Rapid shelter deployment temporary power supply method and system suitable for large-scale activities

Abstract

The invention provides a temporary power supply method and system for rapidly deploying shelters suitable for large-scale activities. According to the method, a geographic information system is used for collecting position data and climate conditions of a large-scale activity site and generating a general situation of the large-scale activity site; based on the general situation of the large-scale activity site, applying a simulated annealing algorithm, controlling transportation cost and time efficiency, searching an optimal warehouse selection scheme, and combining a vehicle path optimization technology to generate a shelter scheduling plan; on the basis of the shelter dispatching plan, using a deep belief network to predict power demands in different time periods, and combining a dynamic load balancing technology to monitor power distribution in real time and generate a power supply optimization strategy; and based on the power supply optimization strategy, analyzing actual power consumption data, evaluating a power supply effect, and generating a rapid shelter deployment scheme. According to the technical scheme, the power supply reliability and efficiency of the large-scale activity site can be improved, and the transportation and operation cost is reduced.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of mobile cabin power supply, and particularly to a method and system for quickly deploying temporary power supply for mobile cabins applicable to large-scale events. Background Art

[0002] With the increasing number and expanding scale of large-scale events, the power supply system needs to comprehensively evaluate the power demand based on the location of the event venue, climate conditions, and historical power consumption data, and quickly deploy mobile cabins to provide temporary power supply. At the same time, the system also needs to have the ability to optimize power distribution, monitor power usage in real time, and evaluate the power supply effect to ensure the smooth progress of the event and the efficient utilization of energy.

[0003] Currently, for the power supply of large-scale events, traditional power dispatching and management methods are usually adopted. This method mainly relies on manual experience for power demand prediction and distribution, lacking intelligent and automated support. In terms of the deployment and dispatching of mobile cabins, it also often relies on manual judgment and experience-based decision-making, making it difficult to achieve precise control over transportation costs, timeliness, and power demand.

[0004] The traditional method mainly relies on manual experience for power demand prediction, making it difficult to accurately reflect the actual power consumption situation of large-scale event venues. This may lead to insufficient or excessive power supply, affecting the normal progress of the event and the efficient utilization of energy; in terms of the deployment and dispatching of mobile cabins, the existing solutions lack intelligent support, making it difficult to achieve precise control over transportation costs, timeliness, and power demand. This may result in a slow deployment speed of mobile cabins and an inability to meet the urgent needs of large-scale events. Summary of the Invention

[0005] The embodiments of the present application provide a method and system for quickly deploying temporary power supply for mobile cabins applicable to large-scale events, aiming to solve the problem in the prior art that it is difficult to achieve precise control over transportation costs, timeliness, and power demand.

[0006] In a first aspect, the embodiments of the present application provide a method for quickly deploying temporary power supply for mobile cabins applicable to large-scale events, including:

[0007] Using a geographic information system, collecting and integrating the location data and climate conditions of the large-scale event venue, and combining with historical power consumption data to generate an overview of the large-scale event venue;

[0008] Based on the overview of the large-scale event venue, using the simulated annealing algorithm to control transportation costs and timeliness, searching for the optimal warehouse selection plan, and combining with vehicle routing optimization technology to plan the specific transportation route and generate a mobile cabin dispatching plan;

[0009] Based on the cabin scheduling plan, use a deep belief network to predict the power demand at different times in a large event venue. Combine dynamic load balancing technology to monitor the power distribution of each cabin in real time and generate an optimized power supply strategy.

[0010] Based on the optimized power supply strategy, analyze the actual power consumption data during the large event, evaluate the power supply effect and energy use efficiency, and combine the cabin deployment rate to generate a rapid deployment cabin plan.

[0011] Optionally, based on the overview of the large event venue, use the simulated annealing algorithm to control the transportation cost and timeliness, search for the optimal warehouse selection plan, combine vehicle routing optimization technology, plan the specific transportation route, and generate a cabin scheduling plan, including:

[0012] Based on the overview of the large event venue, analyze and evaluate potential problems during the large event, determine the required cabin types and quantities, and generate a cabin demand report.

[0013] Based on the cabin demand report, use the simulated annealing algorithm to gradually approach the global optimal solution through multiple iterations, comprehensively consider various factors, control the transportation cost and timeliness, and generate the optimal warehouse selection plan.

[0014] Based on the optimal warehouse selection plan, combine vehicle routing optimization technology, analyze the road conditions and transportation time, plan the specific transportation route of the cabin, and generate a transportation route plan.

[0015] Based on the transportation route plan, make real-time adjustments in combination with the actual transportation situation, improve the overall deployment efficiency, and respond to emergencies through a real-time monitoring feedback mechanism to generate a cabin scheduling plan.

[0016] Optionally, the method of using the simulated annealing algorithm to gradually approach the global optimal solution through multiple iterations, comprehensively consider various factors, control the transportation cost and timeliness, and generate the optimal warehouse selection plan based on the cabin demand report includes:

[0017] Based on the cabin demand report, analyze the key factors of different warehouses, construct a comprehensive evaluation index system, and generate a warehouse selection evaluation criterion.

[0018] Based on the warehouse selection evaluation criterion, use the simulated annealing algorithm to initialize the warehouse selection plan, set the temperature parameter and cooling coefficient, and gradually approach the global optimal solution through multiple iterations to generate a candidate warehouse plan.

[0019] Based on the candidate warehouse plan, compare and analyze the comprehensive evaluation index system, and use an acceptance probability function to prevent the simulated annealing algorithm from falling into a local optimum to generate a preliminary warehouse selection result.

[0020] Based on the preliminary warehouse selection results, a preset maximum number of iterations is set, and the multiple iterations are repeated. Considering multiple factors comprehensively, an optimal warehouse selection plan is generated.

[0021] Optionally, based on the warehouse selection evaluation criteria, the simulated annealing algorithm is used to initialize the warehouse selection plan, set the temperature parameter and the cooling coefficient, and gradually approach the global optimal solution through multiple iterations to generate a candidate warehouse plan, including:

[0022] Based on the warehouse selection evaluation criteria, data cleaning is performed on the key data of each warehouse to obtain key features. The analytic hierarchy process is used to determine the weights of the key features to generate a comprehensive evaluation index;

[0023] The comprehensive evaluation index is calculated through the following formula:

[0024]

[0025] where, E i is the comprehensive evaluation index of the i-th warehouse; j is the index of the key factor, ranging from 1 to n; n is the number of key factors; w j is the weight of the j-th key factor; f j (x i ) is the score of the i-th warehouse on the j-th key factor; d i is the distance from the i-th warehouse to the activity site; α and β are constants used to adjust the influence of the distance on the comprehensive evaluation index; λ is the coefficient to adjust the influence of the inventory cost; c i is the inventory cost of the i-th warehouse;

[0026] Based on the comprehensive evaluation index, considering the temperature sensitivity coefficient, reasonable initial temperature and cooling coefficient are set, and periodic influence and standardization processing parameters are introduced for multi-factor adjustment to generate a candidate plan score;

[0027] The candidate plan score is calculated through the following formula:

[0028]

[0029] where, S i is the candidate plan score of the i-th warehouse; E iis the initial comprehensive evaluation index for the i-th warehouse; η is the coefficient for adjusting the periodic influence; ω is the frequency of the periodic influence; φ is the phase shift in the sine function; μ is the coefficient for adjusting the logarithmic term influence that varies with the increase in temperature; γ is the temperature sensitivity coefficient for adjusting the influence of temperature on the comprehensive evaluation index; κ is the coefficient for adjusting the influence of the Gaussian kernel function; ∈ is a small positive number used to avoid a zero denominator; δ is the coefficient for adjusting the influence of temperature change on the comprehensive evaluation index; θ is the frequency in the cosine function; ψ is the phase shift in the cosine function; v is the coefficient for adjusting the square root term influence that varies with the increase in temperature; ρ is the coefficient for adjusting the distance normalization influence; τ is the coefficient for adjusting the inventory cost normalization influence; is the average value of the comprehensive evaluation indices of all warehouses; σ is the standard deviation of the comprehensive evaluation indices of all warehouses; is the average value of the distances from all warehouses to the event venue; σ d is the standard deviation of the distances from all warehouses to the event venue; is the average value of the inventory costs of all warehouses; σ c is the standard deviation of the inventory costs of all warehouses; T is the current temperature; d i is the distance from the i-th warehouse to the event venue; c i is the inventory cost of the i-th warehouse;

[0030] Based on the scores of the candidate solutions, all candidate warehouses are sorted and screened. Through multiple iterations, the global optimal solution is gradually approximated. Considering multiple dimensional factors comprehensively, the unit cost efficiency is maximized to generate a candidate warehouse solution.

[0031] Optionally, based on the optimal warehouse selection solution, combined with vehicle routing optimization technology, analyze the road conditions and transportation time, plan the specific transportation routes for the mobile shelters, and generate a transportation route plan, including:

[0032] Based on the optimal warehouse selection solution, combined with the location data of the large-scale event venue, comprehensively analyze the influencing factors of the road environment, evaluate the road conditions during the transportation process, and generate a transportation environment assessment report;

[0033] Based on the transportation environment assessment report, use vehicle routing optimization technology to optimize the transportation time, determine the preliminary transportation route and time arrangement, and generate a preliminary transportation plan;

[0034] Based on the preliminary transportation route plan, simulate the actual transportation process through simulation software, evaluate the feasibility and efficiency of the transportation plan, optimize and adjust the preliminary transportation route and time arrangement, and generate an optimized transportation plan;

[0035] Based on the optimized transportation plan, combined with the actual transportation conditions, formulate a transportation execution plan, determine the specific details of the transportation route, and generate a transportation route plan.

[0036] Optionally, based on the scheduling plan of the mobile cabin, use a deep belief network to predict the power demand at different times in a large event venue, and combine dynamic load balancing technology to monitor the power distribution of each mobile cabin in real time, and generate an optimized power supply strategy, including:

[0037] Based on the scheduling plan of the mobile cabin and combined with historical power consumption data, preliminarily analyze the power consumption pattern during large events and generate a preliminary power demand assessment;

[0038] Based on the preliminary power demand assessment, use a deep belief network to predict the power demand at different time periods in a large event venue and generate a power demand prediction report;

[0039] Based on the power demand prediction report, combine dynamic load balancing technology to establish a power distribution monitoring system, monitor the power output and load status of each mobile cabin in real time, and generate a real-time power distribution plan;

[0040] Based on the real-time power distribution plan, comprehensively consider potential emergencies during large events, formulate emergency handling measures, and generate an optimized power supply strategy.

[0041] Optionally, based on the preliminary power demand assessment, use a deep belief network to predict the power demand at different time periods in a large event venue and generate a power demand prediction report, including:

[0042] Based on the preliminary power demand assessment, extract the required input parameter data, perform normalization processing, extract time series features, and generate an input data set;

[0043] Based on the input data set, use a deep belief network, combine historical power consumption patterns and the characteristics of the large event venue, and learn through a multi-layer neural network structure to generate a power demand prediction model;

[0044] Based on the power demand prediction model, predict the power demand at different time periods in a large event venue and generate a power demand prediction result;

[0045] Based on the power demand prediction result, identify peak and trough time periods, analyze the power demand at different time periods in detail, and generate a power demand prediction report.

[0046] Optionally, based on the input data set, use a deep belief network, combine historical power consumption patterns and the characteristics of the large event venue, and learn through a multi-layer neural network structure to generate a power demand prediction model, including:

[0047] Based on the input data set, select the characteristic parameters that significantly affect the power demand prediction, perform Z-value standardization processing to unify the dimension range, extract periodic and seasonal features, and set a reasonable number of hidden layer nodes to generate activation values;

[0048] The activation value is calculated by the following formula:

[0049]

[0050] where h j is the activation value of the j-th hidden layer node; i is the feature index of the input data set, ranging from 1 to m; m is the number of features of the input data set; w ij is the weight from the i-th node in the input layer to the j-th node in the hidden layer; x i is the i-th feature value of the input data set; b j is the bias of the j-th node in the hidden layer; σ is the activation function; γ is the coefficient for adjusting the influence of the sine function; max(x i ) is the maximum value of the input features;

[0051] Based on the activation value, the weights and biases from the hidden layer to the output layer are initialized. Through the multi-layer neural network structure, combined with historical electricity consumption patterns and the characteristics of large event venues, the activation values of the hidden layer nodes are further processed to generate prediction values;

[0052] The prediction value is calculated by the following formula:

[0053]

[0054] where y k is the prediction value of the k-th output layer node; j is the index of the hidden layer node, ranging from 1 to n; n is the number of hidden layer nodes; v jk is the weight from the j-th node in the hidden layer to the k-th node in the output layer; c k is the bias of the k-th node in the output layer; u jk is the additional weight from the j-th node in the hidden layer to the k-th node in the output layer; d k is the additional bias of the k-th node in the output layer; α and β are the coefficients for adjusting the influence of different activation functions; tanh is the hyperbolic tangent activation function; exp is the exponential function; δ is the coefficient for adjusting the influence of the Gaussian kernel function; is the average value of the activation values of the hidden layer nodes; σ h is the standard deviation of the activation values of the hidden layer nodes; σ is the activation function; h j is the activation value of the j-th hidden layer node; γ is the coefficient for adjusting the influence of the sine function;

[0055] Based on the prediction value, the model hyperparameters are adjusted by the grid search method, and the cross-validation technique is used to evaluate the model performance under different hyperparameter combinations, further improving the model stability and prediction accuracy to generate an electricity demand prediction model.

[0056] Optionally, based on the power supply optimization strategy, analyze the actual power consumption data during large-scale events, evaluate the power supply effect and energy usage efficiency, and combine with the cabin deployment rate to generate a rapid deployment cabin plan, including:

[0057] Based on the power supply optimization strategy, collect the actual power consumption data during large-scale events, perform statistical processing and time series analysis, and generate an actual power consumption data analysis;

[0058] Based on the actual power consumption data analysis, obtain the power supply stability and power distribution balance indicators, evaluate the overall power supply effect, identify the optimization space for energy usage efficiency, and generate a power supply effect evaluation;

[0059] Based on the power supply effect evaluation, combine with the cabin deployment rate, decompose the key links in the deployment process to minimize the cabin deployment time, and generate a cabin deployment rate report;

[0060] Based on the cabin deployment rate report, comprehensively consider the power demand changes during large-scale events, combine with the actual situation of cabin deployment, dynamically adjust the deployment location and recovery process, and generate a rapid deployment cabin plan.

[0061] In a second aspect, an embodiment of the present application provides a rapid deployment cabin temporary power supply system applicable to large-scale events, including:

[0062] A collection module for using a geographic information system to collect and integrate the location data and climate conditions of large-scale event venues, and combine with historical power consumption data to generate an overview of large-scale event venues;

[0063] A search module for, based on the overview of large-scale event venues, using a simulated annealing algorithm to control transportation costs and timeliness, search for an optimal warehouse selection plan, and combine with vehicle routing optimization technology to plan specific transportation routes and generate a cabin scheduling plan;

[0064] A monitoring module for, based on the cabin scheduling plan, using a deep belief network to predict the power demand at different times of large-scale event venues, and combine with dynamic load balancing technology to monitor the power distribution of each cabin in real time and generate a power supply optimization strategy;

[0065] An analysis module for, based on the power supply optimization strategy, analyzing the actual power consumption data during large-scale events, evaluating the power supply effect and energy usage efficiency, and combining with the cabin deployment rate to generate a rapid deployment cabin plan.

[0066] In the embodiments of the present application, a geographic information system is used to collect and integrate the location data and climate conditions of large event venues, and combined with historical electricity consumption data, a general overview of large event venues is generated; based on the general overview of large event venues, a simulated annealing algorithm is used to control transportation costs and timeliness, search for the optimal warehouse selection plan, combined with vehicle routing optimization technology, plan specific transportation routes, and generate a mobile cabin scheduling plan; based on the mobile cabin scheduling plan, a deep belief network is used to predict the electricity demand of large event venues at different times, combined with dynamic load balancing technology, monitor the electricity distribution of each mobile cabin in real time, and generate an optimized electricity supply strategy; based on the optimized electricity supply strategy, analyze the actual electricity consumption data during the large event process, evaluate the power supply effect and energy use efficiency, and combined with the deployment rate of mobile cabins, generate a rapid deployment mobile cabin plan.

[0067] The technical solution of the present application has the following beneficial effects:

[0068] By using a geographic information system, the location data and climate conditions of large event venues are collected and integrated, and combined with historical electricity consumption data, a detailed general overview of large event venues is generated. This not only improves the accuracy and integrity of the data, but also provides a solid foundation for subsequent optimization. Based on the general overview of large event venues, a simulated annealing algorithm is used to control transportation costs and timeliness, search for the optimal warehouse selection plan. Combined with vehicle routing optimization technology, plan specific transportation routes, and generate a mobile cabin scheduling plan. This process effectively reduces transportation costs and improves transportation efficiency, ensuring that the mobile cabins can reach the designated location in a timely manner; based on the mobile cabin scheduling plan, a deep belief network is used to predict the electricity demand of large event venues at different times. Combined with dynamic load balancing technology, monitor the electricity distribution of each mobile cabin in real time, and generate an optimized electricity supply strategy. This not only improves the reliability of the electricity supply, but also effectively avoids waste of electric power resources; based on the optimized electricity supply strategy, analyze the actual electricity consumption data during the large event process, evaluate the power supply effect and energy use efficiency, and combined with the deployment rate of mobile cabins, generate a rapid deployment mobile cabin plan. This process ensures the efficient operation of the power supply system, improves energy utilization efficiency, and also provides valuable experience and data support for future events.

[0069] Furthermore, based on the general situation of the large event venue, analyze and evaluate the problems that may be encountered during the large event, determine the types and quantities of required mobile cabins, and generate a mobile cabin demand report. This helps to identify and solve potential problems in advance, ensuring the smooth progress of the event; based on the mobile cabin demand report, use the simulated annealing algorithm to gradually approach the global optimal solution through multiple iterations, comprehensively consider various factors, control the transportation cost and timeliness, and generate an optimal warehouse selection plan. This process effectively reduces the transportation cost and improves the transportation efficiency; based on the optimal warehouse selection plan, combine vehicle routing optimization technology, analyze the road conditions and transportation time, plan the specific transportation routes of the mobile cabins, and generate a transportation route plan. This ensures that the mobile cabins can reach the designated locations on time and as needed, improving the overall deployment efficiency; based on the transportation route plan, make real-time adjustments in combination with the actual transportation situation, and respond to emergencies through a real-time monitoring feedback mechanism to generate a mobile cabin scheduling plan. This improves the flexibility and responsiveness of the entire logistics system, ensuring that the material supply during the event is not affected.

[0070] Furthermore, based on the mobile cabin scheduling plan, combine historical electricity consumption data, initially analyze the electricity consumption patterns during the large event, and generate a preliminary electricity demand assessment. This provides basic data for subsequent electricity demand forecasting, ensuring the accuracy of the forecasting; based on the preliminary electricity demand assessment, use the deep belief network to predict the electricity demand at different time periods in the large event venue, and generate an electricity demand forecasting report. This process improves the accuracy of the electricity demand forecasting and provides a scientific basis for optimizing the electricity supply; based on the electricity demand forecasting report, combine dynamic load balancing technology, establish an electricity distribution monitoring system, monitor the electricity output and load status of each mobile cabin in real time, and generate a real-time electricity distribution plan. This ensures the balance and stability of the electricity supply and avoids waste of electricity resources; based on the real-time electricity distribution plan, comprehensively consider potential emergencies during the large event, formulate emergency handling measures, and generate an electricity supply optimization strategy. This improves the reliability of the electricity supply system and the ability to respond to emergencies, ensuring the continuous and stable electricity supply during the event.

[0071] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. Brief Description of the Drawings

[0072] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0073] Figure 1Flowchart of a fast-deployment cabin temporary power supply method applicable to large-scale events provided by an embodiment of the present application;

[0074] Figure 2 Schematic structural diagram of a fast-deployment cabin temporary power supply system applicable to large-scale events provided by an embodiment of the present application;

[0075] Figure 3 Schematic structural diagram of a computing device provided by an embodiment of the present application. Detailed implementation manners

[0076] In order to enable those skilled in the art of the present technology to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application.

[0077] In some processes described in the specification and claims of the present application and the above-mentioned drawings, a plurality of operations that appear in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0078] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0079] Figure 1 A flowchart of a fast-deployment cabin temporary power supply method applicable to large-scale events is provided for an embodiment of the present application. As Figure 1 shown, the method includes:

[0080] 101. Use a geographic information system to collect and integrate the location data and climate conditions of the large-scale event venue, and combine historical electricity consumption data to generate an overview of the large-scale event venue;

[0081] A Geographic Information System (GIS) is a system used to capture, store, manipulate, analyze, manage, and display all types of geographical data. It can help users understand and analyze geographical data to make more informed decisions; The location data of large event venues includes information such as the longitude and latitude coordinates, topography, and surrounding infrastructure (such as transportation, power facilities, etc.) of the event venues. These data are used to determine the specific location and environmental conditions of the event venues; The climate conditions include meteorological data such as temperature, humidity, wind speed, and rainfall during the event. These data are used to evaluate the impact of the climate on the event, especially during outdoor activities; The historical electricity consumption data includes data on electricity consumption in past similar events, such as hourly electricity consumption and peak electricity consumption times. These data are used to predict the electricity demand for future events.

[0082] In the embodiments of the present application, first, use GIS tools to collect the location data and climate condition data of large event venues from various sources, and at the same time obtain the electricity consumption data of similar events from historical records; Second, clean, format-convert, and integrate the collected various data to ensure the consistency and integrity of the data; Third, conduct in-depth analysis on the integrated data to extract key information, such as the geographical location of the event venue, climate characteristics, historical electricity consumption patterns, etc.; Finally, based on the analysis results, generate a detailed overview report of the large event venue, which should include information such as the location of the event venue, climate conditions, historical electricity consumption data, etc., providing a basis for subsequent optimization and decision-making.

[0083] Suppose there is a large-scale music festival planned to be held in a park on the outskirts of a certain city; obtain the latitude and longitude coordinates, topographical information of the park, as well as data such as surrounding transportation and power facilities; obtain meteorological data such as temperature, humidity, wind speed, and rainfall during the event from the local meteorological station; obtain data such as hourly electricity consumption and peak electricity consumption time from the records of previous similar music festivals; remove outliers and missing values to ensure the accuracy and integrity of the data; convert data from different sources into a unified format for subsequent processing; integrate location data, climate conditions, and historical electricity consumption data into a database to ensure data consistency and integrity; analyze the geographical location of the park to determine the main entrances, parking lots, stage locations, etc.; evaluate the climate conditions during the event, especially temperature and rainfall, to formulate corresponding countermeasures; analyze historical electricity consumption data to identify peak and off-peak electricity consumption periods and predict the electricity demand during the event; The location overview is that the park is located in the suburbs of the city, with latitude and longitude coordinates of 39.9042, 116.4074. There are two main roads around it, and the nearest power facility is 1 kilometer away from the park. The main entrances are located in the northeast direction, and the parking lots are distributed on the south and west sides; The climate overview is that the expected temperature during the event is between 20-30°C, the humidity is about 60%, there is no obvious rainfall, and the wind speed is moderate. It is recommended to increase sunshade facilities to cope with high temperatures; The electricity consumption overview is that according to historical data, the hourly electricity consumption during the event is between 1000-3000 kilowatts, and the peak electricity consumption time usually appears between 7-10 pm. It is recommended to increase power supply during this period to ensure the smooth progress of the event.

[0084] Through the above steps, a detailed report on the overview of the large-scale event venue is generated, providing important data support for subsequent mobile cabin scheduling, electricity demand prediction, and optimization.

[0085] 102. Based on the overview of the large-scale event venue, use the simulated annealing algorithm to control transportation costs and timeliness, search for the optimal warehouse selection plan, combine vehicle routing optimization technology, plan specific transportation routes, and generate a mobile cabin scheduling plan;

[0086] The overview of the large-scale event venue includes the location data, climate conditions, and historical electricity consumption data of the event venue, which are used to comprehensively understand the basic situation of the event venue; the simulated annealing algorithm is a global optimization algorithm that gradually approaches the global optimal solution by simulating the metal annealing process and is suitable for solving complex optimization problems; transportation costs include transportation fees, fuel costs, labor costs, etc., which are used to evaluate the economic costs during transportation; timeliness refers to the time requirements during transportation to ensure that the mobile cabin can arrive at the designated location on time; vehicle routing optimization technology improves transportation efficiency by optimizing the driving routes of vehicles, reducing transportation time and costs; the mobile cabin scheduling plan includes the transportation routes, time arrangements, and allocation plans of the mobile cabins to ensure that the mobile cabins can arrive at the event venue efficiently and on time.

[0087] In the embodiments of the present application, first, based on the general situation of the large-scale event venue, potential problems during the event are analyzed, the types and quantities of required mobile cabins are determined, and a mobile cabin demand report is generated; second, the simulated annealing algorithm is used to gradually approach the global optimal solution through multiple iterations, comprehensively considering transportation costs and timeliness, and an optimal warehouse selection plan is generated; third, based on the optimal warehouse selection plan, combined with vehicle routing optimization technology, the road conditions and transportation time are analyzed, and the specific transportation routes of the mobile cabins are planned to generate a transportation route plan; finally, real-time adjustments are made in combination with the actual transportation situation, and emergency situations are handled through a real-time monitoring feedback mechanism to generate a mobile cabin scheduling plan to ensure the overall deployment efficiency.

[0088] Optionally, the step of, based on the general situation of the large-scale event venue, using the simulated annealing algorithm, controlling transportation costs and timeliness, searching for an optimal warehouse selection plan, combining vehicle routing optimization technology, planning specific transportation routes, and generating a mobile cabin scheduling plan includes: based on the general situation of the large-scale event venue, analyzing and evaluating potential problems during the large-scale event, determining the types and quantities of required mobile cabins, and generating a mobile cabin demand report; based on the mobile cabin demand report, using the simulated annealing algorithm to gradually approach the global optimal solution through multiple iterations, comprehensively considering multiple factors, controlling transportation costs and timeliness, and generating an optimal warehouse selection plan; based on the optimal warehouse selection plan, combining vehicle routing optimization technology, analyzing road conditions and transportation time, planning the specific transportation routes of the mobile cabins, and generating a transportation route plan; based on the transportation route plan, making real-time adjustments in combination with the actual transportation situation, improving the overall deployment efficiency, and handling emergency situations through a real-time monitoring feedback mechanism to generate a mobile cabin scheduling plan.

[0089] Among them, the step of, based on the mobile cabin demand report, using the simulated annealing algorithm to gradually approach the global optimal solution through multiple iterations, comprehensively considering multiple factors, controlling transportation costs and timeliness, and generating an optimal warehouse selection plan includes: based on the mobile cabin demand report, analyzing the key factors of different warehouses, constructing a comprehensive evaluation index system, and generating a warehouse selection evaluation criterion; based on the warehouse selection evaluation criterion, using the simulated annealing algorithm, initializing the warehouse selection plan, setting temperature parameters and cooling coefficients, and gradually approaching the global optimal solution through multiple iterations to generate a candidate warehouse plan; based on the candidate warehouse plan, comparing and analyzing the comprehensive evaluation index system, and using an acceptance probability function to prevent the simulated annealing algorithm from falling into a local optimum to generate a preliminary warehouse selection result; based on the preliminary warehouse selection result, presetting the maximum number of iterations, repeating the multiple iterations, and comprehensively considering multiple factors to generate an optimal warehouse selection plan.

[0090] In this step, the general situation of the large-scale event venue includes the location data, climate conditions, and historical electricity consumption data of the event venue, which are used to comprehensively understand the basic situation of the event venue; the simulated annealing algorithm is a global optimization algorithm that gradually approaches the global optimal solution by simulating the metal annealing process and is suitable for solving complex optimization problems; the transportation cost includes transportation expenses, fuel costs, labor costs, etc., which are used to evaluate the economic costs during transportation; timeliness refers to the time requirements during transportation to ensure that the mobile cabin can reach the designated location on time; the vehicle routing optimization technology optimizes the driving routes of vehicles, reduces transportation time and costs, and improves transportation efficiency; the mobile cabin demand report includes the types and quantities of mobile cabins required during the event, which are used to guide the selection of warehouses and the formulation of transportation plans; the comprehensive evaluation index system is used to evaluate the key factors of different warehouses, such as distance, cost, inventory, etc., and generate warehouse selection evaluation criteria; the acceptance probability function is used to prevent the simulated annealing algorithm from falling into a local optimum, and accepts worse solutions with a certain probability to explore a wider space.

[0091] In the embodiment of the present application, first, based on the general situation of the large-scale event venue, analyze and evaluate potential problems during the large-scale event, determine the types and quantities of required mobile cabins, and generate a mobile cabin demand report; based on the mobile cabin demand report, analyze the key factors of different warehouses, construct a comprehensive evaluation index system, and generate warehouse selection evaluation criteria; second, based on the warehouse selection evaluation criteria, use the simulated annealing algorithm to initialize the warehouse selection plan, set the temperature parameter and cooling coefficient, and gradually approach the global optimal solution through multiple iterations to generate a candidate warehouse plan; third, based on the candidate warehouse plan, compare and analyze the comprehensive evaluation index system, and use the acceptance probability function to prevent the simulated annealing algorithm from falling into a local optimum to generate a preliminary warehouse selection result; finally, based on the preliminary warehouse selection result, preset the maximum number of iterations, repeat multiple iterations, comprehensively consider multiple factors, and generate an optimal warehouse selection plan; based on the optimal warehouse selection plan, combine the vehicle routing optimization technology, analyze the road conditions and transportation time, plan the specific transportation route of the mobile cabin, and generate a transportation route plan; based on the transportation route plan, make real-time adjustments in combination with the actual transportation situation, improve the overall deployment efficiency, and respond to emergencies through a real-time monitoring feedback mechanism to generate a mobile cabin scheduling plan.

[0092] Suppose there is a large-scale outdoor exhibition event planned to be held at an exhibition center in the suburbs. During the event, multiple mobile cabins are needed to be arranged for temporary office and rest;

[0093] First, based on the geographical location, climate conditions, and historical electricity consumption data of the event venue, analyze and evaluate potential problems during the event, determine the types and quantities of required mobile cabins, and generate a mobile cabin demand report; based on the mobile cabin demand report, analyze key factors of different warehouses, including distance, cost, inventory, etc., construct a comprehensive evaluation index system, and generate warehouse selection evaluation criteria; second, based on the warehouse selection evaluation criteria, use the simulated annealing algorithm to initialize the warehouse selection plan, set the initial temperature to 1000, and the cooling coefficient to 0.95, and gradually approach the global optimal solution through multiple iterations to generate a candidate warehouse plan; third, based on the candidate warehouse plan, compare and analyze the comprehensive evaluation index system, and adopt an acceptance probability function to prevent the simulated annealing algorithm from falling into a local optimum, and generate a preliminary warehouse selection result; finally, based on the preliminary warehouse selection result, preset the maximum number of iterations to 1000 times, repeat multiple iterations, comprehensively consider factors such as transportation cost, timeliness, and inventory, and generate an optimal warehouse selection plan; based on the optimal warehouse selection plan, combine vehicle routing optimization technology, analyze road conditions and transportation time, plan the specific transportation routes of the mobile cabins, and generate a transportation route plan; based on the transportation route plan, make real-time adjustments in combination with the actual transportation situation, and respond to emergencies through a real-time monitoring feedback mechanism to generate a mobile cabin scheduling plan to ensure that the mobile cabins can reach the event venue efficiently and on time.

[0094] Through the above steps, a detailed mobile cabin scheduling plan is generated, ensuring the efficient transportation and deployment of mobile cabins during the event, and providing strong support for the successful holding of the event.

[0095] This application takes into account that in order to optimize the warehouse selection plan by comprehensively evaluating indicators and scoring candidate plans, ensure the optimization of transportation cost and timeliness in the mobile cabin scheduling of large event venues, combines the simulated annealing algorithm and multi-factor adjustment, gradually approaches the global optimal solution through multiple iterations, and comprehensively considers various factors such as distance, inventory cost, and periodic influence to ensure that the selected warehouse plan achieves the best balance in terms of cost and efficiency.

[0096] Optionally, based on the warehouse selection evaluation criteria, use the simulated annealing algorithm to initialize the warehouse selection plan, set the temperature parameter and the cooling coefficient, and gradually approach the global optimal solution through multiple iterations to generate a candidate warehouse plan, including:

[0097] Based on the warehouse selection evaluation criteria, perform data cleaning on the key data of each warehouse to obtain key features, and use the analytic hierarchy process to determine the weights of the key features to generate a comprehensive evaluation index;

[0098] Through the following formula, calculate the comprehensive evaluation index:

[0099]

[0100] Among them, E i is the comprehensive evaluation index of the i-th warehouse; j is the index of the key factor, ranging from 1 to n; n is the number of key factors; w j is the weight of the j-th key factor; f j (x i ) is the score of the i-th warehouse on the j-th key factor; d i is the distance from the i-th warehouse to the activity venue; α and β are constants used to adjust the influence of distance on the comprehensive evaluation index; λ is the coefficient to adjust the influence of inventory cost; c i is the inventory cost of the i-th warehouse;

[0101] Based on the comprehensive evaluation index, considering the temperature sensitivity coefficient, set reasonable initial temperature and cooling coefficient, introduce periodic influence and standardization processing parameters, and perform multi-factor adjustment to generate candidate scheme scores;

[0102] Calculate the candidate scheme scores through the following formula:

[0103]

[0104] Among them, S i is the candidate scheme score of the i-th warehouse; E i is the initial comprehensive evaluation index of the i-th warehouse; η is the coefficient to adjust the periodic influence; ω is the frequency of the periodic influence; φ is the phase shift in the sine function; μ is the coefficient to adjust the influence of the logarithmic term that changes with the increase of temperature; γ is the temperature sensitivity coefficient used to adjust the influence of temperature on the comprehensive evaluation index; κ is the coefficient to adjust the influence of the Gaussian kernel function; ∈ is a small positive number used to avoid the denominator being zero; δ is the coefficient to adjust the influence of temperature change on the comprehensive evaluation index; θ is the frequency in the cosine function; ψ is the phase shift in the cosine function; ν is the coefficient to adjust the influence of the square root term that changes with the increase of temperature; ρ is the coefficient to adjust the influence of distance standardization; τ is the coefficient to adjust the influence of inventory cost standardization; is the average value of the comprehensive evaluation indexes of all warehouses; σ is the standard deviation of the comprehensive evaluation indexes of all warehouses; is the average value of the distances from all warehouses to the activity venue; σ d is the standard deviation of the distances from all warehouses to the activity venue; is the average value of the inventory costs of all warehouses; σ c is the standard deviation of the inventory costs of all warehouses; T is the current temperature; d i is the distance from the i-th warehouse to the activity venue; c i is the inventory cost of the i-th warehouse;

[0105] Based on the candidate solution scores, all candidate warehouses are sorted and screened. Through multiple iterations, the global optimal solution is gradually approximated. Considering multiple-dimensional factors comprehensively, the unit cost efficiency is maximized to generate candidate warehouse solutions.

[0106] This method aims to select the optimal warehouse solution when scheduling mobile cabins in large event venues, considering various factors comprehensively, improving transportation efficiency and reducing costs. This formula generates comprehensive evaluation indicators and candidate solution scores through the simulated annealing algorithm and multi-factor adjustment, gradually approaching the global optimal solution.

[0107] In the comprehensive evaluation indicators, the key factor score item w j ·f j (x i ): Considering the weights and scores of each key factor to ensure the comprehensiveness of the comprehensive evaluation; the distance adjustment item adjusts the impact of distance on the comprehensive evaluation indicators to ensure that warehouses with closer distances are given priority; the inventory cost adjustment item λ·log(1 + c i ): Adjusts the impact of inventory cost on the comprehensive evaluation indicators to ensure that warehouses with lower inventory costs are given priority;

[0108] Among them, w j is determined by the analytic hierarchy process; the key factor score f j (x i ) is obtained through data cleaning; α and β are constants, set according to actual needs; d i is the distance from the warehouse to the event venue, obtained through the geographic information system; λ is a constant, set according to actual needs; c i is the inventory cost of the warehouse, obtained through the warehouse management system;

[0109] In the candidate solution scores, the initial comprehensive evaluation indicator item E i : As the basic score to ensure the comprehensiveness of the score; the periodic influence item η·sin(ω·T + φ): Adjusts the periodic influence to ensure that the score changes with time; the temperature logarithm influence item μ·log(1 + γ·T): Adjusts the logarithmic term influence that changes with the increase in temperature to ensure that the score changes with temperature; the Gaussian kernel function item adjusts the Gaussian kernel function influence to ensure the smoothness of the score; the temperature-sensitive item (T + ∈) γ : Adjusts the impact of temperature on the comprehensive evaluation indicators to ensure that the score changes with temperature; the temperature change influence item δ·cos(θ·T + ψ): Adjusts the impact of temperature change on the comprehensive evaluation indicators to ensure that the score changes with temperature; the temperature square root influence item adjusts the square root term influence that changes with the increase in temperature to ensure that the score changes with temperature; the distance normalization influence item Adjust the impact of distance normalization to ensure the fairness of scoring; inventory cost normalization impact item Adjust the impact of inventory cost normalization to ensure the fairness of scoring;

[0110] Among them, E i is the initial comprehensive evaluation index, calculated through the comprehensive evaluation index formula; η, ω, φ are constants, set according to actual needs; T is the current temperature, set through the simulated annealing algorithm; γ is a constant, set according to actual needs; κ is a constant, set according to actual needs; E avg is the average value of the comprehensive evaluation indexes of all warehouses, obtained by calculating the E of all warehouses i and taking the average value; σ is the standard deviation of the comprehensive evaluation indexes of all warehouses, obtained by calculating the E of all warehouses i and calculating the standard deviation; ∈ is a small positive number, set to 0.001; δ, θ, ψ are constants, set according to actual needs; v is a constant, set according to actual needs; ρ is a constant, set according to actual needs; d avg is the average value of the distances from all warehouses to the activity venue, obtained by calculating the d of all warehouses i and taking the average value; σ d is the standard deviation of the distances from all warehouses to the activity venue, obtained by calculating the d of all warehouses i and calculating the standard deviation; τ is a constant, set according to actual needs; c avg is the average value of the inventory costs of all warehouses, obtained by calculating the c of all warehouses i and taking the average value; σ c is the standard deviation of the inventory costs of all warehouses, obtained by calculating the c of all warehouses i and calculating the standard deviation;

[0111] Suppose there is a large outdoor concert planned to be held in the central park of a city, and there are three warehouses A, B, and C. The key factors include distance, inventory cost, and transportation time;

[0112] The weights of the key factors are w 1 = 0.4, w 2 = 0.3, e 3 = 0.3; The scores of the key factors are f 1 (w) = 8, f 1 (B) = 7, f 1 (C) = 6; f 2 (A) = 5, f 2 (B) = 6, f 2 (C) = 7; f 3 (A) = 7, f 3 (B) = 8, f 3 (C) = 9; The distance d A = 10km, dB = 15 km, d C = 20 km; inventory cost c A = 1000 yuan c B = 1500 yuan, c C = 2000 yuan; α = 0.1, β = 5, λ = 0.01; The comprehensive evaluation index is

[0113]

[0114] Assume the parameters T = 100, η = 0.01, ω = 0.1, φ = 0, μ = 0.01, γ = 0.1, κ = 0.1, ∈ = 0.001, δ = 0.01, θ = 0.1, ψ = 0, v = 0.01, ρ = 0.1, τ = 0.1;

[0115]

[0116] Assume the set threshold is 0.9. Since the result S B = 0.91 is greater than the set threshold, it indicates that Warehouse B has the highest comprehensive evaluation and candidate scheme score after comprehensively considering multiple factors such as distance, inventory cost, and transportation time, and is the optimal warehouse choice; Through the above steps, it is possible to comprehensively consider various factors, select the optimal warehouse scheme, improve transportation efficiency, and reduce costs.

[0117] Optionally, based on the optimal warehouse selection scheme, combined with vehicle routing optimization technology, analyze the road conditions and transportation time, plan the specific transportation route of the mobile cabin, and generate a transportation route plan, including:

[0118] Based on the optimal warehouse selection scheme, combined with the location data of the large event venue, comprehensively analyze the influencing factors of the road environment, evaluate the road conditions during the transportation process, and generate a transportation environment assessment report; Based on the transportation environment assessment report, use vehicle routing optimization technology to optimize the transportation time, determine the preliminary transportation route and time arrangement, and generate a preliminary transportation plan; Based on the preliminary transportation route plan, simulate the actual transportation process through simulation software, evaluate the feasibility and efficiency of the transportation plan, optimize and adjust the preliminary transportation route and time arrangement, and generate an optimized transportation plan; Based on the optimized transportation plan, combined with the actual transportation conditions, formulate a transportation execution plan, determine the specific details of the transportation route, and generate a transportation route plan;

[0119] In this step, the optimal warehouse selection plan is the most suitable warehouse selection plan generated by the simulated annealing algorithm, ensuring the lowest transportation cost and the best timeliness; the location data of the large event venue includes information such as the longitude and latitude coordinates, terrain, and surrounding infrastructure of the event venue, which is used to determine the specific location and environmental conditions of the event venue; the road environment impact factors include the width, road conditions, traffic flow, traffic restrictions, etc. of the road, which are used to evaluate the road conditions during transportation; the transportation environment assessment report is an assessment report generated based on the analysis of the road environment impact factors, which is used to guide the selection of transportation routes; the vehicle routing optimization technology reduces the transportation time and cost and improves the transportation efficiency by optimizing the driving routes of vehicles; the simulation software is used to simulate the actual transportation process, evaluate the feasibility and efficiency of the transportation plan, and make optimization adjustments; the transportation execution plan is the specific transportation route and time arrangement to ensure the smooth progress of the transportation process.

[0120] In the embodiment of the present application, first, based on the optimal warehouse selection plan, combined with the location data of the large event venue, comprehensively analyze the road environment impact factors, evaluate the road conditions during transportation, and generate a transportation environment assessment report; second, based on the transportation environment assessment report, use the vehicle routing optimization technology to optimize the transportation time, determine the preliminary transportation route and time arrangement, and generate a preliminary transportation plan; third, based on the preliminary transportation route plan, simulate the actual transportation process through the simulation software, evaluate the feasibility and efficiency of the transportation plan, optimize and adjust the preliminary transportation route and time arrangement, and generate an optimized transportation plan; finally, based on the optimized transportation plan, combined with the actual transportation conditions, formulate a transportation execution plan, determine the specific details of the transportation route, and generate a transportation route plan.

[0121] Suppose there is a large international expo planned to be held at the convention and exhibition center in a city, and multiple mobile cabins need to be arranged for temporary exhibitions and rest areas during the event. First, based on the optimal warehouse selection plan, combined with the location data of the convention and exhibition center, comprehensively analyze the road environment impact factors such as road width, road conditions, traffic flow, and traffic restrictions, evaluate the road conditions during transportation, and generate a transportation environment assessment report; second, based on the transportation environment assessment report, use the vehicle routing optimization technology to optimize the transportation time, determine the preliminary transportation route and time arrangement, and generate a preliminary transportation plan; third, based on the preliminary transportation route plan, simulate the actual transportation process through the simulation software, evaluate the feasibility and efficiency of the transportation plan, optimize and adjust the preliminary transportation route and time arrangement, and generate an optimized transportation plan; finally, based on the optimized transportation plan, combined with the actual transportation conditions, formulate a transportation execution plan, determine the specific details of the transportation route, and generate a transportation route plan to ensure that the mobile cabins can reach the convention and exhibition center efficiently and on time.

[0122] Through the above steps, the efficiency and reliability of the mobile cabin transportation are ensured, providing a solid guarantee for the successful holding of the international expo.

[0123] 103. Based on the mobile cabin scheduling plan, use a deep belief network to predict the power demand at different times in a large event venue. Combine dynamic load balancing technology to monitor the power distribution of each mobile cabin in real time and generate an optimized power supply strategy.

[0124] In this step, the mobile cabin scheduling plan includes the transportation route, time arrangement, and allocation plan of the mobile cabin to ensure that the mobile cabin can reach the event venue efficiently and on time. The deep belief network is a deep learning model that learns through a multi-layer neural network structure and is suitable for complex data prediction tasks. The power demand prediction predicts the power demand at different time periods during the event based on historical power consumption data and the current event situation. The dynamic load balancing technology ensures the balance and stability of power distribution through real-time monitoring and adjustment, avoiding overload and waste. The optimized power supply strategy includes a power distribution plan and emergency handling measures to ensure the continuous and stable power supply during the event.

[0125] In the embodiment of this application, first, based on the mobile cabin scheduling plan and combined with historical power consumption data, preliminarily analyze the power consumption pattern during a large event to generate a preliminary power demand assessment. Second, use a deep belief network to predict the power demand at different time periods in the large event venue to generate a power demand prediction report. Third, based on the power demand prediction report and combined with dynamic load balancing technology, establish a power distribution monitoring system to monitor the power output and load status of each mobile cabin in real time and generate a real-time power distribution plan. Finally, comprehensively consider potential emergencies during the large event, formulate emergency handling measures, and generate an optimized power supply strategy to ensure the reliability and stability of the power supply.

[0126] Optionally, the step 103 of "Based on the mobile cabin scheduling plan, use a deep belief network to predict the power demand at different times in a large event venue. Combine dynamic load balancing technology to monitor the power distribution of each mobile cabin in real time and generate an optimized power supply strategy" includes:

[0127] Based on the mobile cabin scheduling plan and combined with historical power consumption data, preliminarily analyze the power consumption pattern during a large event to generate a preliminary power demand assessment. Based on the preliminary power demand assessment, use a deep belief network to predict the power demand at different time periods in the large event venue to generate a power demand prediction report. Based on the power demand prediction report and combined with dynamic load balancing technology, establish a power distribution monitoring system to monitor the power output and load status of each mobile cabin in real time and generate a real-time power distribution plan. Based on the real-time power distribution plan, comprehensively consider potential emergencies during the large event, formulate emergency handling measures, and generate an optimized power supply strategy.

[0128] In this step, the mobile cabin scheduling plan includes the transportation route, time arrangement, and allocation plan of the mobile cabins to ensure that the mobile cabins can reach the event venue efficiently and on time; the historical electricity consumption data is the electricity consumption data during past similar events at the event venue, which is used to predict future electricity demand; the preliminary electricity demand assessment is an assessment report generated by preliminarily analyzing the electricity consumption pattern during the event based on the historical electricity consumption data and the mobile cabin scheduling plan; the deep belief network is a deep learning model that learns through a multi-layer neural network structure and is suitable for complex data prediction tasks; the electricity demand prediction report is a report generated based on the deep belief network to predict the electricity demand during different time periods of the event; the dynamic load balancing technology ensures the balance and stability of power distribution through real-time monitoring and adjustment, avoiding overload and waste; the power distribution monitoring system is used to monitor the power output and load status of each mobile cabin in real time to ensure the stability and reliability of power supply; the power supply optimization strategy includes a power distribution plan and emergency handling measures to ensure the continuous stability of power supply during the event.

[0129] First, based on the planning of the mobile cabin scheduling, by integrating the historical electricity consumption data, the electricity consumption behavior during large-scale events is preliminarily analyzed to obtain an initial estimate of electricity demand. This step aims to provide an overview of the electricity demand during the event; then, using the advanced technology of the deep belief network, based on the preliminarily estimated electricity demand, the electricity demand of the large-scale event venue at different time periods is predicted more accurately. The prediction results will be compiled into an electricity demand prediction report to provide a scientific basis for subsequent power distribution; secondly, based on the electricity demand prediction report, combined with the dynamic load balancing technology, a power distribution monitoring system is constructed. The system can monitor the power output and load status of each mobile cabin in real time to ensure the reasonable distribution of power resources. At the same time, the system will generate a real-time power distribution plan according to the monitoring results to meet the electricity demand during the event; finally, based on the real-time power distribution plan, various emergencies that may occur during large-scale events are fully considered. To cope with these potential risks, a series of emergency handling measures are formulated, and based on this, a power supply optimization strategy is generated. This strategy aims to ensure that the power supply can remain stable and efficient during the event regardless of what happens.

[0130] In the embodiment of this application, assume that there is an international marathon event planned to be held in the central area of a city, and multiple mobile cabins need to be arranged for temporary medical stations, supply stations, and rest areas during the event;

[0131] First, based on the mobile cabin scheduling plan and combined with historical electricity consumption data, initially analyze the electricity consumption patterns during large-scale events to generate a preliminary electricity demand assessment. In this step, collect the electricity consumption data of past similar marathon events, including the hourly electricity consumption and peak electricity consumption time, etc., and combine the distribution and functions of the mobile cabins to initially estimate the total electricity demand during the event and generate a preliminary electricity demand assessment report. Secondly, based on the preliminary electricity demand assessment, use a deep belief network to predict the electricity demand at different time periods in the large-scale event venue and generate an electricity demand prediction report. Through the deep belief network model, combine historical data and event arrangements to predict the electricity demand at different time periods on the event day and generate a detailed electricity demand prediction report, which includes the hourly electricity consumption prediction and the electricity demand during peak hours. Thirdly, based on the electricity demand prediction report, combine dynamic load balancing technology to establish a power distribution monitoring system to monitor the power output and load status of each mobile cabin in real time and generate a real-time power distribution plan. Through dynamic load balancing technology, monitor the power output and load status of each mobile cabin in real time to ensure the balance and stability of power distribution and generate a real-time power distribution plan, including the power distribution plan and adjustment measures for each time period. Finally, based on the real-time power distribution plan, comprehensively consider potential emergencies during large-scale events, such as a sudden increase in the number of participants or extreme weather, formulate emergency handling measures, and generate an optimized power supply strategy to ensure the continuous and stable power supply during the event. For possible emergencies, such as a sudden increase in the number of participants or extreme weather, formulate emergency handling measures, including the activation of backup power supplies and emergency adjustments to power distribution, and generate an optimized power supply strategy to ensure the continuous and stable power supply during the event.

[0132] Through the above steps, the efficiency and reliability of the power supply during the international marathon event are ensured, providing solid technical support for the smooth progress of the event.

[0133] Optionally, the step of using a deep belief network to predict the electricity demand at different time periods in the large-scale event venue based on the preliminary electricity demand assessment and generating an electricity demand prediction report includes:

[0134] Based on the preliminary electricity demand assessment, extract the required input parameter data, perform normalization processing, extract time series features, and generate an input data set. Based on the input data set, use a deep belief network, combine historical electricity consumption patterns and the characteristics of the large-scale event venue, and learn through a multi-layer neural network structure to generate an electricity demand prediction model. Based on the electricity demand prediction model, predict the electricity demand at different time periods in the large-scale event venue and generate an electricity demand prediction result. Based on the electricity demand prediction result, identify peak and trough time periods, and analyze the electricity demand at different time periods in detail to generate an electricity demand prediction report.

[0135] In this step, the preliminary power demand assessment is an assessment report generated by initially analyzing the power consumption pattern during the event based on historical power consumption data and the scheduling plan of the mobile cabin. The input parameter data includes historical power consumption, time series characteristics, event venue characteristics, etc., which are used as the input for the deep belief network. The normalization process converts data of different scales to the same scale to ensure the stability and accuracy of model training. The time series characteristics include features such as time, date, and season, which are used to capture the time pattern of the power consumption pattern. The deep belief network is a deep learning model that learns through a multi-layer neural network structure and is suitable for complex data prediction tasks. The power demand prediction model is a model generated by training the deep belief network and is used to predict the power demand during different time periods of the event. The power demand prediction report is a detailed report generated based on the power demand prediction results and includes the analysis of power consumption during peak and trough time periods.

[0136] First, based on the preliminary power demand assessment, extract the necessary input parameter data, and then normalize these data to ensure the consistency and comparability of the data. On this basis, further refine the time series characteristics to construct a comprehensive and accurate input data set. Second, introduce the deep belief network, combine the historical power consumption pattern and the characteristics of the large event venue, and let the deep belief network perform deep learning and optimization through its multi-layer neural network structure to generate a model that can accurately predict the power demand. Third, conduct a detailed prediction of the power demand of the large event venue at different time periods, and through the operation and reasoning of the model, obtain the power demand prediction results for each time period. Finally, based on these power demand prediction results, deeply analyze the peak and trough time periods of the power demand, elaborate in detail the power consumption at different time periods, compile a power demand prediction report, provide comprehensive power demand information, and provide strong support for formulating a scientific and reasonable power supply strategy.

[0137] In the embodiment of this application, assume that there is a large international science and technology exhibition planned to be held at the convention and exhibition center in a city. During the event, multiple mobile cabins need to be arranged for temporary exhibition halls, rest areas, and catering services;

[0138] First, based on the preliminary power demand assessment, extract the required input parameter data, including historical electricity consumption, time series features, and event venue features, and perform normalization to generate an input data set. In this step, collect the electricity consumption data of past similar science and technology exhibitions, including hourly electricity consumption, peak electricity consumption time, etc., combine the layout and functions of the event venue, extract time series features such as hourly, daily, weekly periodic features, and perform normalization to generate an input data set. Second, based on the generated input data set, use a deep belief network, combine historical electricity consumption patterns with large event venue features, and learn through a multi-layer neural network structure to generate a power demand prediction model. Through the deep belief network model, combine historical electricity consumption data and event arrangements to train the model to predict the power demand during the event and generate a power demand prediction model. Third, based on the power demand prediction model, predict the power demand of the large event venue at different time periods to generate a power demand prediction result, including hourly electricity consumption and power demand during peak hours. Through the power demand prediction model, predict the power demand at different time periods on the event day to generate a detailed power demand prediction result, including hourly electricity consumption prediction and power demand during peak hours in the report. Finally, based on the power demand prediction result, identify peak and trough time periods, analyze the power demand at different time periods in detail, and generate a power demand prediction report. The report details the peak and trough hours of electricity consumption during the event, as well as the electricity consumption prediction for each period, providing a scientific basis for optimizing power supply. For the prediction result, identify the peak and trough hours of electricity consumption, analyze the electricity consumption of each period in detail, and generate a power demand prediction report, including the electricity consumption prediction for each period and the recommended power distribution plan, providing a scientific basis for optimizing power supply during the event.

[0139] Through the above steps, the efficiency and reliability of power supply during large international science and technology exhibitions are ensured, providing strong technical support for the smooth progress of the event.

[0140] Optionally, based on the input data set, use a deep belief network, combine historical electricity consumption patterns with large event venue features, and learn through a multi-layer neural network structure to generate a power demand prediction model, including:

[0141] Based on the input data set, select the characteristic parameters that significantly affect power demand prediction, perform Z-value standardization to unify the dimension range, extract periodic and seasonal features, and set a reasonable number of hidden layer nodes to generate activation values.

[0142] Calculate the activation value through the following formula:

[0143]

[0144] where h jis the activation value of the j-th hidden layer node; i is the feature index of the input data set, ranging from 1 to m; m is the number of features of the input data set; w ij is the weight from the i-th node in the input layer to the j-th node in the hidden layer; x i is the i-th feature value of the input data set; b j is the bias of the j-th node in the hidden layer; σ is the activation function; γ is the coefficient that adjusts the influence of the sine function; max(x i ) is the maximum value of the input features;

[0145] Based on the activation value, initialize the weights and biases from the hidden layer to the output layer, and through the multi-layer neural network structure, combine the historical electricity consumption patterns and the characteristics of large event venues to further process the activation values of the hidden layer nodes to generate predicted values;

[0146] Calculate the predicted value through the following formula:

[0147]

[0148] where y k is the predicted value of the k-th output layer node; j is the index of the hidden layer node, ranging from 1 to n; n is the number of hidden layer nodes; v jk is the weight from the j-th node in the hidden layer to the k-th node in the output layer; c k is the bias of the k-th node in the output layer; u jk is the additional weight from the j-th node in the hidden layer to the k-th node in the output layer; d k is the additional bias of the k-th node in the output layer; α and β are the coefficients that adjust the influence of different activation functions; tanh is the hyperbolic tangent activation function; exp is the exponential function; δ is the coefficient that adjusts the influence of the Gaussian kernel function; is the average value of the activation values of the hidden layer nodes; σ h is the standard deviation of the activation values of the hidden layer nodes; σ is the activation function; h j is the activation value of the j-th hidden layer node; γ is the coefficient that adjusts the influence of the sine function;

[0149] Based on the predicted value, adjust the model hyperparameters through the grid search method, use the cross-validation technique to evaluate the model performance under different hyperparameter combinations, further improve the model stability and prediction accuracy, and generate the electricity demand prediction model.

[0150] Among the activation values, the weight term from the input layer to the hidden layer maps the input feature x ij to the hidden layer through the weight w i from the i-th node in the input layer to the j-th node in the hidden layer, ensuring the importance and weight of the features; the bias term b j : the bias b of the j-th node in the hidden layerj , which is used to adjust the activation value of the hidden layer nodes to ensure the flexibility of the model; periodic feature term Extracts periodic features through the sine function to ensure the sensitivity of the model to time features;

[0151] Among them, w ij is the weight from the i-th node of the input layer to the j-th node of the hidden layer, obtained through model training; x i is the i-th feature value of the input data set, obtained through data preprocessing; b j is the bias of the j-th node of the hidden layer, obtained through model training; γ is the coefficient that adjusts the influence of the sine function, set according to actual needs; max(x i ) is the maximum value of the input features, obtained through data preprocessing;

[0152] In the predicted value, the weight term from the hidden layer to the output layer maps the activation value h jk of the hidden layer to the output layer through the weight v j from the j-th node of the hidden layer to the k-th node of the output layer to ensure the transfer of features; the bias term c k : the bias c k of the k-th node of the output layer, which is used to adjust the activation value of the output layer nodes to ensure the flexibility of the model; the additional weight term of the hyperbolic tangent activation function enhances the nonlinear ability of the model through the additional weight u jk from the j-th node of the hidden layer to the k-th node of the output layer; the additional bias term d k : the additional bias d k of the k-th node of the output layer, which is used to adjust the activation value of the output layer nodes to ensure the flexibility of the model; the logarithmic transformation term β·log(1+exp(-γ·h j )): performs a logarithmic transformation on the activation value to enhance the nonlinear ability of the model; the Gaussian kernel function term Gaussian kernel function is processed through the Gaussian kernel function to ensure the robustness of the model to outliers;

[0153] Among them, h j is the activation value of the j-th node of the hidden layer, obtained through the activation value calculation term; σ is the activation function, usually the Sigmoid or ReLU function; v jk is the weight from the j-th node of the hidden layer to the k-th node of the output layer, obtained through model training; c k is the bias of the k-th node of the output layer, obtained through model training; u jk is the additional weight from the j-th node of the hidden layer to the k-th node of the output layer, obtained through model training; d kIt is the additional bias of the k-th node in the output layer, obtained through model training; α is the coefficient for adjusting the influence of different activation functions, set according to actual needs; β is the coefficient for adjusting the influence of logarithmic transformation, set according to actual needs; is the average value of the activation values of the hidden layer nodes, obtained by calculating the activation values of all hidden layer nodes and taking the average; σ h is the standard deviation of the activation values of the hidden layer nodes, obtained by calculating the activation values of all hidden layer nodes and calculating the standard deviation; δ is the coefficient for adjusting the influence of the Gaussian kernel function, set according to actual needs; y k is the predicted value of the k-th output layer node, obtained through the predicted value calculation term;

[0154] Suppose there is a large band performance, and the power demand needs to be predicted during the event;

[0155] Suppose the parameter w 11 = 0.5, w 12 = 0.3, w 13 = 0.2, w 14 = 0.1, w 15 = 0.1, w 16 = 0.1, w 17 = 0.1; x 1 = 8, x 2 = 1, x 3 = 18, x 4 = 0, x 5 = 1000, x 6 = 5000, x 7 = 25; b 1 = 0.1; γ = 0.1; max(x 1 ) = 10, max(x 2 ) = 31, max(x 3 ) = 23, max(x 4 ) = 1, max(x 5 ) = 1000, max(x 6 ) = 5000, max(x 7 ) = 30; v 11 = 0.6; c 1 = 0.2; u 11 = 0.5; d 1 = 0.1; α = 0.1, β = 0.1; δ = 0.1; Activation value Predicted value

[0156]

[0157] Assume that the set threshold is 0.9. Since the result 0.723 is less than the set threshold, it indicates that during this time period, the predicted value of power demand is low and there is no need to particularly increase the preparation for power supply. Through the above steps, a power demand prediction model is finally generated, ensuring the efficiency and reliability of power supply during the event.

[0158] 104. Based on the power supply optimization strategy, analyze the actual power consumption data during the large-scale event, evaluate the power supply effect and energy use efficiency, and combine with the deployment rate of the mobile cabin to generate a rapid deployment mobile cabin plan.

[0159] In this step, the power supply optimization strategy includes a power distribution plan and emergency handling measures to ensure the continuous and stable power supply during the event; the actual power consumption data is the actual power consumption data during the event, which is used to evaluate the power supply effect and energy use efficiency; the power supply effect refers to whether the power supply meets the event requirements, including the stability and reliability of the power supply; the energy use efficiency refers to the utilization efficiency of power resources, including the rationality and economy of power consumption; the deployment rate of the mobile cabin refers to the deployment speed and efficiency of the mobile cabin during the event to ensure that the mobile cabin can arrive in time and be put into use.

[0160] In the embodiment of the present application, first, based on the power supply optimization strategy, collect and analyze the actual power consumption data during the large-scale event, and evaluate the power supply effect and energy use efficiency; second, according to the evaluation results, identify the deficiencies and improvement points in the power supply, optimize the power distribution plan, and improve the energy use efficiency; third, combine with the deployment rate of the mobile cabin, analyze the deployment speed and efficiency of the mobile cabin to ensure that the mobile cabin can arrive in time and be put into use; finally, generate a rapid deployment mobile cabin plan, including the transportation arrangement, installation and commissioning, and emergency plan of the mobile cabin, to ensure the efficiency and reliability of the power supply during the event.

[0161] Optionally, the step 104 of analyzing the actual power consumption data during the large-scale event based on the power supply optimization strategy, evaluating the power supply effect and energy use efficiency, and combining with the deployment rate of the mobile cabin to generate a rapid deployment mobile cabin plan includes:

[0162] Based on the power supply optimization strategy, collect the actual electricity consumption data during the large-scale event, conduct statistical processing and time series analysis, and generate the actual electricity consumption data analysis; based on the actual electricity consumption data analysis, obtain the power supply stability and power distribution balance indicators, evaluate the overall effect of power supply, identify the optimization space for energy use efficiency, and generate the power supply effect evaluation; based on the power supply effect evaluation, combined with the cabin deployment rate, decompose the key links in the deployment process to minimize the cabin deployment time, and generate the cabin deployment rate report; based on the cabin deployment rate report, comprehensively consider the changes in power demand during the large-scale event, combined with the actual situation of cabin deployment, dynamically adjust the deployment location and recovery process, and generate the rapid deployment cabin plan.

[0163] In this step, the power supply optimization strategy includes the power distribution plan and emergency treatment measures to ensure the continuous and stable power supply during the event; the actual electricity consumption data is the actual power consumption data during the event, which is used to evaluate the effect of power supply and energy use efficiency; statistical processing and time series analysis extract useful information by conducting statistical processing and time series analysis on the actual electricity consumption data, and generate the actual electricity consumption data analysis report; the power supply stability and power distribution balance indicators are used to evaluate the overall effect of power supply and identify the optimization space for energy use efficiency; the power supply effect evaluation is an evaluation report generated based on the actual electricity consumption data analysis, including the indicators of power supply stability and power distribution balance; the cabin deployment rate refers to the deployment speed and efficiency of the cabin during the event to ensure that the cabin can be in place and put into use in a timely manner; the cabin deployment rate report is a report generated by decomposing the key links in the deployment process to minimize the cabin deployment time; the rapid deployment cabin plan is a plan generated by dynamically adjusting the deployment location and recovery process in combination with the changes in power demand and the actual situation of cabin deployment.

[0164] In the embodiment of this application, first, based on the power supply optimization strategy, collect the actual electricity consumption data during the large-scale event, conduct statistical processing and time series analysis, and generate the actual electricity consumption data analysis; second, based on the actual electricity consumption data analysis, obtain the power supply stability and power distribution balance indicators, evaluate the overall effect of power supply, identify the optimization space for energy use efficiency, and generate the power supply effect evaluation; third, based on the power supply effect evaluation, combined with the cabin deployment rate, decompose the key links in the deployment process to minimize the cabin deployment time, and generate the cabin deployment rate report; finally, based on the cabin deployment rate report, comprehensively consider the changes in power demand during the large-scale event, combined with the actual situation of cabin deployment, dynamically adjust the deployment location and recovery process, and generate the rapid deployment cabin plan.

[0165] Suppose there is a large international art festival planned to be held in the central park of a city, and multiple cabins need to be arranged for temporary exhibition halls, rest areas, and catering services during the event;

[0166] First, based on the power supply optimization strategy, collect the actual electricity consumption data during the large-scale event, conduct statistical processing and time series analysis, and generate an actual electricity consumption data analysis report. In this step, the electricity consumption data per hour during the event is collected and statistically processed, including calculating statistical indicators such as average electricity consumption and standard deviation. At the same time, time series analysis is carried out to identify peak and trough electricity consumption periods, and an actual electricity consumption data analysis report is generated. Secondly, based on the actual electricity consumption data analysis report, obtain the power supply stability and power distribution balance indicators, evaluate the overall effect of the power supply, identify the optimization space for energy use efficiency, and generate a power supply effect evaluation report. By analyzing the actual electricity consumption data, the indicators of power supply stability and power distribution balance are calculated, the overall effect of the power supply is evaluated, the optimization space for energy use efficiency is identified, and a power supply effect evaluation report is generated. Thirdly, based on the power supply effect evaluation report, combined with the cabin deployment rate, decompose the key links in the deployment process to minimize the cabin deployment time and generate a cabin deployment rate report. According to the power supply effect evaluation report, the key links in the cabin deployment process are decomposed, including transportation, installation, commissioning, etc., and the time arrangement for each link is optimized to generate a cabin deployment rate report. Finally, based on the cabin deployment rate report, comprehensively consider the changes in power demand during the large-scale event, combined with the actual situation of cabin deployment, dynamically adjust the deployment location and recovery process, and generate a rapid deployment cabin plan to ensure that the cabin can arrive at and evacuate the event site efficiently and on time, improving the overall event organization efficiency. According to the cabin deployment rate report, combined with the changes in power demand during the event, the deployment location and recovery process of the cabin are dynamically adjusted, and a rapid deployment cabin plan is generated to ensure that the cabin can arrive on time before the event starts and evacuate efficiently after the event ends.

[0167] Through the above steps, the efficiency and reliability of the power supply during the large international art festival are ensured, providing solid technical support for the smooth progress of the event.

[0168] Figure 2 For the embodiment of the present application, a structural schematic diagram of a rapid deployment cabin temporary power supply system applicable to large-scale events is provided, as Figure 2 shown. The device includes:

[0169] A collection module 21, configured to use a geographic information system to collect and integrate the location data and climate conditions of the large-scale event site, and combine historical electricity consumption data to generate an overview of the large-scale event site;

[0170] A search module 22, which is used to generate a temporary shelter scheduling plan by controlling transportation costs and timeliness based on the general situation of the large event venue using the simulated annealing algorithm, searching for the optimal warehouse selection plan, and combining vehicle routing optimization technology to plan specific transportation routes;

[0171] A monitoring module 23, which is used to generate an optimized power supply strategy by predicting the power demand of the large event venue at different times using a deep belief network based on the temporary shelter scheduling plan, and combining dynamic load balancing technology to monitor the power distribution of each temporary shelter in real time;

[0172] An analysis module 24, which is used to generate a rapid deployment temporary shelter plan by analyzing the actual power consumption data during the large event based on the optimized power supply strategy, evaluating the power supply effect and energy use efficiency, and combining the temporary shelter deployment rate;

[0173] Figure 2 The described rapid deployment temporary power supply system for large events can execute Figure 1 The described rapid deployment temporary power supply method for large events in the illustrated embodiment, the implementation principle and technical effects will not be elaborated. For the rapid deployment temporary power supply system for large events in the above embodiment, the specific ways for each module and unit to perform operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0174] In a possible design, Figure 2 The rapid deployment temporary power supply system for large events in the illustrated embodiment can be implemented as a computing device, such as Figure 3 shown, the computing device may include a storage component 31 and a processing component 32;

[0175] The storage component 31 stores one or more computer instructions, where the one or more computer instructions are called and executed by the processing component 32.

[0176] The processing component 32 is used to: collect and integrate the location data and climate conditions of the large event venue using a geographic information system, and generate a general situation of the large event venue in combination with historical power consumption data; based on the general situation of the large event venue, control transportation costs and timeliness using the simulated annealing algorithm, search for the optimal warehouse selection plan, and combine vehicle routing optimization technology to plan specific transportation routes to generate a temporary shelter scheduling plan; based on the temporary shelter scheduling plan, predict the power demand of the large event venue at different times using a deep belief network, and combine dynamic load balancing technology to monitor the power distribution of each temporary shelter in real time to generate an optimized power supply strategy; based on the optimized power supply strategy, analyze the actual power consumption data during the large event, evaluate the power supply effect and energy use efficiency, and combine the temporary shelter deployment rate to generate a rapid deployment temporary shelter plan.

[0177] Among them, the processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0178] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0179] Of course, the computing device may also necessarily include other components, such as input / output interfaces, display components, communication components, etc.

[0180] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above peripheral interface module may be an output device, an input device, etc.

[0181] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0182] Among them, the computing device may be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device may refer to a cloud server, and the above processing component, storage component, etc. may be basic server resources leased or purchased from a cloud computing platform.

[0183] The embodiment of the present application also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above Figure 1 shown embodiment of a rapid deployment temporary power supply method for large-scale event field hospitals.

[0184] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be described herein again.

[0185] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative work.

[0186] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0187] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present application.

Claims

1. A method for temporary power supply of a rapidly deployed shelter suitable for large-scale activities, characterized in that: include: Use geographic information systems to collect and integrate location data and climate conditions of large event venues, combined with historical electricity consumption data, to generate large event venue profiles; Based on the overview of the large-scale event venue, the simulated annealing algorithm is used to control transportation costs and timeliness, search for the optimal warehouse selection plan, combine vehicle path optimization technology, plan specific transportation routes, and generate a shelter scheduling plan; Based on the cabin scheduling plan, a deep belief network is used to predict the power demand of large event venues at different times. Combined with dynamic load balancing technology, the power distribution of each cabin is monitored in real time to generate a power supply optimization strategy. Based on the power supply optimization strategy, the actual power consumption data of large-scale activities is analyzed, the power supply effect and energy efficiency are evaluated, and the rapid deployment of shelters is generated in combination with the shelter deployment rate.

2. The method according to claim 1, characterized in that Based on the overview of the large-scale event venue, the simulated annealing algorithm is used to control the transportation cost and timeliness, search for the optimal warehouse selection plan, combine the vehicle path optimization technology, plan the specific transportation route, and generate the shelter scheduling plan, including: Based on the overview of the large-scale event venue, analyze and evaluate potential problems during the large-scale event, determine the type and number of shelters required, and generate a shelter demand report; Based on the shelter demand report, the simulated annealing algorithm is used to gradually approach the global optimal solution through multiple iterations, comprehensively consider multiple factors, control transportation costs and timeliness, and generate the optimal warehouse selection plan; Based on the optimal warehouse selection scheme, combined with vehicle path optimization technology, the road conditions and transportation time are analyzed, the specific transportation route of the shelter is planned, and the transportation route plan is generated; Based on the transportation route planning, real-time adjustments are made in combination with the actual transportation situation to improve the overall deployment efficiency, respond to emergencies through a real-time monitoring feedback mechanism, and generate a cabin scheduling plan.

3. The method according to claim 2, characterized in that Based on the shelter demand report, the simulated annealing algorithm is used to gradually approach the global optimal solution through multiple iterations, comprehensively consider multiple factors, control transportation costs and timeliness, and generate the optimal warehouse selection plan, including: Based on the shelter demand report, analyze the key factors of different warehouses, build a comprehensive evaluation index system, and generate warehouse selection evaluation criteria; Based on the warehouse selection evaluation criteria, a simulated annealing algorithm is used to initialize the warehouse selection plan, set the temperature parameters and the cooling coefficient, and gradually approach the global optimal solution through multiple iterations to generate candidate warehouse plans; Based on the candidate warehouse solutions, the comprehensive evaluation index system is compared and analyzed, and an acceptance probability function is used to prevent the simulated annealing algorithm from falling into a local optimum, thereby generating a preliminary warehouse selection result; Based on the preliminary warehouse selection result, a maximum number of iterations is preset, the iterations are repeated, and multiple factors are comprehensively considered to generate an optimal warehouse selection plan.

4. The method according to claim 3, characterized in that: Based on the warehouse selection evaluation criteria, the simulated annealing algorithm is used to initialize the warehouse selection scheme, set the temperature parameters and cooling coefficient, and gradually approach the global optimal solution through multiple iterations to generate candidate warehouse schemes, including: Based on the warehouse selection evaluation criteria, the key data of each warehouse is cleaned to obtain key features, and the weights of the key features are determined by using the hierarchical analysis method to generate comprehensive evaluation indicators; The comprehensive evaluation index is calculated by the following formula: Among them, E i is the comprehensive evaluation index of the i-th warehouse; j is the index of the key factor, from 1 to n; n is the number of key factors; w j is the weight of the jth key factor; f j (x i ) is the score of the i-th warehouse on the j-th key factor; d i is the distance from the ith warehouse to the activity site; α and β are constants used to adjust the impact of distance on the comprehensive evaluation index; λ is the coefficient for adjusting the impact of inventory cost; c i is the inventory cost of the i-th warehouse; Based on the comprehensive evaluation index, considering the temperature sensitivity coefficient, setting a reasonable initial temperature and cooling coefficient, introducing periodic influence and standardized processing parameters, and making multi-factor adjustments to generate candidate scheme scores; The candidate solution score is calculated using the following formula: Among them, S i Score the candidate solutions for the i-th warehouse; E i is the initial comprehensive evaluation index of the i-th warehouse; η is the coefficient for adjusting the periodic impact; ω is the frequency of the periodic impact; φ is the phase shift in the sine function; μ is the coefficient for adjusting the logarithmic term that changes with increasing temperature; γ is the temperature sensitivity coefficient, which is used to adjust the impact of temperature on the comprehensive evaluation index; κ is the coefficient for adjusting the impact of the Gaussian kernel function; ∈ is a small positive number used to avoid the situation where the denominator is zero; δ is the coefficient for adjusting the impact of temperature change on the comprehensive evaluation index; θ is the frequency in the cosine function; ψ is the phase shift in the cosine function; v is the coefficient for adjusting the square root term that changes with increasing temperature; ρ is the coefficient for adjusting the impact of distance standardization; τ is the coefficient for adjusting the impact of inventory cost standardization; is the average value of the comprehensive evaluation index of all warehouses; σ is the standard deviation of the comprehensive evaluation index of all warehouses; is the average distance from all warehouses to the activity site; σ d is the standard deviation of the distance from all warehouses to the activity site; is the average inventory cost of all warehouses; σ c is the standard deviation of inventory costs in all warehouses; T is the current temperature; d i is the distance from the i-th warehouse to the activity site; c i is the inventory cost of the i-th warehouse; Based on the candidate solution scores, all candidate warehouses are sorted and screened, and the global optimal solution is gradually approached through multiple iterations. Multi-dimensional factors are comprehensively considered to maximize unit cost efficiency and generate candidate warehouse solutions.

5. The method according to claim 3, characterized in that: Based on the optimal warehouse selection scheme, combined with vehicle path optimization technology, analyzing road conditions and transportation time, planning a specific transportation route for the shelter, and generating a transportation route plan, the method includes: Based on the optimal warehouse selection plan and combined with the location data of the large-scale event venue, comprehensively analyze the factors affecting the road environment, evaluate the road conditions during the transportation process, and generate a transportation environment assessment report; Based on the transportation environment assessment report, use vehicle path optimization technology to optimize transportation time, determine preliminary transportation routes and time arrangements, and generate preliminary transportation plans; Based on the preliminary transportation route planning, the actual transportation process is simulated by simulation software, the feasibility and efficiency of the transportation plan are evaluated, the preliminary transportation route and time arrangement are optimized and adjusted, and an optimized transportation plan is generated; Based on the optimized transportation plan and combined with actual transportation conditions, a transportation execution plan is formulated, the specific details of the transportation route are determined, and a transportation route plan is generated.

6. The method according to claim 1, characterized in that Based on the cabin scheduling plan, the deep belief network is used to predict the power demand of large-scale event venues at different times, and the power distribution of each cabin is monitored in real time in combination with dynamic load balancing technology to generate a power supply optimization strategy, including: Based on the shelter dispatch plan and in combination with historical electricity consumption data, a preliminary analysis of electricity consumption patterns during large-scale events is conducted to generate a preliminary electricity demand assessment; Based on the preliminary power demand assessment, a deep belief network is used to predict the power demand of large event venues at different time periods and generate a power demand forecast report; Based on the power demand forecast report and combined with dynamic load balancing technology, a power distribution monitoring system is established to monitor the power output and load status of each cabin in real time and generate a real-time power distribution plan; Based on the real-time power distribution plan, potential emergencies during large-scale events are comprehensively considered, emergency response measures are formulated, and power supply optimization strategies are generated.

7. The method according to claim 6, characterized in that Based on the preliminary power demand assessment, the deep belief network is used to predict the power demand of large event venues in different time periods, and a power demand forecast report is generated, including: Based on the preliminary power demand assessment, extract required input parameter data, perform normalization processing, extract time series features, and generate an input data set; Based on the input data set, a deep belief network is used to combine historical electricity consumption patterns and characteristics of large-scale event venues, and a multi-layer neural network structure is used to learn and generate a power demand forecasting model; Based on the power demand forecasting model, forecast the power demand of large event venues in different time periods and generate power demand forecasting results; Based on the power demand forecast results, the peak and valley time periods are identified, the power demand in different time periods is analyzed in detail, and a power demand forecast report is generated.

8. The method according to claim 7, characterized in that Based on the input data set, a deep belief network is used to combine historical power consumption patterns and characteristics of large event venues, and a multi-layer neural network structure is used to learn and generate a power demand forecasting model, including: Based on the input data set, characteristic parameters that significantly affect the power demand forecast are selected, Z-value normalization is performed to unify the dimension range, periodicity and seasonality characteristics are extracted, and a reasonable number of hidden layer nodes is set to generate activation values; The activation value is calculated using the following formula: Among them, h j is the activation value of the jth hidden layer node; i is the feature index of the input data set, from 1 to m; m is the number of features of the input data set; w ij is the weight from the i-th node in the input layer to the j-th node in the hidden layer; x i is the i-th eigenvalue of the input data set; b j is the bias of the jth node in the hidden layer; σ is the activation function; γ is the coefficient for adjusting the influence of the sine function; max(x i ) is the maximum value of the input feature; Based on the activation values, weights and biases from the hidden layer to the output layer are initialized, and the activation values ​​of the hidden layer nodes are further processed through a multi-layer neural network structure in combination with historical electricity consumption patterns and characteristics of large-scale event venues to generate prediction values; The predicted value is calculated using the following formula: Among them, y k is the predicted value of the kth output layer node; j is the index of the hidden layer node, from 1 to n; n is the number of hidden layer nodes; v jk is the weight from the jth node in the hidden layer to the kth node in the output layer; c k is the bias of the kth node in the output layer; u jk is the additional weight from the jth node in the hidden layer to the kth node in the output layer; d k is the additional bias of the kth node in the output layer; α and β are coefficients for adjusting the influence of different activation functions; tanh is the hyperbolic tangent activation function; exp is the exponential function; δ is the coefficient for adjusting the influence of the Gaussian kernel function; is the average value of the hidden layer node activation value; σ h is the standard deviation of the hidden layer node activation value; σ is the activation function; h j is the activation value of the jth hidden layer node; γ is the coefficient for adjusting the influence of the sine function; Based on the predicted values, the model hyperparameters are adjusted through the grid search method, and the model performance under different hyperparameter combinations is evaluated using cross-validation technology to further improve the model stability and prediction accuracy, and generate a power demand prediction model.

9. The method according to claim 1, characterized in that: Based on the power supply optimization strategy, the actual power consumption data of large-scale activities is analyzed, the power supply effect and energy efficiency are evaluated, and the rapid deployment plan of shelters is generated in combination with the shelter deployment rate, including: Based on the power supply optimization strategy, actual power consumption data of large-scale activities are collected, statistical processing and time series analysis are performed to generate actual power consumption data analysis; Based on the analysis of the actual power consumption data, power supply stability and power distribution balance indicators are obtained, the overall effect of power supply is evaluated, the optimization space of energy efficiency is identified, and a power supply effect evaluation is generated; Based on the power supply effect evaluation and combined with the shelter deployment rate, the key links of the deployment process are decomposed to minimize the shelter deployment time and generate a shelter deployment rate report; Based on the shelter deployment rate report, the changes in power demand during large-scale events are comprehensively considered, and combined with the actual situation of shelter deployment, the deployment location and recovery process are dynamically adjusted to generate a rapid shelter deployment plan.

10. A temporary power supply system for a rapidly deployable shelter suitable for large-scale activities, characterized in that: include: The collection module is used to use the geographic information system to collect and integrate the location data and climate conditions of large-scale event venues, combined with historical electricity consumption data, to generate an overview of large-scale event venues; A search module is used to control transportation costs and timeliness based on the overview of the large-scale event venue, use simulated annealing algorithm, search for the best warehouse selection solution, combine vehicle path optimization technology, plan specific transportation routes, and generate a shelter scheduling plan; A monitoring module is used to predict the power demand of large event venues at different time periods based on the cabin scheduling plan and using a deep belief network, and to monitor the power distribution of each cabin in real time in combination with dynamic load balancing technology to generate a power supply optimization strategy; The analysis module is used to analyze the actual power consumption data of large-scale activities based on the power supply optimization strategy, evaluate the power supply effect and energy efficiency, and generate a rapid deployment plan for the shelter in combination with the shelter deployment rate.

Images