Energy management system for expressway service area

Abstract

An energy management system for an expressway service area comprises a power consumption management module which is used for acquiring the power consumption of each power consumption place in the service area and storing the power consumption of each power consumption place and the total power consumption of a server in different time periods to obtain historical power consumption data; the electricity consumption prediction module is used for acquiring electricity consumption influence factors of each electricity consumption place and predicting the electricity consumption of each electricity consumption place in the service area in each time period according to historical electricity consumption data and the current electricity consumption influence factors; the photovoltaic management module is used for acquiring the power generation efficiency of the photovoltaic module under the current natural environment factor, and predicting the current-day power generation amount of the photovoltaic module according to the power generation efficiency of the photovoltaic module; the electricity price acquisition module is used for acquiring the real-time electricity price of the current time period; and the mode setting module is used for determining an optimal power utilization strategy and setting the working mode of the photovoltaic module according to the real-time electricity price, the predicted power consumption of each power utilization place in each time period and the stored power in the energy storage equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption management, and particularly relates to an energy management system for highway service areas. Background Art

[0002] In recent years, with the rapid growth of traffic volume and the number of motor vehicles, the number of service areas relying on highway construction has been gradually increasing, becoming an important place for people to replenish, rest and consume during their journeys. Highway service areas usually include various electricity-consuming places such as restaurants, restrooms, shopping areas, gas stations, charging stations, etc., and significant energy consumption is generated along with a large number of people. Among the current places in service areas, the usage requirements of equipment such as air conditioners, kitchens, and charging piles are high, making service areas high-energy-consuming operating places and also bringing high electricity bills.

[0003] Currently, some highway service areas attempt to carry out energy-saving renovations through photovoltaic ceiling lamp facilities, converting solar energy into electrical energy for utilization. However, the existing photovoltaic systems have not achieved intelligent control at present. Due to the influence of weather and environment on photovoltaic power generation, the power generation of photovoltaic power generation often cannot meet the electricity demand of all loads in the service area. The current common practice is only to use photovoltaic power generation for building lighting and charging pile power supply. Although this can reduce a part of the electricity cost consumption, it is only on the original basis of electricity consumption, replacing the power supply of some electrical facilities with photovoltaic power supply. However, the change in electricity price is not considered, and there may be a situation where the photovoltaic power supply is insufficient when the electricity price is high, and the electricity price is low when the photovoltaic power supply is sufficient. Summary of the Invention

[0004] The technical problem solved by the present invention is to provide an energy management system for highway service areas, which can automatically select the working mode of photovoltaic modules according to the electricity consumption situation in the place, and reduce the electricity cost.

[0005] The basic solution provided by the present invention: An energy management system for highway service areas includes a server, and the server includes an electricity consumption management module, an electricity consumption prediction module, a photovoltaic management module, an electricity price acquisition module, and a mode setting module;

[0006] The electricity consumption management module is used to obtain the electricity consumption of each electricity-consuming place in the service area, and store the electricity consumption of each electricity-consuming place and the total electricity consumption of the server in different time periods to obtain historical electricity consumption data;

[0007] The electricity consumption prediction module is used to obtain the electricity consumption influencing factors of each electricity-consuming place, and is used to predict the electricity consumption of each electricity-consuming place in the service area in each time period according to the historical electricity consumption data and the current electricity consumption influencing factors.

[0008] The photovoltaic management module is used to obtain the power generation efficiency of the photovoltaic module under the current natural environmental factors, predict the daily power generation of the photovoltaic module according to the power generation efficiency of the photovoltaic module. The working modes of the photovoltaic module include a first working mode and a second working mode. In the first working mode, the photovoltaic module directly supplies power to the electricity consumption site. In the second working mode, the photovoltaic module charges the energy storage device and updates the stored power of the energy storage device in real time.

[0009] The electricity price acquisition module is used to obtain the real-time electricity price of the current period.

[0010] The mode setting module is used to determine the optimal power consumption strategy according to the real-time electricity price, the predicted power consumption of each electricity consumption site in each period, and the stored power in the energy storage device, and set the working mode of the photovoltaic module.

[0011] The principle and advantages of the present invention are as follows: In the service area, power supply is carried out through two methods of municipal power supply and photovoltaic power supply. The power consumption of each power supply site in the service area is collected, and the power consumption of each power consumption site is stored by period to obtain historical power consumption data. During daily use, by obtaining the power consumption influencing factors of each power consumption site, and according to the power consumption influencing factors and historical power consumption data, the power consumption of each power consumption site in each period is predicted. At the same time, the power generation efficiency of the photovoltaic module is obtained, the daily power generation is predicted according to the power generation efficiency, and according to the predicted power consumption and the daily power generation of the photovoltaic module, the working mode of the photovoltaic module in each period is determined according to the prediction result and the real-time electricity price. Among them, the first working mode is that the photovoltaic module directly supplies power to the electricity consumption site, and the second working mode is that the photovoltaic module charges the energy storage device.

[0012] Compared with the prior art, multiple factors are considered in this solution, and according to the current actual situation, it is selected whether the photovoltaic directly supplies power to the electricity consumption site or performs energy storage. In this way, when the real-time electricity price is low and the power consumption demand is small, energy storage is preferred. When the real-time electricity price is high and the power consumption demand is large, photovoltaic and energy storage power supply are preferred. Thereby reducing the electricity cost and at the same time reducing the consumption of municipal electric energy.

[0013] Further, it is characterized in that the power consumption management module includes a power consumption classification module, a rigid load analysis module, and an elastic load analysis module;

[0014] The power consumption classification module is used to obtain that each power consumption site is divided into a rigid load and an elastic load according to its nature;

[0015] The rigid load analysis module is used to determine the conventional power consumption E1 of each rigid load power consumption site in each period according to the empirical analysis of its historical power consumption data;

[0016] An elastic load analysis module is used to obtain the electricity consumption influencing factors of the electricity consumption sites of elastic loads. The electricity consumption influencing factors include traffic flow, temperature, and time period. An LSTM neural network prediction model is established, and the electricity consumption influencing factors are used as model inputs. The electricity consumption E2 of elastic loads in each time period is predicted through the LSTM neural network prediction model:

[0017] The electricity consumption prediction module obtains the total electricity consumption E in each time period according to the electricity consumption of the electricity consumption sites of rigid loads and the electricity consumption of elastic electricity consumption sites in each time period t = E1 + E2;

[0018] When the photovoltaic module is in the first working mode, it preferentially supplies power to the electricity consumption sites of elastic loads.

[0019] The electricity consumption sites are divided into rigid load electricity consumption and elastic load electricity consumption. Rigid loads are the electricity consumption that will inevitably occur in the corresponding time periods. At night, lighting electricity consumption is rigid load electricity consumption. The electricity consumption generated by these electricity consumption sites in each time period every day will not change greatly with other factors.

[0020] Elastic electricity consumption is affected by external factors. For example, when the traffic flow is large, the consumption of charging piles will increase. When the temperature is high, the electricity consumption of air conditioners will increase. During peak hours, the electricity consumption of restaurants and bathrooms will also increase. The electricity consumption nature of the electricity consumption sites is divided into rigid electricity consumption and elastic electricity consumption. According to historical experience analysis, the conventional electricity consumption E1 of rigid loads in each time period can be obtained. Through the LSTM neural network model, the influencing factors of elastic electricity consumption sites are used as model inputs for training, and through the LSTM neural network model, the electricity consumption E2 of elastic electricity consumption sites is predicted.

[0021] Furthermore, the mode setting module includes a power generation prediction module, a first module control module, and a second mode control module;

[0022] The power generation prediction module is used to obtain weather forecast data. The weather forecast data includes the sunlight, temperature, and cloud cover in the future time periods of the current day, and predicts the power generation in the future time periods of the current day through a TCN temporal convolutional network;

[0023] The first mode control module is used to control the photovoltaic module to work in the first working mode to supply power to the electricity consumption sites of elastic loads and control the energy storage device to supply power to the electricity consumption sites of elastic loads when the current electricity price is greater than the preset electricity price threshold and the electricity consumption demand of elastic loads is greater than the instantaneous power generation of the photovoltaic;

[0024] When the current electricity price is greater than the preset electricity price threshold and the electricity consumption demand of elastic loads is less than the instantaneous power generation of the photovoltaic, then control the photovoltaic module to work in the first working mode and supply power to the electricity consumption sites of elastic loads and some of the electricity consumption sites of rigid loads at the same time;

[0025] A second mode control module, configured to control the photovoltaic module to operate in a second operating mode when the current electricity price is less than a preset threshold.

[0026] When the electricity price is high, priority is given to supplying power to the electricity consumption sites of flexible loads through the photovoltaic module. Since the electricity consumption of flexible loads changes at any time, when the electricity consumption demand of flexible loads is large, power supply is carried out simultaneously through photovoltaic power supply and energy storage power supply. If the energy storage is insufficient, municipal power supply is used. If the current electricity price is low, the photovoltaic module supplies power to the energy storage device.

[0027] Further, the server further includes a vehicle information acquisition module and a vehicle acquisition device;

[0028] The vehicle acquisition device is provided at the entrance of the highway and the service area, and is configured to acquire and record vehicle information and feedback to the server whether the vehicle enters the service area;

[0029] The vehicle information acquisition module is configured to record the driving data of each vehicle according to whether each vehicle uploaded by the vehicle acquisition device enters the service area. The driving data is the number of times x that the vehicle passes by but does not enter the service area. If the vehicle enters the toll station, the number of times x is cleared;

[0030] The flexible load analysis module is configured to predict the number of vehicles entering the server in the next time period according to the driving data of the vehicles between two adjacent service areas, and predict the electricity consumption of the flexible load in the time period according to the predicted number of vehicles.

[0031] At the node at the entrance of the highway and the service area, a vehicle acquisition device such as a camera, ETC, etc. is installed to detect whether the vehicle enters the service area. The acquired vehicle information is uploaded to the server, and the server records the number of times x that each vehicle passes by but does not enter the service area according to whether the vehicle enters each service area. Generally speaking, after a long time of driving, the driver will enter the service area to rest and is not counted. Therefore, the greater the number of times x that the vehicle passes by but does not enter the service area, the greater the possibility that the vehicle will enter the service area. According to the driving data of the vehicles between two adjacent service areas, the number of vehicles entering the server in the next time period is predicted, so as to provide data support for the electricity consumption prediction of the flexible load in the time period.

[0032] Further, the flexible load analysis module includes a vehicle prediction module and a model prediction module;

[0033] The vehicle prediction module is configured to predict the number of vehicles N that will enter the next toll station according to the number of vehicles M between two adjacent servers and their driving data:

[0034]

[0035] x i Let \(x\) be the number of times vehicle \(i\) enters the previous server per unit, and \(\beta\) be the basic entry rate, which is obtained by fitting historical data, where \(0 \lt \beta \lt 1\).

[0036] A model prediction module, according to the predicted number of vehicles \(N\) to enter the next toll station, temperature, and time period, predicts the power consumption \(E_2\) of the flexible load in the next time period through the LSTM model:

[0037] \(E_2 = LSTM(N, T, H)\)

[0038] where \(LSTM\) represents a pre-trained LSTM model, \(T\) represents the current temperature data, and \(H\) represents the current time period characteristics.

[0039] The probability of each vehicle entering the service area increases with the number of times \(x\) of not entering i and represents the probability of the current vehicle entering the service area after continuously not entering the service area \(x\) times. \(\beta\) is obtained by fitting historical data. For example, if \(\beta = 0.3\), when the vehicle has not entered once, the entry probability is \(0.3\). If it has not entered for the second time, it is increased to \(1-(1 - 0.7)\) 2 \(= 0.51\), and so on.

[0040] Suppose there are 100 vehicles between two adjacent service areas and \(\beta = 0.25\). The distribution of \(x\) for each vehicle i is as follows:

[0041] For 50 vehicles, \(x\) i \(= 1\), and the contribution probability is: \(1-(1 - 0.75)\) 1 \(= 0.25\).

[0042] For 30 vehicles, \(x\) i \(= 2\), and the contribution probability is: \(1-(1 - 0.75)\) 2 \(= 0.4375\).

[0043] For 20 vehicles, \(x\) i \(= 3\), and the contribution probability is: \(1-(1 - 0.75)\) 3 \(= 0.578\).

[0044] \(N = 50×0.25 + 30×0.4375 + 20×0.578 \approx 37\) vehicles.

[0045] Thus, it is predicted that the number of vehicles to enter the next service area is 37, providing data for the power consumption prediction of the flexible load. Brief Description of the Drawings

[0046] Figure 1 It is a schematic diagram of an embodiment of an energy management system for highway service areas according to the present invention. Detailed Implementation Modes

[0047] The following is a further detailed description through specific implementation modes:

[0048] An energy management system for highway service areas includes a server, and the server includes an electricity consumption management module, an electricity consumption prediction module, a photovoltaic management module, an electricity price acquisition module, and a mode setting module;

[0049] The electricity consumption management module is used to obtain the electricity consumption of each electricity-consuming place in the service area, and store the electricity consumption of each electricity-consuming place and the total electricity consumption of the server by time period to obtain historical electricity consumption data;

[0050] The electricity consumption prediction module is used to obtain the electricity consumption influencing factors of each electricity-consuming place, and is used to predict the electricity consumption of each electricity-consuming place in the service area at each time period according to the historical electricity consumption data and the current electricity consumption influencing factors;

[0051] The photovoltaic management module is used to obtain the power generation efficiency of the photovoltaic modules under the current natural environmental factors, predict the daily power generation of the photovoltaic modules according to the power generation efficiency of the photovoltaic modules. The working modes of the photovoltaic modules include a first working mode and a second working mode. The first working mode is that the photovoltaic modules directly supply power to the electricity-consuming places, and the second working module is that the photovoltaic modules charge the energy storage device, and the stored electricity of the energy storage device is updated in real time;

[0052] The electricity price acquisition module is used to obtain the real-time electricity price at the current time period;

[0053] The mode setting module is used to determine the optimal electricity consumption strategy according to the real-time electricity price, the predicted electricity consumption of each electricity-consuming place at each time period, and the stored electricity in the energy storage device, and set the working mode of the photovoltaic modules.

[0054] It is characterized in that the electricity consumption management module includes an electricity consumption grading module, a rigid load analysis module, and an elastic load analysis module;

[0055] The electricity consumption grading module is used to obtain that each electricity-consuming place is divided into rigid loads and elastic loads according to its nature;

[0056] The rigid load analysis module is used for the electricity-consuming places with rigid loads, and determines the conventional electricity consumption E1 of each electricity-consuming place with rigid loads at each time period according to the empirical analysis of its historical electricity consumption data;

[0057] The elastic load analysis module is used to obtain the electricity consumption influencing factors of the electricity-consuming places with elastic loads. The electricity consumption influencing factors include traffic flow, temperature, and time period, establish an LSTM neural network prediction model, use the electricity consumption influencing factors as model inputs, and predict the electricity consumption E2 of the elastic loads at each time period through the LSTM neural network prediction model;

[0058] The electricity consumption prediction module obtains the total electricity consumption E for each period based on the electricity consumption of the rigid load's electricity consumption location and the elastic electricity consumption location at each period. t = E1 + E2;

[0059] When the photovoltaic module is in the first working mode, it preferentially supplies power to the electricity consumption locations of the elastic load.

[0060] The electricity consumption locations are divided into rigid load electricity consumption and elastic load electricity consumption. Rigid load is the electricity consumption that will inevitably occur during the corresponding period. At night, lighting electricity consumption is rigid load electricity consumption. The electricity consumption generated by these electricity consumption locations at each period every day will not change greatly due to other factors.

[0061] Elastic electricity consumption is affected by external factors. For example, when the traffic flow is large, the consumption of charging piles will increase. When the temperature is high, the electricity consumption of air conditioners will increase. During peak hours, the electricity consumption of restaurants and restrooms will also increase. The electricity consumption nature of the electricity consumption locations is divided into rigid electricity consumption and elastic electricity consumption. According to historical experience analysis, the conventional electricity consumption E1 of the rigid load at each period can be obtained. Through the LSTM neural network model, the influencing factors of the elastic electricity consumption location are used as the model input for training, and through the LSTM neural network model, the electricity consumption E2 of the elastic electricity consumption location is predicted.

[0062] The mode setting module includes a power generation prediction module, a first module control module, and a second mode control module;

[0063] The power generation prediction module is used to obtain weather forecast data, and the weather forecast data includes the light, temperature, and cloud amount in the future periods of the current day, and predicts the power generation in the future periods of the current day through the TCN temporal convolutional network;

[0064] The first mode control module is used to control the photovoltaic module to work in the first working mode to supply power to the electricity consumption locations of the elastic load and control the energy storage device to supply power to the electricity consumption locations of the elastic load when the current electricity price is greater than the preset electricity price threshold and the electricity consumption demand of the elastic load is greater than the instantaneous power generation of the photovoltaic;

[0065] When the current electricity price is greater than the preset electricity price threshold and the electricity consumption demand of the elastic load is less than the instantaneous power generation of the photovoltaic, then control the photovoltaic module to work in the first working mode and supply power to the electricity consumption locations of the elastic load and part of the electricity consumption locations of the rigid load at the same time;

[0066] The second mode control module is used to control the photovoltaic module to work in the second working mode when the current electricity price is less than the preset threshold.

[0067] When the electricity price is high, the photovoltaic modules are preferentially used to supply power to the electricity consumption places of flexible loads. Since the electricity consumption of flexible loads changes at any time, when the electricity demand of flexible loads is large, power is supplied simultaneously through photovoltaic power supply and energy storage power supply. If the energy storage is insufficient, municipal power supply is used. If the current electricity price is low, the photovoltaic modules supply power to the energy storage device.

[0068] The server further includes a vehicle information acquisition module and a vehicle acquisition device.

[0069] The vehicle acquisition device is installed at the entrance of the highway and the service area, and is used to collect and record vehicle information and feedback to the server whether the vehicle enters the service area.

[0070] The vehicle information acquisition module is used to record the driving data of each vehicle according to whether each vehicle enters the service area uploaded by the vehicle acquisition device. The driving data is the number of times x that the vehicle passes by but does not enter the service area. If the vehicle enters the toll station, the number of times x is cleared.

[0071] The flexible load analysis module is used to predict the number of vehicles entering the server in the next time period according to the driving data of the vehicles between two adjacent service areas, and predict the electricity consumption of the flexible load in the time period according to the predicted number of vehicles.

[0072] At the node at the entrance of the highway and the service area, a vehicle acquisition device such as a camera or ETC is installed to detect whether the vehicle enters the service area. The collected vehicle information is uploaded to the server, and the server records the number of times x that each vehicle passes by but does not enter the service area according to whether the vehicle enters each service area. Generally speaking, after a long time of driving, the driver will enter the service area to rest and does not count. Therefore, the greater the number of times x that the vehicle passes by but does not enter the service area, the greater the possibility that the vehicle will enter the service area. According to the driving data of the vehicles between two adjacent service areas, the number of vehicles entering the server in the next time period is predicted, so as to provide data support for the electricity consumption prediction of the flexible load in the time period.

[0073] The flexible load analysis module includes a vehicle prediction module and a model prediction module.

[0074] The vehicle prediction module is used to predict the number of vehicles N that will enter the next toll station according to the number of vehicles M between two adjacent servers and their driving data:

[0075]

[0076] x i is the number of times that vehicle i passes through and enters the previous server, and β is the basic entry rate, which is obtained by fitting historical data, and 0 < β < 1;

[0077] The model prediction module predicts the power consumption E2 of the flexible load in the next time period through the LSTM model according to the predicted number of vehicles N, temperature, and time period to enter the next toll station:

[0078] E2 = LSTM(N, T, H)

[0079] Where LSTM represents the pre-trained LSTM model, T represents the current temperature data, and H represents the current time period characteristics.

[0080] The probability of each vehicle entering the service area increases with the number of times x of not entering i Incrementally, It represents the probability of the vehicle entering the service area currently after not entering the service area continuously for x times. β is obtained by fitting historical data. For example, β = 0.3. When the vehicle fails to enter once, the probability of entering is 0.3. If it still fails to enter the second time, it is increased to 1 - (1 - 0.7) 2 = 0.51, and so on.

[0081] Suppose there are 100 vehicles between two adjacent service areas, β = 0.25, and the x of each vehicle i Distribution is:

[0082] For 50 vehicles, x i = 1, and the contribution probability is: 1 - (1 - 0.75) 1 = 0.25.

[0083] For 30 vehicles, x i = 2, and the contribution probability is: 1 - (1 - 0.75) 2 = 0.4375.

[0084] For 20 vehicles, x i = 3, and the contribution probability is: 1 - (1 - 0.75) 3 = 0.578.

[0085] N = 50×0.25 + 30×0.4375 + 20×0.578 ≈ 37 vehicles.

[0086] Based on this, it is predicted that the number of vehicles to enter the next service area is 37, providing data for the power consumption prediction of the flexible load.

[0087] In this solution, power supply in the service area is carried out through two methods: municipal power supply and photovoltaic power supply. The electricity consumption of each power supply location in the service area is collected, and the electricity consumption of each power consumption location is stored by time period to obtain historical electricity consumption data. During daily use, by obtaining the electricity consumption influencing factors of each power consumption location, and based on the electricity consumption influencing factors and historical electricity consumption data, the electricity consumption of each power consumption location in each time period is predicted. At the same time, the power generation efficiency of the photovoltaic modules is obtained, the daily power generation is predicted according to the power generation efficiency, and according to the predicted electricity consumption and the daily power generation of the photovoltaic modules, the working mode of the photovoltaic modules in each time period is determined according to the prediction result and the real-time electricity price. Among them, the first working mode is that the photovoltaic modules directly supply power to the power consumption location, and the second working mode is that the photovoltaic modules charge the energy storage device.

[0088] Compared with the prior art, this solution takes into account various factors and selects whether the photovoltaic power is directly supplied to the power consumption location or stored according to the current actual situation. In this way, when the real-time electricity price is low and the electricity demand is small, energy storage is preferred; when the real-time electricity price is high and the electricity demand is large, photovoltaic power and energy storage power supply are preferred. Thereby reducing the electricity cost and at the same time reducing the consumption of municipal electric energy.

[0089] The above are only embodiments of the present invention. Common knowledge such as specific structures and characteristics known in the solution is not described in detail here. Those of ordinary skill in the art know all the common general technical knowledge in the technical field to which the invention belongs before the application date or the priority date, can know all the existing technologies in this field, and have the ability to apply the conventional experimental means before this date. Those of ordinary skill in the art can, under the inspiration given in this application, combine their own abilities to improve and implement this solution. Some typical well-known structures or well-known methods should not become an obstacle for those of ordinary skill in the art to implement this application. It should be noted that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the implementation effect of the present invention and the practicality of the patent. The protection scope required by this application should be based on the content of its claims, and the specific implementation manners described in the specification can be used to interpret the content of the claims.

Claims

1. An energy management system for highway service areas, characterized in that: It includes a server, and the server includes a power consumption management module, a power consumption prediction module, a photovoltaic management module, a power price acquisition module, and a mode setting module; The power consumption management module is used to obtain the power consumption of each power consumption site in the service area, and store the power consumption of each power consumption site and the total power consumption of the server by time period to obtain historical power consumption data; The power consumption prediction module is used to obtain the power consumption influencing factors of each power consumption site, and is used to predict the power consumption of each power consumption site in the service area at each time period according to the historical power consumption data and the current power consumption influencing factors; The photovoltaic management module is used to obtain the power generation efficiency of the photovoltaic modules under the current natural environmental factors, predict the daily power generation of the photovoltaic modules according to the power generation efficiency of the photovoltaic modules. The working modes of the photovoltaic modules include a first working mode and a second working mode. The first working mode is that the photovoltaic modules directly supply power to the power consumption sites, and the second working module is that the photovoltaic modules charge the energy storage device, and the stored power of the energy storage device is updated in real time; The power price acquisition module is used to obtain the real-time power price at the current time period; The mode setting module is used to determine the optimal power consumption strategy according to the real-time power price, the predicted power consumption of each power consumption site at each time period, and the stored power in the energy storage device, and set the working mode of the photovoltaic modules.

2. The energy management system for highway service areas according to claim 1, characterized in that: The power consumption management module includes a power consumption classification module, a rigid load analysis module, and an elastic load analysis module; The power consumption classification module is used to obtain that each power consumption site is divided into rigid loads and elastic loads according to its nature; The rigid load analysis module is used to determine the conventional power consumption E1 of each rigid load power consumption site at each time period according to the empirical analysis of its historical power consumption data for the power consumption sites with rigid loads; The elastic load analysis module is used to obtain the power consumption influencing factors of the power consumption sites with elastic loads. The power consumption influencing factors include traffic flow, temperature, and time period. An LSTM neural network prediction model is established, and the power consumption influencing factors are used as model inputs, and the power consumption E2 of the elastic loads at each time period is predicted through the LSTM neural network prediction model: The electricity consumption prediction module obtains the total electricity consumption E for each period based on the electricity consumption of the rigid load in the electricity consumption site and the electricity consumption of each period in the flexible electricity consumption site. t = E1 + E2; When the photovoltaic modules are in the first working mode, they preferentially supply power to the power consumption sites with elastic loads.

3. The energy management system for highway service areas according to claim 2, wherein: The mode setting module includes a power generation prediction module, a first module control module, and a second mode control module; The power generation prediction module is used to obtain weather forecast data. The weather forecast data includes the illumination, temperature, and cloud amount in the future time periods of the current day, and predicts the power generation in the future time periods of the current day through a TCN temporal convolutional network; The first mode control module is used to control the photovoltaic modules to work in the first working mode to supply power to the power consumption sites with elastic loads, and at the same time control the energy storage device to supply power to the power consumption sites with elastic loads when the current power price is greater than the preset power price threshold and the power consumption demand of the elastic loads is greater than the instantaneous power generation of the photovoltaic; When the current power price is greater than the preset power price threshold and the power consumption demand of the elastic loads is less than the instantaneous power generation of the photovoltaic, then control the photovoltaic modules to work in the first working mode, and at the same time supply power to the power consumption sites with elastic loads and some power consumption sites with rigid loads; The second mode control module is used to control the photovoltaic module to work in the second working mode when the current electricity price is less than the preset threshold.

4. The energy management system for highway service areas according to claim 3, characterized in that: The server further includes a vehicle information acquisition module and a vehicle acquisition device; The vehicle acquisition device is provided at the entrance of the highway and the service area, and is used to collect and record vehicle information and feedback to the server whether the vehicle enters the service area; The vehicle information acquisition module is used to record the driving data of each vehicle according to whether each vehicle uploaded by the vehicle acquisition device enters the service area. The driving data is the number of times x that the vehicle passes by but does not enter the service area. If the vehicle enters the toll station, the number of times x is cleared; The elastic load analysis module is used to predict the number of vehicles entering the server in the next time period according to the driving data of the vehicles between two adjacent service areas, and predict the electricity consumption of the elastic load in the next time period according to the predicted number of vehicles.

5. The energy management system for highway service areas according to claim 4, characterized in that: The elastic load analysis module includes a vehicle prediction module and a model prediction module; The vehicle prediction module is used to predict the number of vehicles N that will enter the next toll station according to the number of vehicles M between two adjacent servers and their driving data; x i where \(x_{i}\) is the number of times vehicle \(i\) enters the previous server per unit, and \(\beta\) is the basic entry rate, which is obtained by fitting historical data, where \(0 \lt \beta \lt 1\); The model prediction module predicts the electricity consumption E2 of the elastic load in the next time period through the LSTM model according to the predicted number of vehicles N that will enter the next toll station, the temperature, and the time period: E2 = LSTM(N, T, H) Where LSTM represents the pre-trained LSTM model, T represents the current temperature data, and H represents the current time period feature.

Images