0220] Point 1: (x1, y1, z1).

[0221] Point 2: (x2, y2, z2).

[0222] By looping through each pair of adjacent points in the path chain, the slope of each segment is calculated and the results are stored. For example:

[0223] Slope from point 1 to point 2 = (z2 - z1) / √((x2 - x1)² + (y2 - y1)²);

[0224] Step S502: predicting the path energy consumption of the mobile power source according to the full moving slope to obtain a predicted energy consumption value of the mobile power source.

[0225] The path energy consumption of the mobile power source is predicted based on the full moving slope. It is assumed that the energy consumption of each path segment can be calculated using the following formula: Energy consumption = Base energy consumption + (Slope coefficient × Moving slope × Distance); where Base energy consumption is the energy consumption of the mobile power source during horizontal travel, Slope coefficient indicates the degree to which the slope affects energy consumption, and Distance is the horizontal distance of the path segment. In the programming implementation, it is assumed that Base energy consumption is 100 W and Slope coefficient is 50 W / degree. For each path segment, energy consumption is predicted based on the calculated slope and distance. For example:

[0226] Energy consumption of path segment = 100 + (50 × moving slope × distance).

[0227] The energy consumption of all path segments is summarized to finally obtain the energy consumption forecast data of the entire path chain.

[0228] Step S503: Obtain the remaining charge of the mobile power supply in real time.

[0229] Among them, the remaining charge is the amount of electricity that the mobile power supply can currently supply, and is a key parameter to ensure that the mobile power supply can successfully complete the power supply task. In actual applications, the remaining charge can be obtained in real time through the power display module of the mobile power supply. For example, assuming the total capacity of the mobile power supply is 10,000 W·h and the current remaining charge is 8,000 W·h, the remaining charge percentage is 80%. This data will be used for subsequent comparison of path energy consumption prediction results to ensure that the remaining charge of the mobile power supply is sufficient to support it to complete the power supply task of the entire support path chain.

[0230] Step S504: determine whether the remaining charge is less than the energy consumption prediction value.

[0231] Step S505 : If it is determined that the remaining charge is less than the energy consumption prediction value, the support path chain is readjusted to obtain an updated support path chain.

[0232] Step S506: Based on the updated support path chain, the full movement slope calculation of the support path chain is performed again to generate the full movement slope of the support path chain until the remaining charge is not less than the energy consumption prediction value, thereby obtaining the energy consumption support path chain.

[0233] The remaining charge is compared with the predicted energy consumption of the support path chain. If the remaining charge is lower than the predicted energy consumption, adjustments are required. A threshold can be set, for example:

[0234] If the remaining charge is less than the predicted energy consumption, the system is marked as "scarce" and the support path chain needs to be readjusted to reduce energy consumption or select lower-priority users for power supply to ensure the power bank can successfully complete its power supply task. During this adjustment process, some users or path segments in the support path chain can be replaced, or the path can be replanned to reduce energy consumption.

[0235] During path replacement, low-energy-consuming segments are selected to replace high-energy-consuming segments, or segments with steeper slopes and higher energy consumption are prioritized. Alternatively, lower-priority users can be replaced with higher-priority users. However, during this replacement, it is important to ensure that overall energy consumption does not increase or remains within an acceptable range. For example, high-energy-consuming users in remote areas can be replaced with lower-energy-consuming users closer to the site, thereby reducing overall energy consumption while maintaining power supply efficiency.

[0236] At the same time, additional charging points or backup power sources can be considered to replenish the power bank. After the adjusted support path chain, the full-route slope calculation and path energy consumption forecast must be repeated to ensure that the remaining charge meets the new energy consumption forecast. If the adjusted support path chain still cannot meet the remaining charge requirement, further adjustments will be required until a feasible energy-consuming support path chain is found. This approach enables intelligent management of mobile power bank scheduling, improving the efficiency and quality of mobile power supply.

[0237] In some embodiments, during the process of the mobile power supply performing real-time mobile power support according to the energy consumption support path chain, the remaining unexecuted energy consumption support path chain is optimized according to the minimum power load of each power-scarce user, and the real-time mobile power support is continued to be performed for the remaining power-scarce users according to the optimized energy consumption support path chain, including:

[0238] Step S601: When the mobile power supply performs real-time mobile power support according to the energy consumption support path chain, the real-time power load of the power-scarce user being supported by the mobile power supply is obtained in real time.

[0239] Real-time electricity load refers to the actual current electricity demand of power-hungry users, which may fluctuate over time and with changes in electricity usage. To obtain real-time electricity load, smart meters or other power monitoring devices can be used to collect electricity usage data from power-hungry users in real time. For example, smart meters can record the electricity consumption of power-hungry users at regular intervals (such as every minute or every second), thereby providing real-time load information.

[0240] Step S602: Compare the real-time power load with the lowest power load of the power-scarce user.

[0241] The minimum power load is the minimum amount of electricity required by power-scarce users to maintain basic power needs. By comparing the real-time power load with the minimum power load, you can assess whether the power provided by the current mobile power supply meets the user's minimum needs. If the real-time power load is lower than the minimum power load, it may mean that the user's power needs are met or that the user is currently experiencing low power consumption. Conversely, if the real-time power load is higher than the minimum power load, it indicates that the user may need more power support.

[0242] Select an appropriate minimum load calculation method, such as the historical average method or percentile method (e.g., the 90th percentile). These methods can effectively identify a user's minimum electricity demand during a specific time period. Determine a time window for calculation, such as hourly or daily, to accurately reflect user electricity usage habits. Based on collected user load data, calculate the minimum load for each critical user. Record each user's minimum load value and the corresponding time period for subsequent energy supply comparisons.

[0243] Step S603: When the real-time power load is greater than the minimum power load, the power priority of the first-level power-scarce user is updated and lowered, and the remaining unexecuted energy consumption support path chain is readjusted according to the updated power priority of the power-scarce user.

[0244] Among them, when the real-time power load continues to be higher than the minimum power load of the power-scarce user, but the remaining charge of the mobile power supply is insufficient to support it to continue supplying power according to the current energy consumption support path chain, the system can automatically or manually update and lower the power priority of the power-scarce user by one level. This adjustment is based on the dynamic balance between the actual power demand of the power-scarce user and the power supply capacity of the mobile power supply. By lowering the power priority, the mobile power supply can prioritize the power supply needs of other users with more urgent or greater power needs.

[0245] If the user's electricity priority is the lowest, there is no need to reduce it.

[0246] Step S604: Control the mobile power supply to continue to perform real-time mobile power support for the remaining power-scarce users according to the readjusted remaining unexecuted energy consumption support path chain, and proceed to obtain the real-time power load of the power-scarce users being supported by the mobile power supply in real time during the process of the mobile power supply performing real-time mobile power support according to the energy consumption support path chain, until all power-scarce users have completed the real-time mobile power support.

[0247] After readjusting the remaining unexecuted energy support path chains, the power bank will continue to provide real-time mobile power support to the remaining power-starved users according to the new plan. This dynamic adjustment process ensures that the power bank can rationally allocate power resources based on actual conditions, prioritizing those with more urgent power needs or higher power consumption. At the same time, by obtaining the real-time power load of the power-starved users being supported and comparing it with the minimum power load, the effectiveness of the power support can be further evaluated, and further adjustments and optimizations can be made when necessary.

[0248] Based on the same inventive concept, an embodiment of the present application further provides a mobile power scheduling optimization system for implementing the above-mentioned mobile power scheduling optimization method.

[0249] The implementation solution provided by the system to solve the problem is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more mobile power scheduling optimization system embodiments provided below can be found in the above limitations on the mobile power scheduling optimization method and will not be repeated here.

[0250] like Figure 3 As shown, the embodiment of the present application provides a mobile power scheduling optimization system, including:

[0251] The load trend determination module 100 is used to obtain the user power consumption monitoring logs in the target dispatching area and determine the user time series load trend curve based on the user power consumption monitoring logs;

[0252] The power shortage distribution module 200 is used to predict the power load in the future time period based on the user time series load trend curve, obtain power load prediction data, and determine the spatiotemporal distribution of power shortage in the future time period based on the power load prediction data; wherein the spatiotemporal distribution of power shortage is used to characterize the geographical distribution of each power shortage user in each time period in the future time period;

[0253] The power supply support determination module 300 is configured to determine a power supply support sequence for the power bank based on the temporal and spatial distribution of power shortages and the power priority of each power-scarce user. The power supply support sequence for the power bank is a user support sequence generated from high to low based on the power priority of each power-scarce user.

[0254] The support path planning module 400 is used to perform the shortest path planning for the power supply support sequence of the mobile power supply and generate a support path chain for the mobile power supply;

[0255] The path energy consumption optimization module 500 is used to predict the path energy consumption of the support path chain of the mobile power supply and optimize the support path chain of the mobile power supply based on the path energy consumption prediction result to obtain an energy consumption support path chain in which the remaining charge of the mobile power supply meets the path energy consumption prediction result;

[0256] The path real-time optimization module 600 is used to optimize the remaining unexecuted energy consumption support path chains according to the minimum power load of each power-scarce user during the process of the mobile power supply performing real-time mobile power support according to the energy consumption support path chain, and continue to perform real-time mobile power support for the remaining power-scarce users according to the optimized energy consumption support path chain.

[0257] In some embodiments, the load trend determination module 100 is configured to:

[0258] Obtain user electricity consumption monitoring logs within the target dispatching area;

[0259] Filter the user's electricity consumption monitoring log to generate a filtered and optimized electricity consumption monitoring log;

[0260] Identify, filter and optimize all electricity users in the electricity monitoring log, and calculate the real-time electricity load of each electricity user to obtain the real-time electricity load parameters of each user;

[0261] Calculate the transient load change of each user's real-time power load parameters and generate the transient load change value of each user at multiple time points;

[0262] The load characteristics of each user's transient load change values ​​at multiple time points are extracted, and time series fitting is performed based on the load characteristics and the power consumption cycle pattern to obtain the user's time series load trend curve.

[0263] In some embodiments, the power shortage distribution module 200 is used to:

[0264] The power consumption cycle mining module is used to analyze the power consumption cycle pattern of each user's real-time power load parameters to obtain each user's power consumption cycle pattern. The power consumption cycle pattern is used to characterize the cyclical regularity of the user's power consumption behavior over time.

[0265] The load forecasting module is used to forecast the power load of future periods based on the user's time series load trend curve according to the power consumption cycle pattern, and obtain the power load forecast data of each user;

[0266] The demand feature extraction module is used to determine the electricity demand characteristics of each user in the future period based on the electricity load forecast data of each user, and cluster the electricity demand characteristics of each user in the future period to identify the electricity demand characteristics of each user in different time periods;

[0267] The fitting module is used to fit the spatiotemporal distribution of power shortage according to the power demand characteristics of each user in different time periods, and obtain the spatiotemporal distribution of power shortage in the future time period.

[0268] In some embodiments, the fitting module is configured to:

[0269] According to the user's electricity consumption monitoring log, determine the power supply load peak corresponding to the target dispatching area in multiple time periods;

[0270] Determine the power demand deviation of each user in different time periods based on the power supply load peaks and power demand characteristics corresponding to multiple time periods;

[0271] According to the power supply demand deviation of each user, determine the power shortage users and the power shortage period of the power shortage users;

[0272] Determine the spatial distribution of power-scarce users based on their geographical locations within the target dispatching area;

[0273] According to the power shortage period, the spatial distribution of power shortage users is mapped throughout the future period to obtain the spatiotemporal distribution of power shortage in the future period.

[0274] In some embodiments, the power supply support determination module 300 is configured to:

[0275] Determine the power urgency of each power-scarce user based on their power demand characteristics and types;

[0276] Determine the actual power demand difference value of each power-scarce user based on the power demand characteristics and actual power load of each power-scarce user;

[0277] Determine the power demand emergency value of each power-scarce user based on the power demand emergency degree of each power-scarce user and the actual power demand emergency difference value;

[0278] Compare the power demand urgency value of each power-scarce user with multiple preset priority thresholds to determine the power priority of each power-scarce user;

[0279] Based on the power priority of each power-scarce user, the power supply sequence is planned for each power-scarce user within the temporal and spatial distribution of power shortage, and a mobile power supply support sequence is constructed.

[0280] In some embodiments, the support path planning module 400 is configured to:

[0281] Performing 3D environmental modeling on the 3D environmental data and environmental obstacle data of the target dispatching area to obtain a 3D environmental structure map of the target dispatching area; wherein the 3D environmental structure map includes distance information between various power-scarce users;

[0282] Based on the path planning algorithm and the distance information between each power-scarce user, the shortest path planning is performed for multiple power-scarce users to obtain the support path chain of the mobile power supply for multiple power-scarce users.

[0283] In some embodiments, the path energy consumption optimization module 500 is configured to:

[0284] Calculate the full moving slope of the support path chain to generate the full moving slope of the support path chain;

[0285] The energy consumption of the mobile power source is predicted based on the full moving slope to obtain the predicted energy consumption value of the mobile power source;

[0286] Get the remaining charge of the mobile power bank in real time;

[0287] Determine whether the remaining charge is less than the energy consumption prediction value;

[0288] If it is determined that the remaining charge is less than the energy consumption prediction value, the support path chain is readjusted to obtain an updated support path chain;

[0289] Based on the updated support path chain, the full moving slope calculation of the support path chain is performed again to generate the full moving slope of the support path chain until the remaining charge is not less than the energy consumption prediction value, thereby obtaining the energy consumption support path chain.

[0290] In some embodiments, the path real-time optimization module 600 is configured to:

[0291] When the mobile power supply performs real-time mobile power support according to the energy consumption support path chain, the real-time power load of the power-scarce user being supported by the mobile power supply is obtained in real time;

[0292] Compare the real-time electricity load with the minimum electricity load of electricity-scarce users;

[0293] When the real-time power load is greater than the minimum power load, the power priority of the first-level power-scarce users is updated and lowered, and the remaining unexecuted energy consumption support path chains are readjusted according to the updated power priority of the power-scarce users;

[0294] Control the mobile power supply to continue to perform real-time mobile power support for the remaining power-shortage users according to the readjusted remaining unexecuted energy consumption support path chain, and obtain the real-time power load of the power-shortage users that the mobile power supply is supporting in real time during the process of the mobile power supply performing real-time mobile power support according to the energy consumption support path chain, until the real-time mobile power support is completed for all power-shortage users.

[0295] like Figure 4As shown, an embodiment of the present application provides an electronic device, the electronic device 10 includes a memory 20 and a processor 30, the memory 20 stores a computer program, and when the computer program is executed by the processor 30, the processor 30 executes the steps of the mobile power scheduling optimization method in the above embodiment.

[0296] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed, the steps of the mobile power scheduling optimization method in the above embodiment are implemented.

[0297] An embodiment of the present application provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the steps of the mobile power scheduling optimization method described in the above embodiment.

[0298] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, electronic devices, computer storage media, and computer program products can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0299] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0300] It should be understood that, although the various steps in the flowcharts involved in the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0301] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, electronic devices, computer storage media, computer program products and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0302] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0303] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0304] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the method described in each embodiment of the present invention via a computer device (which can be a personal computer, server, or network device, etc.). The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0305] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A mobile power scheduling optimization method, characterized in that: include: Obtaining user electricity consumption monitoring logs within the target dispatching area, and determining user time series load trend curves based on the user electricity consumption monitoring logs; Predicting the electricity load for a future period based on the user time-series load trend curve to obtain electricity load prediction data, and determining the spatiotemporal distribution of electricity shortages within the future period based on the electricity load prediction data; wherein the spatiotemporal distribution of electricity shortages is used to characterize the geographical distribution of each electricity shortage user in each period within the future period; Determining a power supply support sequence for the mobile power source based on the temporal and spatial distribution of power shortages and the power priority of each power-scarce user; wherein the power supply support sequence for the mobile power source is a user support order generated from high to low based on the power priority of each power-scarce user; Performing shortest path planning on the power supply support sequence of the mobile power source to generate a support path chain of the mobile power source; Performing a path energy consumption prediction on the support path chain of the mobile power supply, and optimizing the support path chain of the mobile power supply according to the path energy consumption prediction result to obtain an energy consumption support path chain in which the remaining charge of the mobile power supply satisfies the path energy consumption prediction result; During the process of the mobile power supply performing real-time mobile power support according to the energy consumption support path chain, the remaining unexecuted energy consumption support path chains are optimized according to the minimum power load of each of the power-scarce users, and real-time mobile power support is continued to be performed for the remaining power-scarce users according to the optimized energy consumption support path chains.

2. The mobile power scheduling optimization method according to claim 1, characterized in that: The step of obtaining a user electricity consumption monitoring log in the target dispatching area and determining a user time series load trend curve based on the user electricity consumption monitoring log includes: Obtain user electricity consumption monitoring logs within the target dispatching area; Filtering the user's electricity consumption monitoring log to generate a filtered and optimized electricity consumption monitoring log; Identify all electricity users in the filtered and optimized electricity monitoring log, and calculate the real-time electricity load of each electricity user to obtain the real-time electricity load parameters of each user; Calculate the transient load change of each user's real-time power load parameters and generate the transient load change value of each user at multiple time points; The load characteristics of the transient load change values ​​of each user at multiple time points are extracted, and time series fitting is performed based on the load characteristics and the power consumption cycle pattern to obtain the user time series load trend curve.

3. The mobile power scheduling optimization method according to claim 2, characterized in that: The method of predicting the power load in a future time period based on the user time series load trend curve to obtain power load prediction data, and determining the spatiotemporal distribution of power shortage in the future time period based on the power load prediction data, includes: Performing a power consumption cycle pattern analysis on the real-time power load parameters of each user to obtain a power consumption cycle pattern for each user; wherein the power consumption cycle pattern is used to characterize the periodic regularity of the user's power consumption behavior changing over time; Performing power load forecasting for future periods on the user's time series load trend curve according to the power consumption cycle pattern to obtain power load forecast data for each user; Based on the electricity load forecast data of each user, the electricity demand characteristics of each user in the future period are determined, and the electricity demand characteristics of each user in the future period are clustered to identify the electricity demand characteristics of each user in different time periods; The spatiotemporal distribution of power shortage is fitted according to the power demand characteristics of each user in different time periods to obtain the spatiotemporal distribution of power shortage in the future time period.

4. The mobile power scheduling optimization method according to claim 3, characterized in that: The fitting of the spatiotemporal distribution of power shortage according to the power demand characteristics of each user in different time periods to obtain the spatiotemporal distribution of power shortage in the future time period includes: Determine the power supply load peaks corresponding to the target dispatching area in multiple time periods according to the user power consumption monitoring log; Determine the power demand deviation of each user in different time periods based on the power supply load peaks and power demand characteristics corresponding to multiple time periods; Determine power-shortage users and power-shortage periods for the power-shortage users based on the power supply demand deviation of each user; Determining the spatial distribution of power-scarce users based on the geographical locations of the power-scarce users within the target dispatching area; According to the power shortage period, the spatial distribution of the power shortage users is mapped throughout a future period to obtain the spatiotemporal distribution of power shortage in the future period.

5. The mobile power scheduling optimization method according to claim 3, characterized in that: The step of determining the power supply support sequence of the mobile power source according to the temporal and spatial distribution of power shortage and the power priority of each power shortage user includes: Determine the power urgency of each power-scarce user based on their power demand characteristics and types; Determine the actual power demand difference value of each power-scarce user based on the power demand characteristics and actual power load of each power-scarce user; Determine the power demand emergency value of each power-scarce user based on the power demand emergency degree of each power-scarce user and the actual power demand emergency difference value; Compare the power demand urgency value of each power-scarce user with multiple preset priority thresholds to determine the power priority of each power-scarce user; Based on the power priority of each power-scarce user, a power supply sequence is planned for each power-scarce user within the power-scarce spatiotemporal distribution, and a mobile power supply support sequence is constructed.

6. The mobile power supply scheduling optimization method according to claim 5, characterized in that: The performing the shortest path planning on the power supply support sequence of the mobile power source to generate the support path chain of the mobile power source includes: Performing three-dimensional environmental modeling on the three-dimensional environmental data and environmental obstacle data of the target dispatching area to obtain a three-dimensional environmental structure map of the target dispatching area; wherein the three-dimensional environmental structure map includes distance information between various power-scarce users; Based on the path planning algorithm, according to the distance information between each power-scarce user, the shortest path planning is performed for multiple power-scarce users to obtain the support path chain of the mobile power supply under the multiple power-scarce users.

7. The mobile power supply scheduling optimization method according to claim 6, characterized in that: The step of performing path energy consumption prediction on the support path chain of the mobile power supply, and optimizing the support path chain of the mobile power supply according to the path energy consumption prediction result to obtain an energy consumption support path chain in which the remaining charge of the mobile power supply satisfies the path energy consumption prediction result, includes: Calculating the full-range moving slope of the support path chain to generate the full-range moving slope of the support path chain; Predicting the path energy consumption of the mobile power source according to the entire moving slope to obtain a predicted energy consumption value of the mobile power source; Obtaining the remaining charge of the mobile power supply in real time; Determining whether the remaining charge is less than the energy consumption prediction value; If it is determined that the remaining charge is less than the energy consumption prediction value, readjusting the support path chain to obtain an updated support path chain; Based on the updated support path chain, the full-range moving slope calculation of the support path chain is performed again to generate the full-range moving slope of the support path chain until the remaining charge amount is not less than the energy consumption prediction value, thereby obtaining the energy consumption support path chain.

8. The mobile power supply scheduling optimization method according to claim 6, characterized in that: The method further comprises: optimizing the remaining unexecuted energy consumption support path chains according to the minimum power load of each power-scarce user during the process of the mobile power supply performing the real-time mobile power support according to the energy consumption support path chain, and continuing to perform the real-time mobile power support for the remaining power-scarce users according to the optimized energy consumption support path chains, including: During the process of the mobile power supply performing the real-time mobile power support according to the energy consumption support path chain, obtaining in real time the real-time power load of the power-scarce user being supported by the mobile power supply; Comparing the real-time power load with the lowest power load of the power-scarce user; When the real-time power load is greater than the minimum power load, the power priority of the power-scarce user is updated and lowered by one level, and the remaining unexecuted energy consumption support path chain is readjusted according to the updated power priority of the power-scarce user; Control the mobile power supply to continue to perform real-time mobile power support for the remaining power-shortage users according to the readjusted remaining unexecuted energy consumption support path chain, and switch to the process of the mobile power supply performing real-time mobile power support according to the energy consumption support path chain, and obtain the real-time power load of the power-shortage users being supported by the mobile power supply in real time until all power-shortage users have completed the real-time mobile power support.

9. A mobile power scheduling optimization system, characterized in that: include: A load trend determination module is used to obtain user power consumption monitoring logs in the target dispatching area and determine user time series load trend curves based on the user power consumption monitoring logs; A power shortage distribution module is configured to predict the power load in a future time period based on the user time-series load trend curve, obtain power load prediction data, and determine the spatiotemporal distribution of power shortage in the future time period based on the power load prediction data; wherein the spatiotemporal distribution of power shortage is used to characterize the geographical distribution of each power shortage user in each time period in the future time period; a power supply support determination module, configured to determine a power supply support sequence for the mobile power source based on the spatiotemporal distribution of power shortages and the power priority of each power shortage user; wherein the power supply support sequence for the mobile power source is a user support order generated from high to low based on the power priority of each power shortage user; a support path planning module, configured to perform shortest path planning on the power supply support sequence of the mobile power source and generate a support path chain for the mobile power source; a path energy consumption optimization module, configured to perform path energy consumption prediction on the support path chain of the mobile power supply, and optimize the support path chain of the mobile power supply according to the path energy consumption prediction result to obtain an energy consumption support path chain in which the remaining charge of the mobile power supply satisfies the path energy consumption prediction result; The path real-time optimization module is used to optimize the remaining unexecuted energy consumption support path chains according to the minimum power load of each of the power-scarce users during the process of the mobile power supply performing real-time mobile power support according to the energy consumption support path chain, and continue to perform real-time mobile power support for the remaining power-scarce users according to the optimized energy consumption support path chains.

10. An electronic device, characterized in that: The electronic device includes a memory and a processor, wherein a computer program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of the mobile power scheduling optimization method according to any one of claims 1 to 8.

Images