Electrical load prediction and optimization method based on mobile storage and charging robot

Abstract

The invention relates to the technical field of electrical load prediction and optimization, and particularly discloses an electrical load prediction and optimization method based on a mobile storage and charging robot, and the method comprises the steps: needed electricity consumption prediction, actual residual electricity calculation, available storage electricity confirmation, and mobile storage and charging transfer optimization. According to the invention, the corresponding power consumption of each charging area in the next charging period is predicted, the corresponding actual residual electric quantity of each charging area in the current charging period is calculated, and the corresponding actual available storage electric quantity of each mobile storage and charging robot in the next charging period is confirmed; and finally, the storage and charging of each mobile storage and charging robot in the next charging period are mobilized and optimized, so that the accuracy and reliability of required electricity consumption prediction, actual residual electricity calculation and available storage electricity confirmation are improved, an effective data support basis is provided for subsequent mobile storage and charging mobilization and optimization, unreasonable resource allocation is avoided, and the service life of the mobile storage and charging robot is prolonged. And charging inconvenience is brought to a vehicle owner.

Description

Technical Field

[0001] The present invention relates to the technical field of power load prediction and optimization, and in particular to a power load prediction and optimization method based on a mobile storage and charging robot. Background Art

[0002] With the rapid development of smart grids and new energy technologies, load forecasting and optimal scheduling play an increasingly important role in power systems. The accuracy of load forecasting directly affects the power generation planning, resource allocation and power supply reliability of the power system. As an important part of the smart grid, mobile storage and charging robots provide new ideas for load forecasting and optimization due to their flexibility and intelligence.

[0003] For example, the patent with publication number CN116316599A discloses an intelligent power load forecasting method, including: obtaining the data set required for power load forecasting in the target area; preprocessing the load, time and climate data sets, and selecting data with strong characteristics for model training and testing; dividing the target area, and performing abnormal processing on the historical power load data of each area for load forecasting; obtaining a multi-layer random forest algorithm model optimized based on the MPSO algorithm, inputting the training data set into the model after reinforcement learning for training and testing, and obtaining a power load forecasting model; evaluating the prediction performance of the power load forecasting model, inputting the historical power load data after regional processing into the load forecasting model for power load forecasting, and outputting the prediction results. This intelligent power load forecasting method constructs a three-layer random forest algorithm model to improve the accuracy of the predicted data source and the accuracy of the model load forecasting.

[0004] The above existing technologies still have the following problems: 1. In terms of the prediction of required power consumption, the charging trend of charging vehicles is not analyzed in combination with the charging behavior of charging vehicles in the underground parking lot of the community, and the charging status of charging vehicles cannot be displayed intuitively and dynamically, which reduces the accuracy of the prediction of the required power consumption corresponding to the next cycle, which may lead to unreasonable resource allocation and bring charging inconvenience to car owners.

[0005] 2. In terms of the calculation of the actual remaining power, the actual remaining power in the charging area is not comprehensively analyzed in combination with the power conditions in the charging area and the health status of the charging piles, such as the charging speed and charging energy consumption. This reduces the reliability of the calculation of the actual remaining power and results in incomplete data sources for the remaining power prediction, thus affecting the accuracy of the prediction.

[0006] 3. In terms of confirmation of available storage power, the charging and discharging information of the mobile storage and charging robot during the charging and discharging process was not monitored, which reduced the accuracy and rationality of the confirmation of the actual available storage power corresponding to the next charging cycle of the mobile storage and charging robot, and could not provide effective data support for the subsequent mobile storage and charging mobilization optimization. Summary of the invention

[0007] In view of this, in order to solve the problems raised in the above background technology, a power load prediction and optimization method based on a mobile storage and charging robot is proposed.

[0008] The purpose of the present invention can be achieved through the following technical solutions: The present invention provides a method for predicting and optimizing power load based on a mobile storage and charging robot, comprising the following steps: S1. Prediction of required power consumption: extract the remaining power corresponding to each charging area in the underground parking lot of the target community in the current charging cycle, the number of charging times corresponding to each charging vehicle, and the charging time point and charging amount of each charging, and predict the required power consumption corresponding to each charging area in the next charging cycle.

[0009] S2. Calculation of actual remaining power: Collect the access current and output current corresponding to each charging area in the underground parking lot of the target community in each monitoring time period, and collect the health status information of each charging pile in each charging area, and calculate the actual remaining power corresponding to each charging area in the current charging cycle.

[0010] S3. Confirmation of available storage power: extract the charging and discharging information corresponding to each mobile storage and charging robot in the underground parking lot of the target community in each historical charging and discharging, and extract the remaining storage power corresponding to each mobile storage and charging robot in the current charging cycle, analyze the abnormal index of charging and discharging efficiency of each mobile storage and charging robot, and confirm the actual available storage power corresponding to each mobile storage and charging robot in the next charging cycle.

[0011] S4. Mobile storage and charging deployment optimization: Optimize the storage and charging of each mobile storage and charging robot in the next charging cycle.

[0012] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects: (1) The present invention predicts the power consumption required for each charging area in the next charging cycle by combining the number of charging times corresponding to each charging vehicle and the charging time and charging amount of each charging, and intuitively and dynamically displays the charging status of the charging vehicles, thereby improving the accuracy of the prediction of the power consumption required for the next cycle and avoiding unreasonable resource allocation and charging inconvenience for vehicle owners.

[0013] (2) The present invention conducts a comprehensive analysis of the actual remaining power in the charging area by combining the power stability of the charging area and the health status of the charging pile, such as the charging speed and charging energy consumption, thereby improving the reliability of the calculation of the actual remaining power and the data source integrity of the remaining power prediction.

[0014] (3) The present invention monitors the charging and discharging information of the mobile storage and charging robots during the charging and discharging process, analyzes the abnormal index of the charging and discharging efficiency of each mobile storage and charging robot, and confirms the actual available storage power corresponding to the next charging cycle of each mobile storage and charging robot. This improves the accuracy and rationality of the confirmation of the actual available storage power corresponding to the next charging cycle of the mobile storage and charging robots, and provides effective data support for the subsequent optimization of mobile storage and charging mobilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0016] Figure 1 The figure is a schematic flow chart of the steps of the method of the present invention.

[0017] Figure 2 It is a schematic diagram of the power loss deviation curve of the charging pile of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] See also Figure 1 As shown, the present invention provides a method for predicting and optimizing power load based on a mobile storage and charging robot, including: S1, prediction of required power consumption: extracting the remaining power corresponding to each charging area in the underground parking lot of the target community in the current charging cycle, the number of charging times corresponding to each charging vehicle, and the charging time point and charging amount of each charging, and predicting the required power consumption corresponding to each charging area in the next charging cycle.

[0020] It should be noted that the remaining power corresponding to each charging area in the current charging cycle is extracted from the power management background of each charging area, and the number of charging times corresponding to each charging vehicle and the charging time and charging amount of each charging are extracted from the charging vehicle data management background.

[0021] In a specific embodiment of the present invention, the specific process of predicting the power consumption required for each charging area in the next charging cycle is as follows: A1, based on the charging time point and charging amount of each charging vehicle corresponding to each charging area in the underground parking lot of the target community in the current charging cycle, calculate the charging trend index β of each charging vehicle in each charging area ij , where i represents the number of the charging area, i=1,2,...,n, and j represents the number of the charging vehicle, j=1,2,...,m.

[0022] In a specific embodiment of the present invention, the specific process of calculating the charging trend index of each charging vehicle in each charging area is as follows: B1. Subtract the charging time points of each charging time corresponding to each charging vehicle in each charging area to obtain the interval time of each charging time corresponding to each charging vehicle, and extract the maximum value from the interval time of each charging time as the charging interval time corresponding to each charging vehicle in each charging area, recorded as ΔT ij .

[0023] B2. The number of charging times corresponding to each charging vehicle in each charging area is recorded as μ ij .

[0024] B3. Calculate the charging trend index β of each charging vehicle in each charging area ij , Among them, ΔT′ and μ′ represent the set reference charging interval duration and charging times, respectively, a1 and a2 represent the set charging interval duration and charging times corresponding to the charging trend assessment weights, respectively, a1+a2=1.

[0025] In a specific embodiment of the present invention, the setting value of a1 is 0.5, and the setting value of a2 is 0.5. When calculating the charging trend index, the charging interval duration and the number of charges are important factors to be considered. They each reflect different aspects of the vehicle charging behavior and together constitute a complete portrait of the charging trend.

[0026] A2. If the charging trend index of a charging vehicle is greater than or equal to the charging trend index of the set reference, the charging vehicle is determined to be a fixed charging vehicle. If the charging trend index of a charging vehicle is less than the charging trend index of the set reference, the charging vehicle is determined to be a variable charging vehicle.

[0027] A3. Multiply the number of charging times and the charging amount of each charging time corresponding to each fixed charging vehicle in each charging area to obtain the total charging amount corresponding to each fixed charging vehicle, and multiply it by the number of fixed charging vehicles to obtain the total charging amount corresponding to the fixed charging vehicles in each charging area, recorded as

[0028] A4. Multiply the number of charges corresponding to each variable charging vehicle in each charging area by the charge amount of each charge, and obtain the total charge amount corresponding to each variable charging vehicle. Then calculate the average value to obtain the total charge amount corresponding to the variable charging vehicles in each charging area, which is recorded as

[0029] A5. Predict the power consumption required for each charging area in the next charging cycle

[0030] The embodiment of the present invention predicts the power consumption required for each charging area in the next charging cycle by combining the number of charging times corresponding to each charging vehicle and the charging time and charging amount of each charging, and intuitively and dynamically displays the charging status of the charging vehicles, thereby improving the accuracy of the prediction of the power consumption required for the next cycle, avoiding unreasonable resource allocation and causing charging inconvenience to the car owner.

[0031] S2. Calculation of actual remaining power: Collect the access current and output current corresponding to each charging area in the underground parking lot of the target community in each monitoring time period, and collect the health status information of each charging pile in each charging area, and calculate the actual remaining power corresponding to each charging area in the current charging cycle.

[0032] It should be noted that the access current and output current corresponding to each charging area in each monitoring time period are collected by electric energy meters installed at the access end and the output end of each charging area respectively.

[0033] In a specific embodiment of the present invention, the health status information includes the discharge speed, required discharge amount and actual discharge amount corresponding to each discharge process.

[0034] It should be noted that the discharge speed, required discharge amount and actual discharge amount corresponding to each discharge process are all extracted from the charging pile management app.

[0035] In a specific embodiment of the present invention, the specific process of calculating the actual remaining power corresponding to each charging area in the current charging cycle is as follows: C1, based on the access current and output current corresponding to each charging area in the underground parking lot of the target community in each monitoring time period, calculate the power stability x of each charging area i .

[0036] It should be noted that the specific process of calculating the power stability of each charging area is as follows: subtract the access current and output current corresponding to each charging area in the underground parking lot of the target community in each monitoring time period to obtain the output current deviation corresponding to each charging area in each monitoring time period, and calculate the average value to obtain the output current deviation corresponding to each charging area, which is recorded as ΔI i .

[0037] Calculate the power stability of each charging area χ i , Here, ΔI′ represents the output current deviation of the set reference.

[0038] C2. Extract the discharge speed, required discharge amount and actual discharge amount corresponding to each discharge process from the health status information of each charging pile in each charging area, and calculate the health status index δ of the charging pile in each charging area i .

[0039] In a specific embodiment of the present invention, the specific process of calculating the health status index of the charging piles in each charging area is as follows: D1, subtracting the discharge speed corresponding to each discharge process of each charging pile in each charging area from the discharge speed provided by the charging pile manufacturer stored in the database, obtaining the discharge speed deviation corresponding to each discharge process of each charging pile, and extracting the maximum value therefrom, recorded as Δv ij .

[0040] D2. Calculate the abnormal discharge speed index of charging piles in each charging area Wherein, Δv′ represents the discharge speed deviation of the set reference, m represents the number of charged vehicles, and e represents a natural constant.

[0041] D3. Subtract the actual discharge amount and the required discharge amount corresponding to each discharge process of each charging pile in the charging area to obtain the corresponding power loss during each discharge process of each charging pile, and calculate the abnormal power loss index θ of the charging piles in each charging area i .

[0042] See also Figure 2 As shown, it should be noted that the specific process of calculating the abnormal power loss index of the charging piles in each charging area is: taking the number of discharges as the horizontal coordinate and the power loss as the vertical coordinate, constructing the power loss deviation curve of each charging pile, and locating the slope value from the curve as the power loss growth rate of each charging pile, which is marked as K i .

[0043] Calculate the abnormal power loss index θ of the charging piles in each charging area i , Here, K′ represents the reference power consumption growth rate.

[0044] D4. Calculate the health status index δ of the charging piles in each charging area i , Among them, a3 and a4 represent the weights of the charging pile health status assessment corresponding to the set charging pile charging speed abnormality index and charging pile power loss abnormality index, respectively, and a3+a4=1.

[0045] In a specific embodiment of the present invention, the setting value of a3 is 0.4, and the setting value of a4 is 0.6. When calculating the charging pile health status index of each charging area, the charging pile charging speed abnormality index and the charging pile power loss abnormality index should be comprehensively considered. Among them, the power loss abnormality directly affects the energy efficiency of the charging pile, so they need to be given different weights to more comprehensively reflect the health status of the charging pile. C3. Extract the power loss corresponding to the unit power stability deviation and the power loss corresponding to the unit charging pile health status deviation from the database, and record them as ε′ and ε″ respectively.

[0046] C4. Record the remaining power of each charging area in the target community underground parking lot during the current charging cycle as

[0047] C5. Calculate the actual remaining power of each charging area during the current charging cycle Among them, χ′ and δ′ represent the reference power stability and charging pile health status index respectively.

[0048] The embodiment of the present invention comprehensively analyzes the actual remaining power in the charging area by combining the power stability of the charging area and the health status of the charging pile, such as the charging speed and charging energy consumption, thereby improving the reliability of the calculation of the actual remaining power and the data source integrity of the remaining power prediction.

[0049] S3. Confirmation of available storage power: extract the charging and discharging information corresponding to each mobile storage and charging robot in the underground parking lot of the target community in each historical charging and discharging, and extract the remaining storage power corresponding to each mobile storage and charging robot in the current charging cycle, analyze the abnormal index of charging and discharging efficiency of each mobile storage and charging robot, and confirm the actual available storage power corresponding to each mobile storage and charging robot in the next charging cycle.

[0050] In a specific embodiment of the present invention, the charge and discharge information includes charging current, charging time to full charge, average charging voltage, discharging current, discharging time to cut-off voltage and discharging cut-off voltage.

[0051] It should be noted that the charging current, time to fully charge, average charging voltage, discharge current, time to discharge to cut-off voltage, discharge cut-off voltage and remaining storage capacity are all extracted from the mobile storage and charging robot work management platform.

[0052] In a specific embodiment of the present invention, the specific process of analyzing the abnormal index of the charging and discharging efficiency of each mobile storage and charging robot is as follows: E1, extracting the charging current, charging time to full charge, average charging voltage, discharge current, discharge time to cut-off voltage and discharge cut-off voltage from the corresponding charging and discharging information of each mobile storage and charging robot in the underground parking lot of the target community in each historical charging and discharging, and recording them as and Among them, g represents the number of the mobile storage and charging robot, g = 1, 2, ..., p, and r represents the number of each historical charge and discharge, r = 1, 2, ..., q.

[0053] E2. Calculate the charging and discharging efficiency of each mobile storage and charging robot in each historical charging and discharging

[0054] E3. Calculate the abnormal index ω of the charging and discharging efficiency of each mobile storage and charging robot g , in, It represents the charge and discharge efficiency of the set reference, and q represents the number of historical charge and discharge times.

[0055] In a specific embodiment of the present invention, the specific method for confirming the actual available storage power of each mobile storage and charging robot in the next charging cycle is as follows: F1, the remaining storage power of each mobile storage and charging robot in the current charging cycle is recorded as

[0056] F2. Extract the consumed storage power corresponding to the abnormal deviation of unit charge and discharge efficiency from the database and record it as τ0.

[0057] F3: Set the actual available storage capacity of each mobile storage and charging robot in the next charging cycle Here, ω′ represents the abnormal index of charge and discharge efficiency set as a reference.

[0058] The embodiment of the present invention monitors the charging and discharging information of the mobile storage and charging robot during the charging and discharging process, analyzes the abnormal index of the charging and discharging efficiency of each mobile storage and charging robot, and confirms the actual available storage power corresponding to the next charging cycle of each mobile storage and charging robot. This improves the accuracy and rationality of the confirmation of the actual available storage power corresponding to the next charging cycle of the mobile storage and charging robot, and provides effective data support for subsequent mobile storage and charging mobilization optimization.

[0059] S4. Mobile storage and charging deployment optimization: Optimize the storage and charging of each mobile storage and charging robot in the next charging cycle.

[0060] In a specific embodiment of the present invention, the specific process of mobilizing and optimizing the storage and charging of each mobile storage and charging robot in the next charging cycle is: G1. Compare the actual remaining power corresponding to each charging area in the current charging cycle with the required power consumption of each charging area in the next charging cycle. If the actual remaining power of a charging area is greater than the required power consumption in the next charging cycle, it indicates that the charging area does not need a mobile storage and charging robot to replenish power. Otherwise, the remaining charging areas are recorded as target charging areas.

[0061] G2. Subtract the required power consumption of each target charging area in the next charging cycle from the actual remaining power in the current charging cycle to obtain the supplementary power corresponding to each target charging area.

[0062] G3. Extract the target charging area corresponding to the minimum value from the replenishment power corresponding to each target charging area, and record it as the reference charging area. Subtract the actual available storage power corresponding to the next charging cycle of each mobile storage and charging robot from the replenishment power corresponding to the reference charging area, and extract the mobile storage and charging robot corresponding to the minimum difference from the difference, and use it as the mobile storage and charging robot corresponding to the reference charging area.

[0063] G4. Select the mobile storage and charging robots corresponding to the remaining target charging areas in the same way as the mobile storage and charging robots corresponding to the reference charging area. If the replenishment power corresponding to a target charging area is greater than the actual available storage power of the mobile storage and charging robot in the next charging cycle, it indicates that the mobile storage and charging robot cannot replenish the power of the target charging area, and feedback is given.

[0064] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they shall all fall within the protection scope of the present invention.

Claims

1. A method for predicting and optimizing power load based on a mobile storage and charging robot, characterized in that: The steps include: S1. Prediction of required power consumption: extract the remaining power corresponding to each charging area in the underground parking lot of the target community in the current charging cycle, the number of charging times corresponding to each charging vehicle, and the charging time and charging amount of each charging, and predict the required power consumption corresponding to each charging area in the next charging cycle; S2. Calculation of actual remaining power: Collect the access current and output current corresponding to each charging area in the underground parking lot of the target community in each monitoring time period, and collect the health status information of each charging pile in each charging area, and calculate the actual remaining power corresponding to each charging area in the current charging cycle; S3. Confirmation of available storage power: extract the charging and discharging information corresponding to each mobile storage and charging robot in the underground parking lot of the target community in each historical charging and discharging, and extract the remaining storage power corresponding to each mobile storage and charging robot in the current charging cycle, analyze the abnormal index of the charging and discharging efficiency of each mobile storage and charging robot, and confirm the actual available storage power corresponding to each mobile storage and charging robot in the next charging cycle; S4. Mobile storage and charging deployment optimization: Optimize the storage and charging of each mobile storage and charging robot in the next charging cycle.

2. According to claim 1, a method for predicting and optimizing power load based on a mobile storage and charging robot is characterized in that: The specific process of predicting the power consumption required for each charging area in the next charging cycle is as follows: A1. Calculate the charging trend index β of each charging vehicle in each charging area based on the charging time point and charging amount of each charging vehicle in each charging area in the target community underground parking lot during the current charging cycle. ij , where i represents the number of the charging area, i=1,2,...,n, and j represents the number of the charging vehicle, j=1,2,...,m; A2. If the charging trend index of a charging vehicle is greater than or equal to the charging trend index of the set reference, the charging vehicle is determined to be a fixed charging vehicle; if the charging trend index of a charging vehicle is less than the charging trend index of the set reference, the charging vehicle is determined to be a variable charging vehicle; A3. Multiply the number of charging times and the charging amount of each charging time corresponding to each fixed charging vehicle in each charging area to obtain the total charging amount corresponding to each fixed charging vehicle, and multiply it by the number of fixed charging vehicles to obtain the total charging amount corresponding to the fixed charging vehicles in each charging area, recorded as A4. Multiply the number of charges corresponding to each variable charging vehicle in each charging area by the charge amount of each charge, and obtain the total charge amount corresponding to each variable charging vehicle. Then calculate the average value to obtain the total charge amount corresponding to the variable charging vehicles in each charging area, which is recorded as A5. Predict the power consumption required for each charging area in the next charging cycle 3. According to claim 2, a method for predicting and optimizing power load based on a mobile storage and charging robot is characterized in that: The specific process of calculating the charging trend index of each charging vehicle in each charging area is as follows: B1. Subtract the charging time points of each charging time corresponding to each charging vehicle in each charging area to obtain the interval time of each charging time corresponding to each charging vehicle, and extract the maximum value from the interval time of each charging time as the charging interval time corresponding to each charging vehicle in each charging area, recorded as ΔT ij ; B2. The number of charging times corresponding to each charging vehicle in each charging area is recorded as μ ij ; B3. Calculate the charging trend index β of each charging vehicle in each charging area ij , Among them, ΔT′ and μ′ represent the set reference charging interval duration and charging times, respectively, a1 and a2 represent the set charging interval duration and charging times corresponding to the charging trend assessment weights, respectively, a1+a2=1.

4. The method for predicting and optimizing power load based on a mobile storage and charging robot according to claim 2 is characterized in that: The health status information includes the discharge speed, required discharge amount and actual discharge amount corresponding to each discharge process.

5. The method for predicting and optimizing power load based on a mobile storage and charging robot according to claim 4 is characterized in that: The specific process of calculating the actual remaining power corresponding to each charging area in the current charging cycle is as follows: C1. Calculate the power stability of each charging area based on the access current and output current corresponding to each charging area in the underground parking lot of the target community during each monitoring period. i ; C2. Extract the discharge speed, required discharge amount and actual discharge amount corresponding to each discharge process from the health status information of each charging pile in each charging area, and calculate the health status index δ of the charging pile in each charging area i ; C3. Extract the power loss corresponding to the unit power stability deviation and the power loss corresponding to the unit charging pile health status deviation from the database, and record them as ε′ and ε″ respectively; C4. Record the remaining power of each charging area in the target community underground parking lot during the current charging cycle as C5. Calculate the actual remaining power of each charging area during the current charging cycle Among them, χ′ and δ′ represent the reference power stability and charging pile health status index respectively.

6. The method for predicting and optimizing power load based on a mobile storage and charging robot according to claim 5 is characterized in that: The specific process of calculating the charging pile health status index of each charging area is as follows: D1. Subtract the discharge speed corresponding to each discharge process of each charging pile in each charging area from the discharge speed provided by the charging pile manufacturer stored in the database to obtain the discharge speed deviation corresponding to each discharge process of each charging pile, and extract the maximum value from it, recorded as Δv ij ; D2. Calculate the abnormal discharge speed index of charging piles in each charging area Wherein, Δv′ represents the discharge speed deviation of the set reference, m represents the number of charging vehicles, and e represents a natural constant; D3. Subtract the actual discharge amount and the required discharge amount corresponding to each discharge process of each charging pile in the charging area to obtain the corresponding power loss during each discharge process of each charging pile, and calculate the abnormal power loss index θ of the charging piles in each charging area i ; D4. Calculate the health status index δ of the charging piles in each charging area i , Among them, a3 and a4 represent the weights of the charging pile health status assessment corresponding to the set charging pile charging speed abnormality index and charging pile power loss abnormality index, respectively, and a3+a4=1.

7. The method for predicting and optimizing power load based on a mobile storage and charging robot according to claim 5 is characterized in that: The charge and discharge information includes charging current, time to charge to full charge, average charging voltage, discharging current, time to discharge to cut-off voltage and discharge cut-off voltage.

8. The method for predicting and optimizing power load based on a mobile storage and charging robot according to claim 7 is characterized in that: The specific process of analyzing the abnormal index of the charging and discharging efficiency of each mobile storage and charging robot is as follows: E1. Extract the charging current, charging time to full charge, average charging voltage, discharge current, time to discharge to cut-off voltage and discharge cut-off voltage from the charging and discharging information of each mobile storage and charging robot in the underground parking lot of the target community, and record them as and Wherein, g represents the serial number of the mobile storage and charging robot, g = 1, 2, ..., p, and r represents the serial number of each historical charge and discharge, r = 1, 2, ..., q; E2. Calculate the charging and discharging efficiency of each mobile storage and charging robot in each historical charging and discharging E3. Calculate the abnormal index ω of the charging and discharging efficiency of each mobile storage and charging robot g , in, It represents the charge and discharge efficiency of the set reference, and q represents the number of historical charge and discharge times.

9. The method for predicting and optimizing power load based on a mobile storage and charging robot according to claim 8 is characterized in that: The specific method of confirming the actual available storage power of each mobile storage and charging robot corresponding to the next charging cycle is: F1. Record the remaining storage capacity of each mobile storage and charging robot in the current charging cycle as F2, extract the corresponding consumed storage power of the abnormal deviation of unit charge and discharge efficiency from the database and record it as τ0; F3: Set the actual available storage capacity of each mobile storage and charging robot in the next charging cycle Here, ω′ represents the abnormal index of charge and discharge efficiency set as a reference.

10. The method for predicting and optimizing power load based on a mobile storage and charging robot according to claim 9 is characterized in that: The specific process of optimizing the storage and charging of each mobile storage and charging robot in the next charging cycle is as follows: G1. Compare the actual remaining power of each charging area in the current charging cycle with the required power consumption of each charging area in the next charging cycle. If the actual remaining power of a charging area is greater than the required power consumption in the next charging cycle, it means that the charging area does not need a mobile storage and charging robot to replenish power. Otherwise, the remaining charging areas are recorded as target charging areas. G2, subtract the required power consumption of each target charging area in the next charging cycle from the actual remaining power in the current charging cycle to obtain the supplementary power corresponding to each target charging area; G3. Extract the target charging area corresponding to the minimum value from the replenishment power corresponding to each target charging area, and record it as the reference charging area. Subtract the actual available storage power corresponding to the next charging cycle of each mobile storage and charging robot from the replenishment power corresponding to the reference charging area, and extract the mobile storage and charging robot corresponding to the minimum difference from the difference, and use it as the mobile storage and charging robot corresponding to the reference charging area. G4. Select the mobile storage and charging robots corresponding to the remaining target charging areas in the same way as the mobile storage and charging robots corresponding to the reference charging area. If the replenishment power corresponding to a target charging area is greater than the actual available storage power of the mobile storage and charging robot in the next charging cycle, it indicates that the mobile storage and charging robot cannot replenish the power of the target charging area, and feedback is given.

Images