Intelligent charging pile off-peak charging method and intelligent charging pile system

Abstract

The invention discloses an off-peak charging method for an intelligent charging pile and an intelligent charging pile system, relates to the technical field of off-peak charging, and aims to solve the problems that color deviation is generated due to the fact that environmental factors are not considered in the conventional license plate recognition technology; the problem that the charging pile may be overloaded due to the fact that the charging requirement of a large number of vehicles cannot be effectively handled, or overhigh power is still maintained when the requirement is low, and energy is wasted is solved. The system can integrate environmental factors, dynamically correct the power adjustment range of the charging pile to better adapt to different weather and illumination conditions, adjust through a time sequence model to ensure more reasonable power distribution, predict and adjust the power of the charging pile in real time according to historical data, and improve the charging efficiency. And the flexibility and adaptability of the charging pile in different time periods and environment conditions are improved, so that more accurate off-peak charging and power load balance are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of staggered charging, and more specifically, to a smart charging pile staggered charging method and a smart charging pile system. Background Art

[0002] With the rapid development of new energy vehicles, the popularity of electric vehicles (EVs) and the demand for charging are increasing. As the charging infrastructure for electric vehicles, the use and management efficiency of charging piles has become a key issue. In order to avoid excessive pressure on the power grid caused by charging demand during peak hours and to achieve more efficient and economical energy utilization during the charging process, smart charging pile systems have come into being. By integrating modern information technology, communication technology, and power management technology, smart charging piles can achieve peak-shifting charging, optimize the allocation of power resources, reduce the burden on the power grid, and improve users' charging experience.

[0003] The prior art has the following deficiencies:

[0004] Previous license plate recognition technology did not take into account the color deviation caused by environmental factors, such as the degree of haze particles and whether it is sunrise or sunset, which will increase the yellow value of the light source and cause color deviation. Existing technologies do not consider this aspect. During high-demand periods, charging piles may be overloaded due to the inability to effectively handle the charging needs of a large number of vehicles, or maintain too high power when demand is low, resulting in energy waste. The peak-shifting charging scheduling of traditional charging piles is mostly static, without sufficient real-time dynamic adjustment capabilities.

[0005] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a smart charging pile staggered charging method and a smart charging pile system to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A smart charging pile peak-shifting charging method and a smart charging pile system, comprising the following steps:

[0009] Step S1: Identify the license plate color captured by a high-resolution camera installed at the entrance of the highway, use the HSV model to distinguish the color of the photograph, and distinguish electric vehicles from ordinary cars;

[0010] Step S2: Obtain the current haze particle level and whether it is during sunrise or sunset to determine the current yellow light percentage, and determine the current photo exposure based on the V data in HSV, and determine the fuzzy range of the H value based on the above data, use the white balance algorithm to obtain the color temperature deviation value, correct the H value within the fuzzy range, and record the current electric vehicle traffic volume;

[0011] Step S3: Obtain temperature data of a built-in temperature sensor of the charging pile and average vehicle speed data and determine whether the power of the charging pile is reasonable in combination with the flow rate of electric vehicles;

[0012] Step S4: modify and adjust the unreasonable charging power of the charging pile using the time series model.

[0013] In a preferred embodiment, step S1 includes the following contents:

[0014] Identify the vehicle photos taken by the high-resolution camera installed at the entrance of the highway, use Canny edge detection to obtain the license plate area in the recognition image, and determine the location of the license plate by finding the rectangular area in the image. After the license plate position is recognized, the license plate area is cropped to obtain a clearer license plate image portion;

[0015] The license plate RGB image is converted into the HSV color space. For each license plate area, its H value is calculated and compared with the threshold. The H threshold is set. When it is less than the threshold, the license plate is considered to be green and belongs to an electric car; when it is greater than the threshold, the license plate is considered to be blue and belongs to an ordinary car.

[0016] In a preferred embodiment, step S2 includes the following contents:

[0017] Get the degree of haze particles and sunrise and sunset periods: Use the air quality API to obtain the real-time concentration of PM2.5 or PM10. The 30 minutes before and after sunrise is recorded as the sunrise period, and the 30 minutes before and after sunset is recorded as the sunset period;

[0018] The formula for calculating the percentage of yellow light is: Yellow light percentage = Base Yellow Light × (1 + f PM2.5 ×PM2.5)×f Sunligh Period , where: Base Yellow Light: basic yellow light ratio. Under normal clear weather conditions, the yellow light component in sunlight is 50%, which is used as the benchmark; f PM2.5 :The influence coefficient of PM2.5 on yellow light is set to 0.005, that is, when the PM2.5 concentration increases by 1μg / m 3 , the percentage of yellow light increases by 0.5%; PM2.5: the concentration of PM2.5, f SUnlight Period: Correction coefficient for sunrise and sunset periods, the values ​​are: 1.2: the current time is in the sunrise and sunset period (assuming 30 minutes before and after sunrise, 30 minutes before and after sunset), 1: the current time is not in the sunrise and sunset period;

[0019] Get the pixel value of the V channel in the image, and normalize the pixel value of the V channel to a standard range by dividing each pixel value of the V channel by 255;

[0020] The adjustment coefficient comprehensively considers the yellow light percentage and the normalized V value, and uses the following simple weighted average method: Adjustment coefficient = w1×Yellow Light Percentage+w2×Normalized V, where: w1 and w2 are weight coefficients, which control the influence of the yellow light percentage and the normalized V value on the final adjustment coefficient, w1+w2=1 (for example, w1 can be set to 0.3, w20.7); Yellow Light Percentage: the calculated yellow light percentage; Normalized V: the normalized V value;

[0021] The basic fuzzy range is set to 80-100, and the adjustment is performed according to the adjustment coefficient. According to the adjustment coefficient k (the value range is from 0 to 1), the fuzzy range is adjusted. The fuzzy range = [80-αk, 100+αk], where: α is used to control the amplitude of the adjustment, indicating the influence of the coefficient k on the fuzzy range, which is set by technicians in this field according to actual conditions. k is the adjustment coefficient, and the value range is between 0 and 1. When k = 0, the fuzzy range is 80 to 100, that is, no adjustment. When k = 1, the fuzzy range is [80-α, 100+α], that is, maximum adjustment.

[0022] White balance gain G r and G b It is calculated by comparing the brightness of the red and blue channels with the brightness of the green channel, and the formula is expressed as: Where: I r is the average brightness of the red channel, I g is the average brightness of the green channel, I b is the average brightness of the blue channel;

[0023] Color temperature is usually expressed as a temperature in white light, in Kelvin. For most cameras or image processing systems, color temperature is related to gain, and the color temperature can be estimated from the gain value: Where C is a constant, with a value of 3000 Kelvin;

[0024] The color temperature deviation value refers to the difference between the color temperature of the actual camera image and the ideal white point (e.g. 6500K neutral color temperature). The calculation formula of the deviation value is expressed as: ΔT = TTideal , where: T is the estimated color temperature, is the ideal white point color temperature, set to 6500K;

[0025] For the H value within the fuzzy interval, deviation adjustment is performed and a constant K is set. H To express the change in color temperature per unit deviation from the corresponding H value, the formula for correcting the H value is expressed as: H new =HK H ×ΔT, where: H new is the corrected hue value, H is the hue value of the original image, K H is a constant that indicates the influence of color temperature deviation on hue. ΔT is the deviation value of color temperature. After the H value in the fuzzy interval is adjusted, the H threshold is set. When it is less than the threshold, the license plate is considered to be green and belongs to an electric car; when it is greater than the threshold, the license plate is considered to be blue and belongs to an ordinary car, and the traffic flow of electric vehicles is recorded.

[0026] In a preferred embodiment, step S3 includes the following contents:

[0027] Get the temperature data of the built-in temperature sensor of the charging pile and the average vehicle speed data;

[0028] After receiving the temperature data, the average vehicle speed data, and the flow of electric vehicles, the temperature data, the average vehicle speed data, and the flow of electric vehicles are defined as input variables, and they are divided into different fuzzy sets respectively;

[0029] Whether the charging power is reasonable is defined as the output variable and divided into fuzzy sets;

[0030] Formulate fuzzy rules to describe the impact of temperature data, average vehicle speed data, and electric vehicle flow definition on whether the charging power is reasonable;

[0031] Fuzzy reasoning is performed based on fuzzy rules to determine whether the charging power is reasonable.

[0032] In a preferred embodiment, step S4 includes the following contents:

[0033] For unreasonable charging power schemes, power allocation forecasting and analysis are performed through time series models to determine the optimal adjustment of the initial power allocation scheme;

[0034] The time series model uses the ARIMAX model. The specific steps for power allocation forecasting and analysis using the time series model are as follows:

[0035] Step A1, obtaining prediction data;

[0036] Step A2, establishing an ARIMAX model;

[0037] Step A3, using the maximum likelihood estimation (MLE) method to estimate the ARIMAX model parameters;

[0038] Step A4, verify the effect of the fitting model and check the goodness of fit of the model by residual analysis;

[0039] Step A5, using the fitted model to predict the future power allocation plan, and taking the maximum value of the prediction result as the highest point of power demand in the future time period;

[0040] The exogenous variables in the ARIMAX model include temperature data, average vehicle speed data, and electric vehicle traffic. The ARIMAX model formula is:

[0041] In the formula, y t is the power demand at the current time point, α is a constant term, is the i-th order autoregressive parameter, p is the order of the autoregressive term, θ j is the jth order moving average parameter, q is the order of the moving average term, ∈ t is a white noise term, representing random error, β k is an exogenous variable X t-k The coefficient of m is the lag order of the exogenous variable, X t-k is an exogenous variable lagged by k periods;

[0042] In step A3, α, θ1, β1, and β2 are calculated using the maximum likelihood estimation method.

[0043] A smart charging pile peak-shifting charging and smart charging pile system, including: an identification and differentiation module, a fuzzy correction module, a power detection module and a modification and adjustment module:

[0044] Identification and differentiation module: Identify the license plate color captured by the high-resolution camera installed at the entrance of the highway, use the HSV model to distinguish the color of the photo, and distinguish between electric vehicles and ordinary cars;

[0045] Blur correction module: obtain the current haze particle level and whether it is during sunrise and sunset to determine the current yellow light percentage, and determine the current photo exposure based on the V data in HSV. Combine the above data to determine the fuzzy range of the H value, use the white balance algorithm to obtain the color temperature deviation value, correct the H value within the fuzzy range, and record the current electric vehicle traffic volume;

[0046] Power detection module: obtains the temperature data of the built-in temperature sensor of the charging pile and the average speed data, and determines whether the power of the charging pile is reasonable in combination with the electric vehicle traffic flow;

[0047] Modification and adjustment module: Modify and adjust the unreasonable charging power of the charging pile using the time series model.

[0048] The technical effects and advantages of the intelligent charging pile peak-shifting charging method and intelligent charging pile system of the present invention are as follows:

[0049] By analyzing haze and exposure, the system can integrate environmental factors and dynamically correct the power adjustment range of the charging pile to better adapt to different weather and lighting conditions, thereby optimizing charging efficiency and power utilization. Combined with temperature sensor data and vehicle speed information, it can more accurately determine whether the charging pile is in a reasonable working state. If the power of the charging pile is abnormal, the system can make adjustments through the time series model to ensure more reasonable power distribution. The power of the charging pile can be predicted and adjusted in real time based on historical data, thereby improving the flexibility and adaptability of the charging pile in different time periods and environmental conditions, thereby achieving more accurate peak-shifting charging and power load balance. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a structural schematic diagram of a peak-shifting charging method for an intelligent charging pile according to the present invention.

[0051] Figure 2 It is a schematic diagram of the structure of a smart charging pile peak-shifting charging and a smart charging pile system according to the present invention. DETAILED DESCRIPTION

[0052] 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.

[0053] Example 1

[0054] The present invention Figure 1 As shown, the present invention discloses a peak-shifting charging method for an intelligent charging pile, comprising the following steps:

[0055] Step S1: Identify the license plate color captured by a high-resolution camera installed at the entrance of the highway, use the HSV model to distinguish the color of the photograph, and distinguish electric vehicles from ordinary cars;

[0056] Step S2: Obtain the current haze particle level and whether it is during sunrise or sunset to determine the current yellow light percentage, and determine the current photo exposure based on the V data in HSV, and determine the fuzzy range of the H value based on the above data, use the white balance algorithm to obtain the color temperature deviation value, correct the H value within the fuzzy range, and record the current electric vehicle traffic volume;

[0057] Step S3: Obtain temperature data of a built-in temperature sensor of the charging pile and average vehicle speed data and determine whether the power of the charging pile is reasonable in combination with the flow rate of electric vehicles;

[0058] Step S4: modify and adjust the unreasonable charging power of the charging pile using the time series model.

[0059] In step S1, the license plate color captured by the high-resolution camera installed at the entrance of the highway is identified, and the HSV model is used to distinguish the color of the photographed car and distinguish electric vehicles from ordinary cars. The specific contents include:

[0060] The high-resolution camera installed at the entrance of the highway takes a photo of the vehicle, and uses Canny edge detection or contour extraction to identify the license plate area in the image. By finding the rectangular area in the image, the position of the license plate can be determined. After the license plate position is identified, the license plate area is cropped out to obtain a clearer license plate image portion.

[0061] The license plate RGB image is converted to the HSV color space. In the HSV model, H represents hue, S represents saturation, and V represents brightness. The hue H of green is usually between 40 and 80, and the hue H of blue is usually between 100 and 140. The saturation S and brightness V of blue and green are similar, both S∈[60,255] and V∈[50,255]. Therefore, only by the value of hue H, electric vehicles (green license plates) and ordinary cars (blue license plates) can be effectively distinguished. For each license plate area, its H value is calculated and compared with the threshold value, and classified as electric vehicles or ordinary cars. According to the different H values ​​of blue and green above, the H threshold is set. When it is less than the threshold, the license plate is considered to be green and the license plate belongs to an electric car; when it is greater than the threshold, the license plate is considered to be blue and the license plate belongs to an ordinary car.

[0062] In step S2, the current haze particle level and whether it is in the sunrise and sunset period are obtained to determine the current yellow light percentage, and the exposure level of the current photo is determined based on the V data in HSV. The fuzzy range of the H value is determined based on the above data, and the deviation value of the color temperature is obtained using the white balance algorithm. The H value within the fuzzy range is corrected, and the current electric vehicle traffic volume is recorded. The specific contents include:

[0063] Get the degree of haze particles and sunrise and sunset periods: The degree of haze particles and the sunrise and sunset periods affect the percentage of yellow light. Use the air quality API to obtain the real-time concentration of PM2.5 or PM10. Haze increases the particulate matter in the air, which increases the scattering of light, especially short-wavelength blue light. After the blue light is scattered, the remaining light wavelength is relatively long, mainly yellow and red light components. Therefore, the light source will look more yellow in a haze environment, which will increase the yellowness value of the light, causing the color temperature to change, and then affect the distribution of H, S, and V values. Use astronomical calculation tools to obtain the sunrise and sunset times of the current location to accurately determine whether a certain moment belongs to sunrise or sunset, and determine whether it is close to the sunrise or sunset period based on the current time. Specifically: 30 minutes before and after sunrise: considered as the sunrise period, 30 minutes before and after sunset: considered as the sunset period. At sunrise and sunset, the color temperature of sunlight will tend to yellow and orange. The path of sunlight through the atmosphere is longer, and the short wavelengths in the light will be scattered, while the long wavelength light is relatively less scattered and finally reaches the ground. The angle of sunlight is low, which may increase the component of yellow light.

[0064] Based on the above influencing factors, the following simplified model is designed to calculate the percentage of yellow light: Yellow light percentage = Base Yellow Light × (1 + f PM2.5 ×PM2.5)×f Sunlight Period , where: Base Yellow Light: basic yellow light ratio. Under normal clear weather conditions, the yellow light component in sunlight is 50%, which is used as the benchmark; f PM2.5 :The influence coefficient of PM2.5 on yellow light is set to 0.005, that is, when the PM2.5 concentration increases by 1μg / m 3 , the percentage of yellow light increases by 0.5%; PM2.5: the concentration of PM2.5, f Sunlight Period : Correction coefficient for sunrise and sunset periods, the values ​​are: 1.2: the current time is in the sunrise and sunset period (assuming 30 minutes before and after sunrise, 30 minutes before and after sunset), 1: the current time is not in the sunrise and sunset period.

[0065] The value of the V channel is usually in the range of 0 to 255, representing the brightness of the image. By calculating the average value of this channel, you can understand the overall exposure of the image. Evaluate the exposure level: if the average value is close to 255, the image is overexposed, if the average value is close to 0, the image is underexposed, and a medium value indicates proper exposure. And the pixel values ​​of the V channel are normalized and adjusted to a standard range, which is done by dividing each pixel value of the V channel by 255.

[0066] The adjustment coefficient takes into account the yellow light percentage and the normalized V value, and the following simple weighted average method can be used: Adjustment Coefficient = w1×Yellow Light Percentage+w2×Normalized V, where: w1 and w2 are weight coefficients, which control the influence of the yellow light percentage and the normalized V value on the final adjustment coefficient, w1+w2=1 (for example, w1 can be set to 0.3, w20.7); Yellow Light Percentage: the calculated yellow light percentage; Normalized V: the normalized V value.

[0067] Since the green hue H is usually between 40 and 80, and the blue hue H is usually between 100 and 140, the basic fuzzy range is set to 80-100, and adjusted according to the adjustment coefficient. According to the adjustment coefficient k (the value range is from 0 to 1), the fuzzy range is adjusted, and the fuzzy range = [80-αk, 100+αk], where: α is used to control the amplitude of the adjustment, indicating the influence of the coefficient k on the fuzzy range, which is set by technicians in this field according to actual conditions, k is the adjustment coefficient, and the value range is between 0 and 1. When k = 0, the fuzzy range is 80 to 100, that is, no adjustment, and when k = 1, the fuzzy range is [80-α, 100+α], that is, maximum adjustment.

[0068] White balance gain G r and G b It is calculated by comparing the brightness of the red and blue channels with the brightness of the green channel, and the formula is expressed as: Where: I r is the average brightness of the red channel, I g is the average brightness of the green channel, I b is the average brightness of the blue channel.

[0069] Color temperature is usually expressed as a temperature of color in white light in Kelvin (K). For most cameras or image processing systems, color temperature is related to gain and can be estimated from the gain value: where C is a constant, usually taken as about 3000 Kelvin.

[0070] The color temperature deviation value refers to the difference between the color temperature of the actual camera image and the ideal white point (e.g. 6500K neutral color temperature). The calculation formula of the deviation value is expressed as: ΔT = TT ideal , where: T is the estimated color temperature, is the ideal white point color temperature, usually set to 6500K (standard white temperature).

[0071] For the H value within the fuzzy interval, deviation adjustment is performed and a constant K is set. HTo express the change in color temperature per unit deviation from the corresponding H value, the formula for correcting the H value is expressed as: H new =HK H ×ΔT, where: H new is the corrected hue value, H is the hue value of the original image, K H is a constant that indicates the influence of color temperature deviation on hue, and ΔT is the deviation value of color temperature. After the H value in the fuzzy interval is adjusted, the H threshold is set. When it is less than the threshold, the license plate is considered to be green and belongs to an electric car; when it is greater than the threshold, the license plate is considered to be blue and belongs to an ordinary car, and the traffic volume of electric cars is recorded.

[0072] In step S3, the temperature data of the built-in temperature sensor of the charging pile and the average speed data are obtained and combined with the traffic volume of electric vehicles to determine whether the power of the charging pile is reasonable. The specific contents include:

[0073] The temperature data of the built-in temperature sensor of the charging pile and the average vehicle speed data are obtained, and combined with the electric vehicle traffic flow, it is determined whether the power of the charging pile is reasonable.

[0074] It should be noted that the temperature sensor of the charging pile can provide data about the battery, the internal temperature of the charging equipment and the ambient temperature. Excessive temperature may indicate that the charging pile is overloaded or the heat dissipation is insufficient, which may cause the equipment to overheat and affect the charging efficiency. Therefore, a reasonable temperature range is crucial to determine whether the charging pile is in a reasonable working condition. The average vehicle speed helps to determine the traffic flow and capacity near the charging pile. Lower speeds may mean traffic congestion, which may cause more electric vehicles to stay in the area and use the charging pile. The flow of electric vehicles directly affects the charging demand. When the traffic flow is high, the charging demand increases, so it is necessary to find a period of time with less charging demand to avoid excessive gathering of electric vehicles.

[0075] After receiving the temperature data, the average vehicle speed data, and the flow of electric vehicles, the temperature data, the average vehicle speed data, and the flow of electric vehicles are defined as input variables, and are divided into different fuzzy sets, respectively.

[0076] For example, "Cold", "Normal", "Hot" for the overall temperature coefficient, "Low", "Medium", "High" for the average vehicle speed data, and "Low", "Medium", "High" for the flow of electric vehicles.

[0077] Whether the charging power is reasonable is defined as the output variable and divided into fuzzy sets, for example, "Yes", "No" for whether the charging power is reasonable.

[0078] Formulate a set of fuzzy rules to describe the impact of different input variables on output variables. The definition of rules can be based on professional knowledge or obtained through data analysis and experiments. For example:

[0079] The overall temperature coefficient is marked as T, the average speed data is marked as C, the flow rate of electric vehicles is marked as B, and whether the charging power is reasonable is marked as P_power.

[0080] Rule 1:IF(T is Cold)AND(C is Low)AND(B is Low)THEN(P_power is Yes)

[0081] Rule 2:IF(T is Hot)AND(C is High)AND(B is High)THEN(P_power is No) ...

[0083] Fuzzy reasoning is performed based on fuzzy rules to determine whether the charging power is reasonable.

[0084] It should be noted that the division of fuzzy sets can be adjusted according to actual conditions. For example, although this embodiment takes four fuzzy sets as examples, in fact, the overall temperature coefficient, average vehicle speed data, electric vehicle flow and charging power can be reasonably divided into more than four sets to facilitate better precise adjustment according to different situations.

[0085] Furthermore, for the judgment of the overall temperature coefficient and the high, medium and low flow of electric vehicles, thresholds can be set according to actual conditions. For example, when the overall temperature coefficient exceeds 40 degrees Celsius, it is marked as "Hot", and when the flow of electric vehicles is higher than 80%, it is marked as "High", etc., which will not be elaborated here.

[0086] The proportion of the number of unreasonable charging pile charging powers is calculated. When the proportion of the number of unreasonable charging pile charging powers reaches a set threshold, step S4 is performed to adjust the charging power of the charging piles. The threshold can be set by technicians in this field according to actual conditions.

[0087] In step S4, the unreasonable charging pile charging power is modified and adjusted using the time series model, and the specific contents include:

[0088] Obtain unreasonable charging power solutions, perform power allocation forecasting and analysis through time series models, and further refine and optimize the initial power allocation solution;

[0089] It should be noted that the time series model of this embodiment adopts the ARIMAX model. Refining and optimizing the initialization power allocation scheme means that when it is determined that the current initialization power allocation scheme is unreasonable, further analysis and adjustment are made to make the power allocation scheme more scientific and reasonable, thereby realizing the control of the power allocation of the charging pile.

[0090] Furthermore, the specific steps of power distribution forecasting analysis through time series model are as follows:

[0091] Step A1, obtaining prediction data;

[0092] Step A2, establishing an ARIMAX model;

[0093] Step A3, using the maximum likelihood estimation (MLE) method to estimate the ARIMAX model parameters;

[0094] Step A4, verify the effect of the fitting model and check the goodness of fit of the model by residual analysis;

[0095] Step A5: Use the fitted model to predict the future power allocation plan, and use the maximum value of the prediction result as the highest point of power demand in the future time period.

[0096] Specifically, the prediction data includes temperature data, average vehicle speed data, flow rate of electric vehicles and power demand data corresponding to each time point; wherein, the temperature data, average vehicle speed data and flow rate of electric vehicles corresponding to each time point have been exemplified in step S3 and will not be described in detail here;

[0097] Power demand data refers to historical power demand data, whose data are used as the main variables of the time series;

[0098] Furthermore, the basic form of the ARIMAX model is:

[0099]

[0100] In the formula, y t is the power demand at the current time point, α is a constant term, is the i-th order autoregressive parameter, p is the order of the autoregressive term, θ j is the jth order moving average parameter, q is the order of the moving average term, ∈ t is a white noise term, representing random error, β k is an exogenous variable X t-k The coefficient of m is the lag order of the exogenous variable, X t-k is an exogenous variable lagged by k periods;

[0101] It should be noted that the exogenous variable part can integrate the impact of other relevant variables (such as temperature data, average vehicle speed data, and electric vehicle flow) on power demand;

[0102] It should be noted that in step A3, α, θ1, β1, and β2 are calculated by the maximum likelihood estimation (MLE) method. The specific steps are as follows:

[0103] Error term ∈ t Subordinate to the normal distribution N(0,σ 2 ), then the likelihood function is:

[0104]

[0105] Taking the logarithm of the likelihood function gives the log-likelihood function:

[0106]

[0107] By maximizing the log-likelihood function, we can obtain the parameter estimates α, θ1, β1, β2;

[0108] Dynamically adjust the charging pile power allocation strategy by predicting the maximum, minimum and average values ​​of the results;

[0109] This embodiment exemplifies as follows:

[0110] The maximum value of the predicted result Represents the highest point of power demand in the future time period. A peak allocation strategy is formulated to allocate power during the predicted peak power demand period (i.e. close to or equal to At the time point of the vehicle, increase the battery output power by 20% to ensure the smooth operation of the vehicle and avoid power shortage;

[0111] According to the lowest value of the predicted results or valley interval, formulate valley allocation strategy, in the valley period of power demand (i.e. close to or below At the same time, the output power of the battery is reduced by 15% to extend the battery life and efficiency;

[0112] According to the average of the predicted results Formulate a balance period allocation strategy to maintain the normal output of the battery during the period when the power demand is close to the average value, ensure the continuous and stable operation of the vehicle, and time period to maintain the normal output of the battery and ensure the continuous and stable operation of the vehicle.

[0113] The present invention Figure 2As shown, a smart charging pile staggered charging and smart charging pile system is disclosed, including: an identification and differentiation module, a fuzzy correction module, a power detection module and a modification and adjustment module, and the signal connection between each module is:

[0114] Identification and differentiation module: Identify the license plate color captured by the high-resolution camera installed at the entrance of the highway, use the HSV model to distinguish the color of the photo, and distinguish between electric vehicles and ordinary cars;

[0115] Blur correction module: obtain the current haze particle level and whether it is during sunrise and sunset to determine the current yellow light percentage, and determine the current photo exposure based on the V data in HSV. Combine the above data to determine the fuzzy range of the H value, use the white balance algorithm to obtain the color temperature deviation value, correct the H value within the fuzzy range, and record the current electric vehicle traffic volume;

[0116] Power detection module: obtains the temperature data of the built-in temperature sensor of the charging pile and the average speed data, and determines whether the power of the charging pile is reasonable in combination with the electric vehicle traffic flow;

[0117] Modification and adjustment module: Modify and adjust the unreasonable charging power of the charging pile using the time series model.

[0118] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0119] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0120] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0121] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0122] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0123] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for staggered charging of intelligent charging piles, characterized in that: The steps include: Step S1: Identify the license plate color captured by a high-resolution camera installed at the entrance of the highway, use the HSV model to distinguish the color of the photograph, and distinguish electric vehicles from ordinary cars; Step S2: Obtain the current haze particle level and whether it is during sunrise or sunset to determine the current yellow light percentage, and determine the current photo exposure based on the V data in HSV, and determine the fuzzy range of the H value based on the above data, use the white balance algorithm to obtain the color temperature deviation value, correct the H value within the fuzzy range, and record the current electric vehicle traffic volume; Step S3: Obtain temperature data of a built-in temperature sensor of the charging pile and average vehicle speed data and determine whether the power of the charging pile is reasonable in combination with the flow rate of electric vehicles; Step S4: modify and adjust the unreasonable charging power of the charging pile using the time series model.

2. The method for staggered charging of an intelligent charging pile according to claim 1, characterized in that: Identify the vehicle photos taken by the high-resolution camera installed at the entrance of the highway, use Canny edge detection to obtain the license plate area in the recognition image, and determine the location of the license plate by finding the rectangular area in the image. After the license plate position is recognized, the license plate area is cropped to obtain a clearer license plate image portion; The license plate RGB image is converted into the HSV color space. For each license plate area, its H value is calculated and compared with the threshold. The H threshold is set. When it is less than the threshold, the license plate is considered to be green and belongs to an electric car; when it is greater than the threshold, the license plate is considered to be blue and belongs to an ordinary car.

3. The method for staggered charging of an intelligent charging pile according to claim 2, characterized in that: Get the degree of haze particles and sunrise and sunset periods: Use the air quality API to obtain the real-time concentration of PM2.5 or PM10. The 30 minutes before and after sunrise is recorded as the sunrise period, and the 30 minutes before and after sunset is recorded as the sunset period; The formula for calculating the percentage of yellow light is: Yellow light percentage = Base Yellow Light × (1 + f PM2.5 ×PM2.5)×f Sunlight Period , where: Base Yellow Light: basic yellow light ratio. Under normal clear weather conditions, the yellow light component in sunlight is 50%, which is used as the benchmark; f PM2.5 : The influence coefficient of PM2.5 on yellow light is set to 0.005, that is, when the PM2.5 concentration increases by 1 μg / m 3 , the percentage of yellow light increases by 0.5%; PM2.5: the concentration of PM2.5, f Sunlight Period : Correction coefficient for sunrise and sunset periods, the values ​​are: 1.2: the current time is in the sunrise and sunset period (assuming 30 minutes before and after sunrise, 30 minutes before and after sunset), 1: the current time is not in the sunrise and sunset period; Get the pixel value of the V channel in the image, and normalize the pixel value of the V channel to a standard range by dividing each pixel value of the V channel by 255; The adjustment coefficient comprehensively considers the yellow light percentage and the normalized V value, and uses the following simple weighted average method: Adjustment coefficient = w1×Yellow Light Percentage+w2×Normalized V, where: w1 and w2 are weight coefficients, which control the influence of the yellow light percentage and the normalized V value on the final adjustment coefficient, w1+w2=1 (for example, w1 can be set to 0.3, w20.7); Yellow Light Percentage: the calculated yellow light percentage; Normalized V: the normalized V value; The basic fuzzy range is set to 80-100, and the adjustment is performed according to the adjustment coefficient. According to the adjustment coefficient k (the value range is from 0 to 1), the fuzzy range is adjusted. The fuzzy range = [80-αk, 100+αk], where: α is used to control the amplitude of the adjustment, indicating the influence of the coefficient k on the fuzzy range, which is set by technicians in this field according to actual conditions. k is the adjustment coefficient, and the value range is between 0 and 1. When k = 0, the fuzzy range is 80 to 100, that is, no adjustment. When k = 1, the fuzzy range is [80-α, 100+α], that is, maximum adjustment. White balance gain G r and G b It is calculated by comparing the brightness of the red and blue channels with the brightness of the green channel, and the formula is expressed as: Where: I r is the average brightness of the red channel, I g is the average brightness of the green channel, I b is the average brightness of the blue channel; Color temperature is usually expressed as a temperature in white light, in Kelvin. For most cameras or image processing systems, color temperature is related to gain, and the color temperature can be estimated from the gain value: Where C is a constant, with a value of 3000 Kelvin; The color temperature deviation value refers to the difference between the color temperature of the actual camera image and the ideal white point (e.g. 6500K neutral color temperature). The calculation formula of the deviation value is expressed as: ΔT = TT ideal , where: T is the estimated color temperature, is the ideal white point color temperature, set to 6500K; For the H value within the fuzzy interval, deviation adjustment is performed and a constant K is set. H To express the change in color temperature per unit deviation from the corresponding H value, the formula for correcting the H value is expressed as: H new =HK H ×ΔT, where: H new is the corrected hue value, H is the hue value of the original image, K H is a constant that indicates the influence of color temperature deviation on hue. ΔT is the deviation value of color temperature. After the H value in the fuzzy interval is adjusted, the H threshold is set. When it is less than the threshold, the license plate is considered to be green and belongs to an electric car; when it is greater than the threshold, the license plate is considered to be blue and belongs to an ordinary car, and the traffic flow of electric vehicles is recorded.

4. The method for staggered charging of an intelligent charging pile according to claim 3 is characterized in that ； Get the temperature data of the built-in temperature sensor of the charging pile and the average vehicle speed data; After receiving the temperature data, the average vehicle speed data, and the flow of electric vehicles, the temperature data, the average vehicle speed data, and the flow of electric vehicles are defined as input variables, and they are divided into different fuzzy sets respectively; Whether the charging power is reasonable is defined as the output variable and divided into fuzzy sets; Formulate fuzzy rules to describe the impact of temperature data, average vehicle speed data, and electric vehicle flow definition on whether the charging power is reasonable; Fuzzy reasoning is performed based on fuzzy rules to determine whether the charging power is reasonable.

5. The method for staggered charging of an intelligent charging pile according to claim 4, characterized in that: The unreasonable charging power scheme is analyzed through power allocation forecasting through time series model to determine the optimal adjustment of the initial power allocation scheme.

6. A method for staggered charging of intelligent charging piles according to claim 5, characterized in that: The time series model uses the ARIMAX model. The specific steps for power allocation forecasting and analysis using the time series model are as follows: Step A1, obtaining prediction data; Step A2, establishing an ARIMAX model; Step A3, using the maximum likelihood estimation (MLE) method to estimate the ARIMAX model parameters; Step A4, verify the effect of the fitting model and check the goodness of fit of the model by residual analysis; Step A5: Use the fitted model to predict the future power allocation plan, and use the maximum value of the prediction result as the highest point of power demand in the future time period.

7. A method for staggered charging of intelligent charging piles according to claim 6, characterized in that: The exogenous variables in the ARIMAX model include temperature data, average vehicle speed data, and electric vehicle traffic. The ARIMAX model formula is: In the formula, y t is the power demand at the current time point, α is a constant term, is the i-th order autoregressive parameter, p is the order of the autoregressive term, θ j is the jth order moving average parameter, q is the order of the moving average term, ∈ t is a white noise term, representing random error, β k is an exogenous variable X t-k The coefficient of m is the lag order of the exogenous variable, X t-k is an exogenous variable lagged by k periods.

8. The method for staggered charging of an intelligent charging pile according to claim 7, characterized in that: In step A3, α, θ1, β1, and β2 are calculated using the maximum likelihood estimation method.

9. A smart charging pile staggered charging and a smart charging pile system, used to implement the trust evaluation improvement method for regional health data according to any one of claims 1 to 8, characterized in that: include: Identification and differentiation module, fuzzy correction module, power detection module and modification and adjustment module: Identification and differentiation module: Identify the license plate color captured by the high-resolution camera installed at the entrance of the highway, use the HSV model to distinguish the color of the photo, and distinguish between electric vehicles and ordinary cars; Blur correction module: obtain the current haze particle level and whether it is during sunrise and sunset to determine the current yellow light percentage, and determine the current photo exposure based on the V data in HSV. Combine the above data to determine the fuzzy range of the H value, use the white balance algorithm to obtain the color temperature deviation value, correct the H value within the fuzzy range, and record the current electric vehicle traffic volume; Power detection module: obtains the temperature data of the built-in temperature sensor of the charging pile and the average speed data, and determines whether the power of the charging pile is reasonable in combination with the electric vehicle traffic flow; Modification and adjustment module: Modify and adjust the unreasonable charging power of the charging pile using the time series model.

Images