Community charging pile optimization control method, electronic equipment and storage medium

Abstract

The invention discloses a community charging pile optimization control method, electronic equipment and a storage medium, and belongs to the field of power demand response. In order to realize optimal control of the charging pile of the community, the total power grid load of the community is calculated; taking seasons as units, collecting electricity consumption condition historical data of the community infrastructure and equipment, and establishing an electricity consumption load model of the community infrastructure; the method comprises the following steps: by taking a day as a unit, collecting electricity consumption conditions of residents in a single day including each hour and historical data of weather and whether the residents are festivals and holidays, and establishing a community resident daily life electricity consumption load model; establishing an available electrical load model of the charging pile; taking real-time acquisition of electric vehicles accessed by the charging piles as a quantity basis, and establishing a charging pile charging scheduling prediction model according to corresponding time and in combination with a community infrastructure electrical load and a residential electrical load; and a priority iterative optimization algorithm is designed to carry out optimization scheduling on the charging pile charging scheduling prediction model, the access number of the charging piles is dynamically adjusted, and the electrical load is always in a reasonable range.

Description

Technical Field

[0001] The present invention belongs to the field of power demand response, and specifically relates to a community charging pile optimization control method, electronic equipment and storage medium. Background Art

[0002] In recent years, with the intensification of global warming, oil resource shortages and energy security issues, in order to achieve the global low-carbon development goals, vehicle types are undergoing rapid changes. The continuous advancement of automotive power battery technology, especially new energy models represented by pure electric vehicles, is becoming the main force driving this change. With the rise of electric vehicles, its subsidiary products, charging piles, are also spread all over the world. Not only are there large-scale charging stations, but there are also private charging piles installed. Despite this, the growth rate of charging piles has slowed down compared to the sales growth rate of new energy vehicles, and the "mileage anxiety" and "endurance pain points" of new energy vehicle owners have also been amplified. The existing charging piles are completely unable to meet the needs of new energy vehicle owners, and this problem has not been effectively solved: the reason is that the load of the community power grid is limited, while the power load of the charging piles is very large, so charging piles cannot be installed in large numbers, so car owners need to go elsewhere to charge.

[0003] Generally speaking, if too many charging piles are installed in a community, when multiple charging piles charge electric vehicles at the same time, the power load will surge. When the power load exceeds the grid load, there will be safety hazards such as tripping or even fire.

[0004] Common machine scheduling methods include: (1) First come first served, assigning tasks to charging piles in the order in which they arrive. This is simple and easy to implement, but may result in a longer average waiting time; (2) Shortest job first, selecting the charging pile with the shortest charging time first, which can minimize the average waiting time, but may cause long tasks to wait too long. (3) Priority scheduling, assigning a priority to each task and scheduling them according to their priority, but this may cause low-priority tasks to wait for a long time and there is a priority inversion problem; (4) Round robin scheduling, assigning tasks to machines according to time slices, and switching to the next task after each task executes a time slice, but this may result in frequent context switching, increase system overhead, and unstable response time, and is not suitable for real-time systems. Summary of the invention

[0005] The problem to be solved by the present invention is to realize the optimization control of charging piles in a residential area, and a method for optimizing the control of charging piles in a residential area, an electronic device and a storage medium are proposed.

[0006] To achieve the above object, the present invention is implemented through the following technical solutions:

[0007] A method for optimizing and controlling charging piles in a residential area comprises the following steps:

[0008] S1. Calculate the total grid load of the community: collect the rated capacity, rated voltage, and transformation ratio data of all transformers in the community, then add up the actual load of each transformer to obtain the total grid load of the community, and set the total grid load of the community to K;

[0009] S2. Collect historical data on electricity consumption of community infrastructure and equipment on a seasonal basis and establish a power load model for community infrastructure;

[0010] S3. Collect historical data on residents’ electricity consumption per day, including hourly electricity consumption, weather conditions, and whether it is a holiday, on a daily basis, and establish a prediction model for the daily electricity consumption of residents in the community;

[0011] S4. Based on the total grid load of the community obtained in step S1, the power load model of the community infrastructure obtained in step S2, and the daily power load prediction model of the community residents obtained in step S3, a charging pile available power load model is established;

[0012] S5. Based on the real-time data of electric vehicles connected to charging piles, a charging pile charging scheduling prediction model is established according to the corresponding time, combined with the power load of community infrastructure and residents;

[0013] S6. Design a priority iterative optimization algorithm to optimize the charging pile charging scheduling prediction model obtained in step S6, and dynamically adjust the number of connected charging piles according to real-time data and prediction results to ensure that the power load is always within a reasonable range.

[0014] Furthermore, the specific implementation method of step S2 includes the following steps:

[0015] S2.1. Collect the electricity consumption of various infrastructure and equipment in the community, including the electricity consumption data of street lights, elevators, water supply and power supply systems, with hourly intervals, including the power consumption and operating time of each device, and clean the collected data to remove abnormal values;

[0016] S2.2. Perform seasonal classification and statistics on the electricity consumption data after data cleaning in step S2.1, and use the python pandas library to perform seasonal classification of equipment electricity consumption, so as to establish a hierarchical structure of community infrastructure electricity load, and divide each equivalent part into different levels according to its load characteristics;

[0017] S2.3. Establish a single community infrastructure power load model, the expression is:

[0018] Y 1 =w 1 x 1 +w 2 x 2 +w3 x 3 +b

[0019] Among them, x 1 is the current season, w 1 is the characteristic value of the current season, x 2 is the current date, w 2 is the characteristic value of the current date, x 3 is the current time point, w 3 is the characteristic value at the current time point, Y 1 is the output power load, b is the bias;

[0020] When the number of samples is multiple, the total power load of the community infrastructure is obtained, and the expression is:

[0021] Y=Xw

[0022] Among them, Y is the total power load of the community infrastructure, X is the attribute matrix, and w is the eigenvalue matrix;

[0023] The squared error loss function is used to calculate the mean loss of multiple samples and obtain the bias b to minimize the total loss of the training samples. The squared error loss function l (i) The expression of (w,b) is:

[0024]

[0025] in, is the output power load forecast value corresponding to infrastructure i, y (i) is the actual value of the output power load corresponding to infrastructure i.

[0026] Furthermore, the specific implementation method of step S3 includes the following steps:

[0027] S3.1. Collect the electricity consumption of community residents every day of the year, and collect data on the weather and whether it is a holiday on that day. Fit the daily electricity load of community residents with the time of day, weather and whether it is a holiday to obtain the daily life electricity load prediction model of community residents. The expression of the daily life electricity load H of community residents at the current moment is obtained as follows:

[0028] H=r 1 k 1 +r 2 k 2 +r 3 k 3 +c

[0029] Among them, k 1 is the time of the day, r 1 is the characteristic value at the time of the day, k 2 For weather,2 is the weather characteristic value, k 3 Is it a holiday? 3 is the characteristic value of whether it is a holiday, and c is the bias of the daily life electricity load prediction model of the community residents;

[0030] S3.2. Set the identification and judgment of outliers by judging whether the power load of the i-th sample deviates from 2 times the standard deviation. The expression is:

[0031]

[0032] Among them, H i is the electricity load of the i-th sample, μ is the mean of n samples, and σ is the standard deviation of the samples;

[0033] If the following conditions are met, then d i is an outlier, and the expression is:

[0034] |H i -μ|>2*σ

[0035] Set the method of filling the median to handle the missing values ​​of the sample. The expression is:

[0036] H filled =median(H 1 ,H 2 ,H 3 ,…,H n )

[0037] Among them, median(·) represents the median of the data;

[0038] S3.3. Combined with the actual observation of smart meters, the current residential electricity load R now Modeling is performed, and the expression is:

[0039] X T Xr'=X T R now

[0040] Among them, X is the characteristic equation, each row represents the attribute characteristics of a sample; r' is the regression coefficient vector; R now The actual observed electricity load of residents in the community at the current moment;

[0041] The root mean square error between different characteristics and power load in the daily life power load prediction model of community residents is used as the first function. Through the optimization algorithm fitting, the minimum value of the first function is made the optimal target, and the optimal characteristic parameters are obtained. The expression of the root mean square error MSE is:

[0042]

[0043] Where n is the number of samples, R nowi is the actual observed electricity load of the residents in the community at the current moment of the i-th sample, is the predicted daily life electricity load of the community residents for the i-th sample; the obtained r' is the optimal parameter of the daily life electricity load prediction model of the community residents.

[0044] Furthermore, the specific implementation method of step S4 includes the following steps:

[0045] S4.1. Calculate the total available electrical load T(t) using the expression:

[0046] T(t) = KHY;

[0047] S4.2. Based on the fact that the load rate of the transformer is usually controlled between 75% and 85% of its rated capacity, the total power load is set to be controlled at 85% of the rated capacity, and the available power load model of the charging pile is established, and the expression is

[0048] T'(t)=K*0.85-HY

[0049] Among them, T'(t) is the available power load of the charging pile.

[0050] Furthermore, the specific implementation method of step S5 includes the following steps:

[0051] S5.1. Set the relevant parameters for establishing the charging pile charging scheduling prediction model, including the available power load T'(t) of the charging pile, the number of electric vehicles connected to the charging pile N, and the initial charge state B of the i-th electric vehicle i 、The battery capacity C of the i-th electric car i 、Rated charging power P of the i-th electric vehicle i 、Charging efficiency of electric vehicles η i ;

[0052] S5.2. Calculate the charging time t of the i-th electric vehicle i , the expression is:

[0053]

[0054] S5.3. Real-time monitoring of the geographical location, usage, number of connected electric vehicles, and power consumption of each charging pile; point-to-point division by household, so as to obtain the usage load data of charging piles in the community on a household basis;

[0055] S5.4. Combine the infrastructure power load model with the residents' daily life power load forecast model to establish a charging pile charging scheduling forecast model, which is expressed as:

[0056] T′(t)≥P f1 +P f2 +…+P ff +P j1 +P j2 +…+P jj

[0057] Among them, P is the residential charging pile usage load data on a household basis extracted from each partition. For the two partitions, f samples and j samples are extracted respectively according to the sorting.

[0058] Furthermore, the specific implementation method of step S6 includes the following steps:

[0059] S6.1. Set an indicator to perform local restrictions. For example, in one day, the charging completion ratio of the vehicles in the first partition of the ordinary zone (0,1) and the advanced zone (0,2) is a:b, where a <b;

[0060] S6.2. Based on the charging pile charging scheduling prediction model constructed in step S5, calculation is performed to obtain the expression:

[0061]

[0062] Among them, A is the theoretical value of the number of vehicles that have completed charging in 24 hours; a is the number of vehicles that have completed charging in the ordinary area of ​​the first partition, and b is the number of vehicles that have completed charging in the advanced area;

[0063] a≤f

[0064] b≤j;

[0065] S6.3. Set U(n,m) as the value of the partition threshold, where U(n,m) is taken from one of the charging times of the electric vehicle, i.e., t i A value in , calculate and sort the A values ​​one by one for all possible U(n,m) values ​​by exhaustive enumeration, and the maximum value obtained is the optimal value;

[0066] After the selection of U(n,m) and the number of iterations is completed, scheduling is performed to ensure that the grid load is always below the limit load to meet the charging needs of each electric vehicle.

[0067] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of a community charging pile optimization control method when executing the computer program.

[0068] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the method for optimizing and controlling charging piles in a residential area.

[0069] Beneficial effects of the present invention:

[0070] The present invention discloses a method for optimizing and controlling charging piles in a residential area, which describes an optimization control algorithm for charging piles in a residential area, assuming that every household in the residential area has an electric car and is equipped with a charging pile. This method satisfies the charging needs of electric vehicles without changing the original grid load. The method includes analyzing the power structure of the residential area; analyzing the comprehensive power consumption of the residential area, i.e., daily life power consumption, infrastructure power consumption, and charging pile power consumption; estimating and predicting the daily life power consumption of residents; estimating and predicting the power consumption of the residential area's infrastructure; collecting the usage of all charging piles in the residential area and the power consumption of electric vehicles in real time, and combining the daily life power consumption prediction and infrastructure power consumption prediction of the residential area, and optimizing the control algorithm to reasonably dispatch charging piles to realize the charging of electric vehicles.

[0071] The method for optimizing and controlling charging piles in a residential area described in the present invention collects the usage of each charging pile in real time, the power of electric vehicles connected to the charging piles, and adjusts the number of connected charging piles in real time in combination with the prediction of daily electricity consumption in the residential area and the prediction of electricity consumption of infrastructure, so that the power load of the residential area is always under the load of the power grid. The method realizes that the charging capacity of the charging piles can be maximized through the scheduling of the optimization control algorithm under the load of the original distribution network.

[0072] The community charging pile optimization control method described in the present invention can adjust the power load of the charging pile in a targeted manner by predicting the power load of the community infrastructure and the power load of the daily life of the community residents; by analyzing the power of the connected electric vehicle, the time it needs to charge can be predicted, and it is connected to the community charging pile system in the form of a point, and through the optimization control model analysis and calculation, the charging time period allocated to it is obtained to meet the charging needs of each electric vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 This is a flow chart of a community charging pile optimization control method according to the present invention;

[0074] Figure 2 Model the electricity load for infrastructure;

[0075] Figure 3 Provide a prediction model for the electricity load in residents' daily life;

[0076] Figure 4 Optimize prediction models for charging stations. DETAILED DESCRIPTION

[0077] In order to make the purpose, technical solution and advantages of the present invention more clear, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention, that is, the specific embodiments described are only part of the embodiments of the present invention, rather than all of the specific embodiments. The components of the specific embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations, and the present invention can also have other embodiments.

[0078] Therefore, the following detailed description of the specific embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents the selected specific embodiments of the present invention. Based on the specific embodiments of the present invention, all other specific embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0079] In order to further understand the content, features and effects of the present invention, the following specific implementation methods are given as examples, and the attached Figure 1 -Attached Figure 4 The detailed instructions are as follows:

[0080] Embodiment 1:

[0081] A method for optimizing and controlling charging piles in a residential area comprises the following steps:

[0082] S1. Calculate the total grid load of the community: collect the rated capacity, rated voltage, and transformation ratio data of all transformers in the community, then add up the actual load of each transformer to obtain the total grid load of the community, and set the total grid load of the community to K;

[0083] S2. Collect historical data on electricity consumption of community infrastructure and equipment on a seasonal basis and establish a power load model for community infrastructure;

[0084] Furthermore, the specific implementation method of step S2 includes the following steps:

[0085] S2.1. Collect the electricity consumption of various infrastructure and equipment in the community, including the electricity consumption data of street lights, elevators, water supply and power supply systems, with hourly intervals, including the power consumption and operating time of each device, and clean the collected data to remove abnormal values;

[0086] S2.2. Perform seasonal classification and statistics on the electricity consumption data after data cleaning in step S2.1, and use the python pandas library to perform seasonal classification of equipment electricity consumption, so as to establish a hierarchical structure of community infrastructure electricity load, and divide each equivalent part into different levels according to its load characteristics;

[0087] A hierarchical equivalent model for power load of community infrastructure is established, wherein the hierarchical equivalent model includes parameters for different seasons; equipment or facilities with similar power consumption patterns are grouped into an equivalent part, that is, multiple equipment are equivalent to a whole, representing the power load of this type of equipment in this season.

[0088] S2.3. Establish a single community infrastructure power load model, the expression is:

[0089] Y 1 =w 1 x 1 +w 2 x 2 +w 3 x 3 +b

[0090] Among them, x 1 is the current season, w 1 is the characteristic value of the current season, x 2 is the current date, w 2 is the characteristic value of the current date, x 3 is the current time point, w 3 is the characteristic value at the current time point, Y 1 is the output power load, b is the bias;

[0091] For example, if we have m samples, each sample has 3 eigenvalues, which is what we mentioned above; then we put all the sample points into the equation:

[0092] Y=w 1 x 1,1 +w 2 x 1,2 +w 3 x 1,3 +b

[0093] Y=w 1 x 2,1 +w 2 x 2,2 +w 3 x 2,3 +b

[0094] …

[0095] Y=w 1 x m,1 +w 2 x m,2 +w 3 x m,3 +b

[0096] When the number of samples is multiple, the total power load of the community infrastructure is obtained, and the expression is:

[0097] Y=Xw

[0098] Among them, Y is the total power load of the community infrastructure, X is the attribute matrix, and w is the eigenvalue matrix;

[0099] The squared error loss function is used to calculate the mean loss of multiple samples and obtain the bias b to minimize the total loss of the training samples. The squared error loss function l (i) The expression of (w,b) is:

[0100]

[0101] in, is the output power load forecast value corresponding to infrastructure i, y (i) is the actual value of the output power load corresponding to infrastructure i.

[0102] The above-mentioned prediction models are used for fitting, and a graded equivalent prediction model is obtained after classification; and historical data is used to evaluate the model to ensure its accuracy and reliability.

[0103] S3. Collect historical data on residents’ electricity consumption per day, including hourly electricity consumption, weather conditions, and whether it is a holiday, on a daily basis, and establish a prediction model for the daily electricity consumption of residents in the community;

[0104] Furthermore, the specific implementation method of step S3 includes the following steps:

[0105] S3.1. Collect the electricity consumption of community residents every day of the year, and collect data on the weather and whether it is a holiday on that day. Fit the daily electricity load of community residents with the time of day, weather and whether it is a holiday to obtain the daily life electricity load prediction model of community residents. The expression of the daily life electricity load H of community residents at the current moment is obtained as follows:

[0106] H=r 1 k 1 +r 2 k 2 +r 3 k 3 +c

[0107] Among them, k 1 is the time of the day, r 1 is the characteristic value at the time of the day, k 2 For weather, 2 is the weather characteristic value, k 3 Is it a holiday? 3 is the characteristic value of whether it is a holiday, and c is the bias of the daily life electricity load prediction model of the community residents;

[0108] Establish the above relationship model, fit and analyze the weather data, whether it is holiday data and the power load at that time, and improve the correlation. Here, a linear regression model similar to requirement 2 is still used to build a prediction model; perform feature engineering processing on the collected data, including outlier processing, missing value processing, and feature extraction to ensure the quality and availability of the data;

[0109] S3.2. Set the identification and judgment of outliers by judging whether the power load of the i-th sample deviates from 2 times the standard deviation. The expression is:

[0110]

[0111] Among them, H i is the electricity load of the i-th sample, μ is the mean of n samples, and σ is the standard deviation of the samples;

[0112] If the following conditions are met, then H i is an outlier, and the expression is:

[0113] |H i -μ|>2*σ

[0114] Set the method of filling the median to handle the missing values ​​of the sample. The expression is:

[0115] H filled =median(H 1 ,H 2 ,H 3 ,…,H n )

[0116] Among them, median(·) represents the median of the data;

[0117] S3.3. Combined with the actual observation of smart meters, the current residential electricity load R now Modeling is performed, and the expression is:

[0118] X T Xr'=X T R now

[0119] Among them, X is the characteristic equation, each row represents the attribute characteristics of a sample; r' is the regression coefficient vector; R now The actual observed electricity load of residents in the community at the current moment;

[0120] The root mean square error between different characteristics and power load in the daily life power load prediction model of community residents is used as the first function. Through the optimization algorithm fitting, the minimum value of the first function is made the optimal target, and the optimal characteristic parameters are obtained. The expression of the root mean square error MSE is:

[0121]

[0122] Where n is the number of samples, R nowi is the actual observed electricity load of the residents in the community at the current moment of the i-th sample, is the predicted daily life electricity load of the community residents for the i-th sample; the obtained r' is the optimal parameter of the daily life electricity load prediction model of the community residents.

[0123] Using the above relationship model, combined with the real-time power load measured by the smart meter, now , establish a prediction model for the daily electricity consumption of community residents, and use historical data to evaluate the model to ensure its accuracy and reliability.

[0124] S4. Based on the total grid load of the community obtained in step S1, the power load model of the community infrastructure obtained in step S2, and the daily power load prediction model of the community residents obtained in step S3, a charging pile available power load model is established;

[0125] Furthermore, the specific implementation method of step S4 includes the following steps:

[0126] S4.1. Calculate the total available electrical load T(t) using the expression:

[0127] T(t) = KHY;

[0128] At this point, it cannot be said that the above is the available power load of the charging pile, because under normal circumstances, the load rate of the transformer is usually controlled between 75% and 85% of its rated capacity, which is more appropriate. The load rate within this range can ensure that the transformer has a certain redundant capacity in long-term operation, improving its stability and reliability. At the same time, the load rate within this range can also ensure the normal operation of the transformer within the rated capacity range, extending its service life. Therefore, the total power load is set to be controlled at 85% of the rated capacity, then the available power load power of the charging pile can be obtained at this time:

[0129] S4.2. Based on the fact that the load rate of the transformer is usually controlled between 75% and 85% of its rated capacity, the total power load is set to be controlled at 85% of the rated capacity, and the available power load model of the charging pile is established, and the expression is

[0130] T'(t)=K*0.85-HY

[0131] Among them, T'(t) is the available power load of the charging pile.

[0132] S5. Based on the real-time data of electric vehicles connected to charging piles, a charging pile charging scheduling prediction model is established according to the corresponding time, combined with the power load of community infrastructure and residents;

[0133] Furthermore, the geographical location, usage, number of connected electric vehicles, and power consumption of electric vehicles of each charging pile are monitored in real time; the above data are divided point by point for each household; thus obtaining the charging pile usage load data P of the community based on the household. i ; Using the above data, combined with the infrastructure power load model and the residents' daily life power load forecasting model, a priority iterative optimization algorithm is adopted, and historical data is used for model evaluation to ensure the accuracy and reliability of the model.

[0134] First, we need to clarify the goal, which is to ensure that the load on the power grid is always below the load limit. Second, we need to consider the efficiency of charging, which is to meet the charging needs of every electric vehicle as much as possible.

[0135] Then, first consider dividing the priorities according to the time required for battery charging. The more time the battery needs to be charged, the higher the priority, and the less time the battery needs to be charged, the lower the priority of the corresponding charging pile node. However, charging cannot be done only by priority. The above background technology mentioned that if it is judged only by priority, then the waiting time for low-priority tasks may be too long, that is, the charging pile fails to charge in time, or even when the owner picks up the car, it is still not charged. Therefore, the charging piles are dynamically divided according to the time required to charge the battery of the electric vehicle, that is, they are divided into ordinary areas and advanced areas. The ordinary area is still charged according to priority, while the advanced area is specifically used to serve low-priority tasks, that is, charging piles that require a shorter charging time to connect to the battery of the electric vehicle.

[0136] With the above introduction, the charging piles can be sorted from most to least according to the time required for charging the connected electric vehicle, and assigned priorities from low to high. Furthermore, the electric vehicle that needs to be charged for less than U(0,0) is divided into the advanced zone (0,2), and correspondingly, the electric vehicle that needs to be charged for more than U(0,0) is divided into the ordinary zone (0,1). The ordinary zone and the advanced zone can be further divided into their ordinary zone sub-zones and advanced zone sub-zones, and the division is continued until one electric vehicle occupies one sub-zone. The purpose of this is to avoid the phenomenon of local optimal solutions during iteration. In this way, by comparing the optimal values ​​calculated for each part, the overall optimal value is taken to determine the optimal solution. In this way, the partition results and specific data can be obtained.

[0137] Charging is performed based on the above data. At the same time, it is detected whether the grid load exceeds the set threshold or the load fluctuation is greater than 15% and whether there are new electric vehicles connected: (1) Whether the grid load exceeds the set threshold. If not, the detection is repeated; if it exceeds or the fluctuation is too large, it jumps back to the partitioning step to re-partition the access of electric vehicles. (2) Whether there are new electric vehicles connected. If the number of connected cars is the same as or less than the original number, the number of connected cars is repeatedly detected; if it is more than the original number, it is determined whether there are any charging cars that have reached the partition threshold or are fully charged. If not, it enters the detection of the number of connected cars and waits while detecting; if yes, it jumps back to the start step to calculate.

[0138] Furthermore, the specific implementation method of step S5 includes the following steps:

[0139] S5.1. Set the relevant parameters for establishing the charging pile charging scheduling prediction model, including the available power load T'(t) of the charging pile, the number of electric vehicles connected to the charging pile N, and the initial charge state B of the i-th electric vehicle i 、The battery capacity C of the i-th electric car i 、Rated charging power P of the i-th electric vehicle i 、Charging efficiency of electric vehicles η i ;

[0140] S5.2. Calculate the charging time t of the i-th electric vehicle i , the expression is:

[0141]

[0142] S5.3. Real-time monitoring of the geographical location, usage, number of connected electric vehicles, and power consumption of each charging pile; point-to-point division by household, so as to obtain the usage load data of charging piles in the community on a household basis;

[0143] S5.4. Combine the infrastructure power load model with the residents' daily life power load forecast model to establish a charging pile charging scheduling forecast model, which is expressed as:

[0144] T′(t)≥P f1 +P f2 +…+P ff +P j1 +P j2 +…+P jj

[0145] Among them, P is the residential charging pile usage load data on a household basis extracted from each partition. For the two partitions, f samples and j samples are extracted respectively according to the sorting.

[0146] S6. Design a priority iterative optimization algorithm to optimize the charging pile charging scheduling prediction model obtained in step S6, and dynamically adjust the number of connected charging piles according to real-time data and prediction results to ensure that the power load is always within a reasonable range.

[0147] The calculation of the optimal value mentioned above is the optimal value of each partition. The goal mentioned above is to ensure that the load of the power grid is always under the load limit and to meet the charging needs of each electric vehicle as much as possible. If it is judged only by the number of cars that have completed charging, there will inevitably be a reverse problem of the previous priority, that is, tasks with low priority will be executed first, which is contrary to the priority algorithm, so it cannot be judged based on this indicator. Then it is necessary to set an indicator for local restriction;

[0148] Furthermore, the specific implementation method of step S6 includes the following steps:

[0149] S6.1. Set an indicator to perform local restrictions. For example, in one day, the charging completion ratio of the vehicles in the first partition of the ordinary zone (0,1) and the advanced zone (0,2) is a:b, where a <b;

[0150] S6.2. Based on the charging pile charging scheduling prediction model constructed in step S5, calculation is performed to obtain the expression:

[0151]

[0152] Among them, A is the theoretical value of the number of vehicles that have completed charging in 24 hours; a is the number of vehicles that have completed charging in the ordinary area of ​​the first partition, and b is the number of vehicles that have completed charging in the advanced area;

[0153] a≤f

[0154] b≤j;

[0155] S6.3. Set U(n,m) as the value of the partition threshold, where U(n,m) is taken from one of the charging times of the electric vehicle, i.e., t i A value in , calculate and sort the A values ​​one by one for all possible U(n,m) values ​​by exhaustive enumeration, and the minimum value found is the optimal value;

[0156] After the selection of U(n,m) and the number of iterations is completed, scheduling is performed to ensure that the grid load is always below the limit load to meet the charging needs of each electric vehicle.

[0157] Embodiment 2:

[0158] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a community charging pile optimization control method described in Example 1 are implemented.

[0159] The computer device of the present invention may be a device including a processor and a memory, such as a single chip microcomputer including a central processing unit, etc. Moreover, the processor is used to implement the steps of the above-mentioned method for optimizing and controlling charging piles in a residential area when executing a computer program stored in the memory.

[0160] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0161] The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0162] Embodiment 3:

[0163] A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for optimizing and controlling a charging pile in a residential area described in Example 1 is implemented.

[0164] The computer-readable storage medium of the present invention can be any form of storage medium that can be read by the processor of a computer device, including but not limited to non-volatile memory, volatile memory, ferroelectric memory, etc. The computer-readable storage medium stores a computer program. When the processor of the computer device reads and executes the computer program stored in the memory, the steps of the above-mentioned community charging pile optimization control method can be implemented.

[0165] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer readable media do not include electric carrier signals and telecommunication signals.

[0166] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0167] Although the present application has been described above with reference to specific embodiments, various modifications may be made thereto and parts thereof may be replaced with equivalents without departing from the scope of the present application. In particular, as long as there is no structural conflict, the various features in the specific embodiments disclosed in the present application may be used in combination with each other in any manner, and the fact that these combinations are not exhaustively described in this specification is only for the sake of omitting space and saving resources. Therefore, the present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for optimizing and controlling charging piles in a residential area, characterized in that: The steps include: S1. Calculate the total grid load of the community: collect the rated capacity, rated voltage, and transformation ratio data of all transformers in the community, then add up the actual load of each transformer to obtain the total grid load of the community, and set the total grid load of the community to K; S2. Collect historical data on electricity consumption of community infrastructure and equipment on a seasonal basis and establish a power load model for community infrastructure; S3. Collect historical data on residents’ electricity consumption per day, including hourly electricity consumption, weather conditions, and whether it is a holiday, on a daily basis, and establish a prediction model for the daily electricity consumption of residents in the community; S4. Based on the total grid load of the community obtained in step S1, the power load model of the community infrastructure obtained in step S2, and the daily power load prediction model of the community residents obtained in step S3, a charging pile available power load model is established; S5. Based on the real-time data of electric vehicles connected to charging piles, a charging pile charging scheduling prediction model is established according to the corresponding time, combined with the power load of community infrastructure and residents; S6. Design a priority iterative optimization algorithm to optimize the charging pile charging scheduling prediction model obtained in step S6, and dynamically adjust the number of connected charging piles according to real-time data and prediction results to ensure that the power load is always within a reasonable range.

2. A community charging pile optimization control method according to claim 1, characterized in that: The specific implementation method of step S2 includes the following steps: S2.

1. Collect the electricity consumption of various infrastructure and equipment in the community, including the electricity consumption data of street lights, elevators, water supply and power supply systems, with hourly intervals, including the power consumption and operating time of each device, and clean the collected data to remove abnormal values; S2.

2. Perform seasonal classification and statistics on the electricity consumption data after data cleaning in step S2.1, and use the python pandas library to perform seasonal classification of equipment electricity consumption, so as to establish a hierarchical structure of community infrastructure electricity load, and divide each equivalent part into different levels according to its load characteristics; S2.

3. Establish a single community infrastructure power load model, the expression is: Y1=w1x1+w2x2+w3x3+b Among them, x1 is the current season, w1 is the characteristic value of the current season, x2 is the current date, w2 is the characteristic value of the current date, x3 is the current time point, w3 is the characteristic value of the current time point, Y1 is the output power load, and b is the offset; When the number of samples is multiple, the total power load of the community infrastructure is obtained, and the expression is: Y=Xw Among them, Y is the total power load of the community infrastructure, X is the attribute matrix, and w is the eigenvalue matrix; The squared error loss function is used to calculate the mean loss of multiple samples and obtain the bias b to minimize the total loss of the training samples. The squared error loss function l (i) The expression of (w,b) is: in, is the output power load forecast value corresponding to infrastructure i, y (i) is the actual value of the output power load corresponding to infrastructure i.

3. A community charging pile optimization control method according to claim 2, characterized in that: The specific implementation method of step S3 includes the following steps: S3.

1. Collect the electricity consumption of community residents every day of the year, and collect data on the weather and whether it is a holiday on that day. Fit the daily electricity load of community residents with the time of day, weather and whether it is a holiday to obtain the daily life electricity load prediction model of community residents. The expression of the daily life electricity load H of community residents at the current moment is obtained as follows: H=r1k1+r2k2+r3k3+c Among them, k1 is the time of the day, r1 is the characteristic value of the time of the day, k2 is the weather, r2 is the weather characteristic value, k3 is whether it is a holiday, r3 is the characteristic value of whether it is a holiday, and c is the bias of the daily life power load prediction model of the community residents; S3.

2. Set the identification and judgment of outliers by judging whether the power load of the i-th sample deviates from 2 times the standard deviation. The expression is: Among them, H i is the electricity load of the i-th sample, μ is the mean of n samples, and σ is the standard deviation of the samples; If the following conditions are met, then H i is an outlier, and the expression is: |H i -μ|>2*σ Set the method of filling the median to handle the missing values ​​of the sample. The expression is: H filled =median(H1,H2,H3,…,H n ) Among them, median(·) represents the median of the data; S3.

3. Combined with the actual observation of smart meters, the current residential electricity load R now Modeling is performed, and the expression is: X T Xr'=X T R now Among them, X is the characteristic equation, each row represents the attribute characteristics of a sample; r' is the regression coefficient vector; R now The actual observed electricity load of residents in the community at the current moment; The root mean square error between different characteristics and power load in the daily life power load prediction model of community residents is used as the first function. Through the optimization algorithm fitting, the minimum value of the first function is made the optimal target, and the optimal characteristic parameters are obtained. The expression of the root mean square error MSE is: Where n is the number of samples, R nowi is the actual observed electricity load of the residents in the community at the current moment of the i-th sample, is the predicted daily life electricity load of the community residents for the i-th sample; the obtained r' is the optimal parameter of the daily life electricity load prediction model of the community residents.

4. A community charging pile optimization control method according to claim 3, characterized in that: The specific implementation method of step S4 includes the following steps: S4.

1. Calculate the total available electrical load T(t) using the expression: T(t) = KHY; S4.

2. Based on the fact that the load rate of the transformer is usually controlled between 75% and 85% of its rated capacity, the total power load is set to be controlled at 85% of the rated capacity, and the available power load model of the charging pile is established, and the expression is T'(t)=K*0.85-HY Among them, T'(t) is the available power load of the charging pile.

5. A community charging pile optimization control method according to claim 4, characterized in that: The specific implementation method of step S5 includes the following steps: S5.

1. Set the relevant parameters for establishing the charging pile charging scheduling prediction model, including the available power load T'(t) of the charging pile, the number of electric vehicles connected to the charging pile N, and the initial charge state B of the i-th electric vehicle i 、The battery capacity C of the i-th electric car i 、Rated charging power P of the i-th electric vehicle i 、Charging efficiency of electric vehicles η i ; S5.

2. Calculate the charging time t of the i-th electric vehicle i , the expression is: S5.

3. Real-time monitoring of the geographical location, usage, number of connected electric vehicles, and power consumption of each charging pile; point-to-point division by household, so as to obtain the usage load data of charging piles in the community on a household basis; S5.

4. Combine the infrastructure power load model with the residents' daily life power load forecast model to establish a charging pile charging scheduling forecast model, which is expressed as: T′(t)≥P f1 +P f2 +…+P ff +P j1 +P j2 +…+P jj Among them, P is the residential charging pile usage load data on a household basis extracted from each partition. For the two partitions, f samples and j samples are extracted respectively according to the sorting.

6. A community charging pile optimization control method according to claim 5, characterized in that: The specific implementation method of step S6 includes the following steps: S6.

1. Set an indicator to perform local restrictions. For example, in one day, the first partition of the cars that complete charging is the ordinary zone (0,1) and the advanced zone (0,2). The charging completion ratio of the vehicles involved is a:b, where a <b; S6.

2. Based on the charging pile charging scheduling prediction model constructed in step S5, calculation is performed to obtain the expression: Among them, A is the theoretical value of the number of vehicles that have completed charging in 24 hours; a is the number of vehicles that have completed charging in the ordinary area of ​​the first partition, and b is the number of vehicles that have completed charging in the advanced area; a≤f b≤j; S6.

3. Set U(n,m) as the value of the partition threshold, where U(n,m) is taken from one of the charging times of the electric vehicle, i.e., t i A value in , calculate and sort the A values ​​one by one for all possible U(n,m) values ​​by exhaustive enumeration, and the maximum value obtained is the optimal value; After the selection of U(n,m) and the number of iterations is completed, scheduling is performed to ensure that the grid load is always below the limit load to meet the charging needs of each electric vehicle.

7. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of a community charging pile optimization control method as described in any one of claims 1 to 6 when executing the computer program.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for optimizing and controlling a charging pile in a residential area according to any one of claims 1 to 6 is implemented.

Images