A method and system for coordination and distribution of mobile power stations

Abstract

The application discloses a kind of coordination and distribution method and system of mobile power station, wherein method includes the following steps: obtaining each regional energy demand information in target range, traffic information between each region, each mobile power station equipment information, each regional environment information;Based on the each regional energy demand information and the each regional environment information, obtain the demand priority of each region;Initialization is dispatched, and the mobile power station corresponding to the each region is matched according to priority from high to low, and the initial matching table is output;The initial matching table is input into improved ant colony algorithm, and iteration optimization is carried out to obtain distribution scheme;Each mobile power station and each region receive and execute the distribution scheme.By the above-mentioned mode, the application can efficiently and quickly issue accurate and reliable dispatching distribution scheme, as far as possible to meet the power demand of each region, effectively save time, improve processing efficiency, meet the demand of special power consumption scene.

Description

Technical Field

[0001] This application relates to the field of power technology, and in particular to a method and system for coordinating and distributing mobile power stations. Background Technology

[0002] With continuous technological advancements, my country's power grid coverage is expanding, the electricity market is deepening, and the development of electrical equipment and devices is broadening. From new energy vehicles to energy storage facilities, the construction of power grid infrastructure is booming. According to my country's annual special report on the power facilities industry, the proportion of electricity in end-use energy consumption has increased significantly in my country's energy electrification, which in turn poses new requirements for the power supply side.

[0003] In this context, new demands have arisen for power supply in special circumstances and areas where the power grid cannot fully cover, such as islands, field operations, outdoor scientific expeditions, and post-disaster reconstruction. While mobile power stations are typically deployed for coordination, complex power supply needs require the rapid development of suitable power supply coordination solutions and the ability to adjust these solutions in real time, a solution that is currently lacking. Summary of the Invention

[0004] In view of this, this application mainly provides a method and system for coordinating and allocating mobile power stations to solve the problem of dispatching mobile power stations in special situations such as emergency response, emergency repair, and outdoor use.

[0005] To solve the above-mentioned technical problems, this application adopts the following technical solution: providing a method for coordinating and allocating mobile power stations, including the following steps:

[0006] S10: Obtain energy demand information for each region within the target area, traffic information between regions, information on mobile power station equipment, and environmental information for each region;

[0007] S20: Based on the energy demand information and environmental information of each region, obtain the demand priority of each region;

[0008] S30: Initialize the scheduling, match the corresponding mobile power station for each region according to the priority from high to low, and output the initial matching table;

[0009] S40: Based on the traffic information between the regions, the mobile power station equipment information, and the environmental information of the regions, set the parameters of the improved ant colony algorithm, and input the initial matching table into the improved ant colony algorithm to iteratively optimize and obtain the allocation scheme;

[0010] S50: Each mobile power station and each region receives and executes the allocation scheme.

[0011] In one possible implementation, after the steps of acquiring energy demand information for each area within the target range, traffic information between areas, information on mobile power station equipment, and environmental information for each area, the process includes:

[0012] S11: Perform data cleaning, data completion, and confidence calculation on the energy demand information of each region, the traffic information between each region, the mobile power station equipment information, and the environmental information of each region.

[0013] In one possible implementation, the step of obtaining the demand priority of each region based on the energy demand information and environmental information of each region includes:

[0014] S21: Construct a scoring model, assign values ​​to each region based on the energy demand information and environmental information of each region, and obtain the demand priority based on the assigned values.

[0015] In one possible implementation, the step of initializing the scheduling, matching corresponding mobile substations to each region according to priority from high to low, and outputting an initial matching table includes:

[0016] S31: Analyze the demand of each region in descending order of priority, and obtain the matching result of the mobile power station for each region based on the constraints of traffic information between the regions, equipment information of each mobile power station, and environmental information of each region. Output the initial matching table based on the matching result. The initial matching table includes regions that have been successfully matched and regions that have not been successfully matched.

[0017] In one possible implementation, the step of setting improved ant colony algorithm parameters based on traffic information between the regions, mobile power station equipment information, and environmental information of the regions, and inputting the initial matching table into the improved ant colony algorithm for iterative optimization to obtain an allocation scheme includes:

[0018] S41: Initialize the parameters of the ant colony algorithm, set the ant colony size according to the unmatched areas, set the pheromone parameters according to the fit weight of the power station to the region, set the heuristic function according to the real-time fit and data confidence of the power station to the region's needs, set the number of iterations, pheromone evaporation coefficient, and pheromone update mechanism, and output the allocation scheme after iterating a preset number of times.

[0019] In one possible implementation, after the step of setting the number of iterations and the pheromone evaporation coefficient, and outputting the allocation scheme after the iteration, the method includes:

[0020] S42: Perform an overall fitness evaluation on the allocation scheme in each iteration and select the optimal scheme.

[0021] In one possible implementation, the step of acquiring energy demand information for each area within the target range, traffic information between areas, information on mobile power station equipment, and environmental information for each area further includes:

[0022] S12: If information acquisition in a certain area is interrupted, the last valid data is used for matching, and only steps S20 and S30 are executed. The matching result in the output initial matching table is used as the final solution.

[0023] In one possible implementation, the step of acquiring energy demand information for each area within the target range, traffic information between areas, information on mobile power station equipment, and environmental information for each area further includes:

[0024] S13: Continuously record various data and store them as a regional offline data pool. If information reception is interrupted in multiple regions, retrieve the most recent data from the regional offline data pool, process it, and output a global allocation scheme.

[0025] In one possible implementation, the step of continuously recording various data and storing them in a regional offline data pool, and retrieving the most recent data from the regional offline data pool for processing and outputting a global allocation scheme when information reception is interrupted in multiple regions, further includes:

[0026] S14: If data reception is restored after the area goes offline, the new data will overwrite the original data according to the timestamp, and a new allocation scheme will be obtained again; if the new allocation scheme conflicts with the original allocation scheme, a warning will be issued to request intervention.

[0027] To solve the above-mentioned technical problems, another technical solution adopted in this application is: providing a coordination and allocation system for mobile power stations, applicable to a coordination and allocation method for mobile power stations, including:

[0028] The data acquisition module is used to obtain energy demand information, traffic information between regions, information on mobile power station equipment, and environmental information of each region within the target area.

[0029] The analysis module is used to obtain the demand priority of each region based on the energy demand information and environmental information of each region.

[0030] The first algorithm module is used to initialize the scheduling and match the corresponding mobile power stations for each region according to priority from high to low, and output the initial matching table;

[0031] The second algorithm module is used to input the initial matching table into the improved ant colony algorithm and iteratively optimize it to obtain the allocation scheme.

[0032] The execution module is used by each mobile power station and each region to receive and execute the allocation scheme.

[0033] The beneficial effects of this application are as follows: Unlike the prior art, this application discloses a method for coordinating and allocating mobile power stations. By collecting data from various regions and combining the advantages of two algorithms, it can efficiently and quickly generate accurate and reliable scheduling and allocation schemes for mobile power station scheduling scenarios in special situations such as emergency response, repair, and outdoor use. This can meet the power demand of various regions as much as possible, effectively save time, and meet the needs of special power consumption scenarios. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein:

[0035] Figure 1 This is a schematic flowchart of a method for coordinating and allocating mobile power stations according to an embodiment of this application;

[0036] Figure 2 This is a modular structure diagram of a coordination and distribution system for a mobile power station according to an embodiment of this application.

[0037] Explanation of key component symbols:

[0038] 10-A coordination and distribution system for mobile power stations; 11-Acquisition module; 12-Analysis module; 13-First algorithm module; 14-Second algorithm module; 15-Execution module. Detailed Implementation

[0039] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0040] The terms "first," "second," and "third" used in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0041] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0042] Please see Figure 1 This application includes a method for coordinating and allocating mobile power stations, comprising the following steps:

[0043] S10: Obtain energy demand information for each region within the target area, traffic information between regions, information on mobile power station equipment, and environmental information for each region;

[0044] S20: Based on regional energy demand information and regional environmental information, obtain the demand priority of each region;

[0045] S30: Initialize the scheduling, match the corresponding mobile power station for each area according to priority from high to low, and output the initial matching table;

[0046] S40: Based on traffic information between regions, mobile power station equipment information and environmental information of each region, set the parameters of the improved ant colony algorithm, and input the initial matching table into the improved ant colony algorithm to iteratively optimize and obtain the allocation scheme;

[0047] S50: Each mobile power station receives and executes the distribution plan with each region.

[0048] This embodiment addresses the power supply coordination problem in areas not covered by conventional power grids, such as islands, field operations, outdoor scientific research, and post-disaster reconstruction. In order to achieve accurate matching of power supply resources with power demand scenarios, coordination is carried out based on various data.

[0049] Specifically, in step S10, the target range refers to the entire area involved in this dispatch, and each area refers to a specific location, facility, or area within a certain range that requires power support. The sum of all areas constitutes the target range. Information from each area is collected and summarized, including energy demand information for each area, traffic information between areas, information on mobile power station equipment, and environmental information for each area. The data collection method can be automatic data collection through a set data acquisition device, or manual data collection followed by active uploading. This embodiment does not limit the data collection method.

[0050] In this embodiment, the energy demand information for each region may include urgency, power demand, and power outage duration. Urgency refers to the degree of urgency of the power demand, for example, the urgency of hospitals and rescue stations is higher than that of temporary residences. Power demand is the power required, for example, the specifications of industrial electricity and residential electricity are different, and it can also be calculated using the average daily power supply, which can be selected according to the specific scenario. Power outage duration refers to the time that power has been lost. The longer the power outage, the higher the urgency of the power demand.

[0051] Traffic information between regions includes road distances, road conditions, and available vehicles. Road distances refer to the distance between regions that are accessible by vehicles, which is different from straight-line distances. Road conditions refer to the specific road conditions connecting the two locations. In the event of a disaster, roads may be disconnected or blocked and cannot be used normally. Available vehicles refer to the type of vehicle corresponding to the road, which involves the matching of the mobile power station with the mobility of the mobile power station. For example, if the mobile power station is a containerized power supply cabin, it is necessary to consider whether it can be transported by that vehicle.

[0052] The equipment information for each mobile power station includes its output power, remaining energy, mobility, and deployment method. Mobility refers to whether the mobile power station has mobility capabilities, and deployment method refers to the installation method of the mobile power station, such as hoisting or trailer installation.

[0053] Environmental information for each region includes environmental risks, geographical conditions, and climate. Environmental risks include potential hazards such as floods, landslides, and typhoons. Geographical conditions include the altitude and slope of specific locations. Climate refers to temperature, precipitation, wind resources, etc., and is particularly relevant to mobile power stations that generate electricity through photovoltaic and wind power.

[0054] In step S20, based on the energy demand information and environmental information of each region, and according to the urgency of the demand of each region and whether the environmental constraints of each region are met, a score is given according to the principle of prioritizing life safety and emergency situations, and each region is prioritized.

[0055] In step S30, based on the greedy algorithm, matching is performed sequentially from high to low priority according to the demand priority, that is, areas with urgent needs are given priority, and the matching results are output as an initial matching table. The initial matching table includes successfully matched areas and power plants, areas whose needs were not matched and the remaining power plants, and serves as input for subsequent improvements to the ant colony algorithm.

[0056] In step S40, the improved ant colony algorithm is used to process the initial matching table. Multiple ants are used to search for paths, with each ant corresponding to a matching between a region and a power station. Groups of multiple ants correspond to the entire allocation scheme. After several iterations, the optimal allocation scheme is obtained and output as the final result.

[0057] In step S50, each mobile power station and each region begins to execute the allocation plan after receiving it.

[0058] This application combines the ideas of greedy algorithm and improved ant colony algorithm, which can take into account the advantages of the greedy algorithm in fast initialization and rapid analysis and the ant colony algorithm in avoiding local optima. It combines the advantages of both to better suit the applicable scenarios of this application, so as to quickly analyze and propose accurate and optimal allocation schemes.

[0059] In one embodiment, after obtaining energy demand information for each area within the target range, traffic information between areas, information on mobile power station equipment, and environmental information for each area, the process includes:

[0060] S11: Perform data cleaning, data completion, and confidence calculation on energy demand information, traffic information between regions, mobile power station equipment information, and environmental information of each region.

[0061] Step S11 involves preprocessing the collected phase data, including data cleaning, data completion, and confidence level calculation. Specifically, data cleaning standardizes the collected data, such as unifying daily electricity consumption and daily electricity usage time into real-time power demand, and digitizes urgency levels, such as marking life-saving needs as 3, public welfare uses as 2, and others as 1 (higher numbers indicate higher urgency). Data completion involves checking the data; if missing values ​​or obvious errors are found, the erroneous data is removed, and missing values ​​are filled in. For short-term data gaps (missing data within 5 minutes), linear interpolation can be used; for long-term data gaps (missing data between 5 and 15 minutes), historical data for the region can be used; for very long-term data gaps (more than 15 minutes), a preset value can be used for estimation. This preset value can be set based on the nature of the region, the number of people involved, relevant electrical equipment, and experience. Confidence level C is a comprehensive measure of timeliness and data completeness, and can be obtained using the following formula:

[0062] C = α·A + β·B

[0063] In this embodiment, A represents the timeliness score, B represents the data integrity score, α represents the timeliness coefficient, and β represents the data integrity coefficient. The timeliness score A is assigned based on the data acquisition time: 1.0 for data acquired within 30 minutes, 0.8 for data acquired between 30 and 120 minutes, 0.5 for data acquired between 2 and 6 hours, 0.2 for data acquired between 6 and 12 hours, and 0 for data acquired after 12 hours, accompanied by a warning and a suggestion to acquire data using other methods. Higher data timeliness results in a higher score. Data integrity B is assigned based on the extent of data loss: 1.0 for complete data without any loss, 0.8 for data missing minor fields, 0.3 for data missing important fields or a large number of minor fields, and 0 for data missing a large number of important fields, accompanied by a warning. Important fields refer to urgent green energy needs, power requirements, etc., while minor fields refer to less influential fields such as climate and environment. Furthermore, importance values ​​can be assigned to each data point to further improve the accuracy of the data acquisition confidence level.

[0064] In one embodiment, the step of obtaining the demand priority of each region based on the energy demand information and environmental information of each region includes:

[0065] S21: Construct a scoring model, assign values ​​to each region based on its energy demand information and environmental information, and obtain demand priority based on the assigned values.

[0066] Specifically, a scoring model is constructed to quantify and rank the demand priorities of each region. The demand priority score S can be obtained using the following formula:

[0067] ,

[0068] Where X represents the indicator weight and Y represents the indicator score. The indicators are evaluation metrics extracted from regional energy demand and environmental information, such as urgency, power demand, environmental risk, and power outage duration. Each indicator is assigned a corresponding weight, with a total weight of 1. Each indicator is then scored, and the scoring rules can be based on the sub-items under each indicator. Finally, the weights of each indicator and their corresponding scores are multiplied and summed to obtain the priority score. In this embodiment, the scoring rules are shown in Table 1.

[0069] Table 1 Scoring Rules

[0070]

[0071] The priority of needs for each region is obtained according to the scoring rules, sorted, and used for subsequent calculation steps.

[0072] In one embodiment, the step of initializing the scheduling and matching corresponding mobile power stations to each region according to priority from high to low, and outputting an initial matching table, includes:

[0073] S31: Analyze the demand of each region in descending order of priority, and obtain the matching results of the mobile power station for each region based on the constraints of traffic information between regions, equipment information of each mobile power station, and environmental information of each region. Output an initial matching table based on the matching results. The initial matching table includes regions that have been successfully matched and regions that have not been successfully matched.

[0074] Specifically, after obtaining the priority of the needs in each region, they are sorted and matched sequentially from highest to lowest, while taking into account the constraints between the data. A greedy algorithm is adopted, that is, prioritizing the larger needs, constructing a better solution as the initial plan, and then optimizing it in subsequent steps.

[0075] The priority of regional needs, as scored (F) and ranked in the embodiment, is shown in Table 2:

[0076] Table 2 Regional Demand Priority Scoring

[0077]

[0078] After prioritizing the data according to their scores, the power supply needs of temporary hospitals, resettlement sites, and material storage points are met sequentially, forming an initial matching table. Simultaneously, the data is filtered based on constraints arising from the relationships between various data points. For example, in terms of deployment methods, hoisting is difficult to implement during heavy rain; whether the specifications of the mobile power station are compatible with the area's electrical infrastructure; and whether the mobility of the mobile power station meets current road conditions. After comprehensively considering the constraints of each data point, an initial matching table is generated, as shown in Table 3.

[0079] Table 3 Initial Matching Table

[0080]

[0081] In one embodiment, the steps of setting improved ant colony algorithm parameters based on traffic information between regions, mobile power station equipment information, and environmental information of each region, and inputting the initial matching table into the improved ant colony algorithm for iterative optimization to obtain an allocation scheme include:

[0082] S41: Initialize the parameters of the ant colony algorithm, set the ant colony size according to the unmatched areas, set the pheromone parameters according to the fitness weight of the power station to the region, set the heuristic function according to the real-time fitness of the power station to the region's needs and the data confidence, set the number of iterations, pheromone evaporation coefficient, and pheromone update mechanism, and output the allocation scheme after iterating a preset number of times.

[0083] Specifically, an improved ant colony algorithm is used to select the best allocation scheme. The ant colony size can be set according to the unmatched regions. If there are still 5 unmatched regions, the initial ant colony size is 5, with each ant corresponding to one region. The pheromone τ(i,j) represents the fitness weight when mobile station i is assigned to region j, and its initial value is T0=0.5. The heuristic function η(i,j) represents the immediate fitness of mobile station i for region j, which means judging the current matching degree of a mobile station for a certain region based on the current data. The number of iterations should be set to balance the optimization effect and the calculation speed. In this embodiment, the number of iterations is selected as 500. The pheromone evaporation coefficient ρ=0.1 is used to avoid getting trapped in local optima.

[0084] Furthermore, the heuristic function η can be designed as:

[0085] ,

[0086] Where P represents power fit, L represents distance fit, E represents environmental fit, and C represents confidence level. The power fit P is:

[0087] P=min(p_max(j) / p(i),1.5),

[0088] That is, the smaller of the two values ​​is selected and does not exceed 1.5. The former refers to the ratio of the maximum power required by region j to the power that mobile power station i can provide.

[0089] The distance fit L is:

[0090] L = 1 - t(i, j) / t_max,

[0091] Where t(i,j) refers to the number of events required for mobile power station i to move to region j, and t_max refers to the longest maneuver time among all combinations of mobile power stations moving to the region within the target range. Therefore, subtracting this ratio from 1 will result in a higher distance fit L score, indicating less time is used and an advantage in the time dimension.

[0092] The environmental adaptability E is determined by the deployment method and environmental risk. For example, trailer deployment is feasible in heavy rain conditions and is assigned a score of 1, while hoisting deployment is difficult to achieve in heavy rain conditions and is assigned a score of 0.5.

[0093] The confidence level is as shown above; please refer to step S11 for how to obtain it.

[0094] In the previous step S31, factors such as environmental adaptability were used as constraints to make a preliminary decision on mismatch. However, this mismatch is only a preliminary judgment, and it is still necessary to supply power to each area. Therefore, this step fully considers it in order to propose the most feasible allocation plan to ensure full power supply in the area.

[0095] The ant's migration probability is O(i,j), which is the probability that the ant chooses power station j to be assigned to region i:

[0096] ,

[0097] Where m is the pheromone importance factor, the larger the value of this factor, the more it relies on historical experience during iteration; n is the heuristic function importance factor, the larger the value of this factor, the more it relies on immediate fit during iteration. In this embodiment, m is set to 1.2 and n is set to 0.8.

[0098] The pheromone update mechanism can be referenced in the following formula:

[0099] ,

[0100] Where τ(i,j) represents the pheromone, and the subscript... k +1 indicates the pheromone level for the next moment, based on the previous moment. k Pheromones are used to obtain information; the triangular marker △ refers to... k arrive k The change in pheromone between +1 and ρ indicates that the solution is closer to the optimal solution. ρ refers to the pheromone evaporation coefficient, and in this embodiment, ρ=1.

[0101] During runtime, the unmatched regions from the initial allocation are imported along with mobile power stations. The process iterates a preset number of times, selecting a mobile power station for each region corresponding to each ant, and completing the matching scheme for the unmatched regions. Combined with the initial matching table from the previous steps, a complete allocation scheme is generated.

[0102] In one embodiment, after setting the number of iterations and the pheromone evaporation coefficient, and outputting the allocation scheme after iteration, the method includes:

[0103] S42: Evaluate the overall fit of the allocation schemes in each iteration and select the optimal scheme.

[0104] Specifically, by combining the previously defined heuristic function η(i,j) covering various fit parameters with the requirement priority score S, a comprehensive score F is obtained, according to:

[0105] ,

[0106] Obtain the score for each solution and output the solution with the highest score as the optimal solution.

[0107] In one embodiment, the step of acquiring energy demand information for each area within the target range, traffic information between areas, information on mobile power station equipment, and environmental information for each area further includes:

[0108] S12: If information acquisition in a certain area is interrupted, the last valid data will be used for matching, and only steps S20 and S30 will be executed. The matching results in the output initial matching table will be used as the final solution.

[0109] Due to the specific nature of the scenario addressed in this application, signal loss is easily caused by power outages. In such cases, calculations are performed based on the last valid data received. Especially when the disconnection time is short, the data received in the previous round still has a certain degree of reliability. In this case, lightweight calculations are performed, i.e., only steps S20 and S30 are executed, which can quickly obtain a simplified solution and execute it in advance to restore power supply and communication as soon as possible. Subsequently, this solution can be coordinated and modified to further optimize and improve it.

[0110] Specifically, during matching, the power of the mobile power station can be estimated at 1.2 times the demand, and the demand can be met in order of priority, thus achieving lightweight calculation.

[0111] In one embodiment, the step of acquiring energy demand information for each area within the target range, traffic information between areas, information on mobile power station equipment, and environmental information for each area further includes:

[0112] S13: Continuously record various data and store them in the regional offline data pool. If information reception is interrupted in multiple regions, retrieve the most recent data from the regional offline data pool for processing and output a global allocation scheme.

[0113] When multiple regions experience information outages, the demand in each region can be determined from historical data, and processing can be performed based on the most recent data. Some data properties in the offline data pool will not change, such as urgency and environmental requirements, and will remain unchanged in the short to medium term. In addition, information outages in multiple locations also indicate that demand will increase. It can be estimated based on the previous data showing a rise in demand to 1.5 times, and power can be provided as much as possible to restore power as quickly as possible.

[0114] In one embodiment, the step of continuously recording various data and storing them in a regional offline data pool, and retrieving the most recent data from the regional offline data pool for processing and outputting a global allocation scheme when information reception is interrupted in multiple regions, further includes:

[0115] S14: If data reception is restored after the area goes offline, the new data will overwrite the original data according to the timestamp, and a new allocation scheme will be obtained again; if the new allocation scheme conflicts with the original allocation scheme, a warning will be issued to request intervention.

[0116] As power is gradually restored, data uploaded from each area will be received again. At this point, the new data will overwrite the original data according to the timestamp, and the scheme matching will be performed again. If the original scheme has already been activated, some mobile power stations have started to move, and the newly acquired scheme conflicts with it, a warning should be issued to remind dispatchers. Manual intervention is recommended. Depending on the specific situation, it should be considered whether to stop the original scheme or recall the mobile power stations that have already set off, in order to avoid wasting resources and mismatch.

[0117] The above is an explanation of a coordination and allocation method for mobile power stations in the embodiments of this application. The coordination and allocation system 10 for mobile power stations in the embodiments of this application will be described below. Please refer to... Figure 2 The embodiments of this application also include a mobile power station coordination and allocation system 10, applicable to a mobile power station coordination and allocation method, including:

[0118] The data acquisition module 11 is used to acquire energy demand information, traffic information between regions, mobile power station equipment information, and environmental information of each region within the target area.

[0119] Analysis module 12 is used to obtain the demand priority of each region based on the energy demand information and environmental information of each region;

[0120] The first algorithm module 13 is used to initialize the scheduling and match the corresponding mobile power stations for each region according to priority from high to low, and output the initial matching table;

[0121] The second algorithm module 14 is used to input the initial matching table into the improved ant colony algorithm and iteratively optimize it to obtain the allocation scheme.

[0122] Execution module 15 is used by each mobile power station and each region to receive and execute the allocation scheme.

[0123] Since some embodiments of the system correspond to the embodiments of the aforementioned method, the description of the coordination and allocation system for a mobile power station provided in this application is the same as that of the aforementioned method embodiments, and will not be repeated here. It also has the same technical effect as the aforementioned coordination and allocation method for a mobile power station.

[0124] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method of coordinating and distributing mobile power stations, characterized in that, Comprising the following steps: S10: Obtain regional energy demand information, inter-regional traffic information, mobile power station device information, and regional environmental information within a target range; S20: Obtain demand priorities for each region based on the regional energy demand information and the regional environmental information; S30: Initialize scheduling, match corresponding mobile power stations for each region according to priorities from high to low, and output an initial matching table; The initial matching table includes regions that have been successfully matched and regions that have not been successfully matched; S40: Set improved ant colony algorithm parameters based on the inter-regional traffic information, the mobile power station device information, and the regional environmental information, input the initial matching table into the improved ant colony algorithm, and iteratively optimize to obtain an allocation scheme; S50: Each mobile power station and each region receive and execute the allocation scheme; The step of setting improved ant colony algorithm parameters based on the inter-regional traffic information, the mobile power station device information, and the regional environmental information, inputting the initial matching table into the improved ant colony algorithm, and iteratively optimizing to obtain an allocation scheme comprises: S41: Initialize ant colony algorithm parameters, set ant colony size according to regions that have not been successfully matched, set pheromone parameters according to the adaptability weight of power stations allocated to regions, set heuristic functions according to the immediate adaptability of power stations to regional demand and data confidence, set iteration number, pheromone evaporation coefficient, and pheromone update mechanism, and output the allocation scheme after iterating a preset number of times; S42: Evaluate the total adaptability of the allocation scheme in each iteration and select the optimal scheme.

2. The method of claim 1, wherein, After the step of obtaining regional energy demand information, inter-regional traffic information, mobile power station device information, and regional environmental information within a target range, comprising: S11: Perform data cleaning, data completion, and confidence calculation on the regional energy demand information, inter-regional traffic information, mobile power station device information, and regional environmental information.

3. The method of claim 1, wherein, The step of obtaining demand priorities for each region based on the regional energy demand information and the regional environmental information comprises: S21: Build a scoring model, assign values to each region according to the regional energy demand information and the regional environmental information, and obtain the demand priorities based on the assigned values.

4. The method of claim 1, wherein, The step of initializing scheduling, matching corresponding mobile power stations for each region according to priorities from high to low, and outputting an initial matching table comprises: S31: Analyze the demand of each region according to priorities from high to low, obtain matching results of mobile power stations for each region based on the inter-regional traffic information, the mobile power station device information, and the regional environmental information constraints, and output the initial matching table according to the matching results.

5. The method of claim 1, wherein, The step of obtaining regional energy demand information, inter-regional traffic information, mobile power station device information, and regional environmental information within a target range further comprises: S12: If the information of a region is interrupted, the last valid data is matched and only steps S20 and S30 are executed, and the matching result in the initial matching table is output as the final scheme.

6. The method of claim 1, wherein, The step of obtaining the energy demand information of each region, the traffic information between regions, the information of each mobile power station, and the environmental information of each region further comprises: S13: Continuously record each item of data and store it as a regional offline data pool, and if information receiving is interrupted in multiple regions, the last data is obtained from the regional offline data pool to process and output a global allocation scheme.

7. The method of claim 6, wherein, The step of continuously recording each item of data and storing it as a regional offline data pool, and if information receiving is interrupted in multiple regions, the last data is obtained from the regional offline data pool to process and output a global allocation scheme further comprises: S14: If data receiving is restored after the region is offline, the new data is overwritten on the original data according to the time stamp, and a new allocation scheme is obtained; if the new allocation scheme conflicts with the original allocation scheme, a warning is issued to apply for intervention.

8. A system for coordinating and distributing mobile power stations, adapted to a method for coordinating and distributing mobile power stations according to any one of claims 1 to 7, characterized in that, Comprise: The acquisition module is configured to obtain the energy demand information of each region, the traffic information between regions, the information of each mobile power station, and the environmental information of each region; The analysis module is configured to obtain the demand priority of each region based on the energy demand information of each region and the environmental information of each region; The first algorithm module is configured to initialize scheduling and match the corresponding mobile power station for each region according to the priority from high to low, and output an initial matching table; The second algorithm module is configured to input the initial matching table into an improved ant colony algorithm, iteratively optimize to obtain an allocation scheme; The execution module is configured to receive and execute the allocation scheme by each mobile power station and each region.

Images