Semi-empirical hybrid high-speed service area consumption prediction method and related device

Abstract

The invention provides a semi-empirical hybrid high-speed service area consumption prediction method and a related device, and relates to the technical field of energy management. The method based on traffic data analysis is used for predicting energy consumption and water consumption of the expressway service area. In combination with vehicle flow data, time information and specific vehicle type statistics, energy and water resource consumption of a service area under different time and different conditions is accurately predicted through a series of calculation models.

Description

Technical Field

[0001] The present application relates to the field of energy management technology, and in particular to a semi-empirical hybrid high-speed service area consumption prediction method and related devices. Background Art

[0002] Highway service areas are important nodes for energy and water consumption, and their energy consumption prediction is crucial for optimal resource allocation. The existing technology has the following defects: Historical data analysis method: It relies on static historical data and cannot adapt to changes in dynamic factors such as traffic flow and holidays; Simple linear model: predicts energy consumption only by the total volume of traffic, ignoring the impact of vehicle type, time period, and tidal effect of the opposite service area; Real-time monitoring system: lacks prediction function and is difficult to support early regulation.

[0003] Therefore, there is an urgent need for an energy consumption prediction method that integrates multi-source data, dynamically models, and can be embedded and deployed. Summary of the invention

[0004] The core of the present invention is to provide a semi-empirical hybrid highway service area consumption prediction method and related devices, which integrates real-time traffic data, time parameters and historical data of the opposite service area to construct a dynamic prediction model to solve the problems of poor adaptability and low accuracy in the existing technology.

[0005] In the first aspect, the semi-empirical hybrid highway service area consumption prediction method provided by the present application adopts the following technical solution: A semi-empirical hybrid high-speed service area consumption prediction method, comprising: S1. Obtain vehicle flow data within a preset section of the target service area, and divide the data collection interval according to the preset section length through the highway toll station and monitoring system; S2. Obtain time data, the time data includes the current hour , day of the week 、Whether it is a holiday , whether it is a long holiday , where long holidays are defined as consecutive holidays ≥ 5 days; S3. Call the historical energy consumption data of the opposite service area from the database and align the current forecast period by timestamp; S4. Calculate the measured energy consumption based on the vehicle flow data; S5. Calculate the time impact on energy consumption based on time data; S6. Calculate the energy consumption of the opposite side based on the historical energy consumption data of the opposite service area; S7. Accumulate the measured energy consumption, time-affected energy consumption and opposite-side-affected energy consumption to obtain a predicted total energy consumption value.

[0006] Optionally, in step S1, the division of the preset road sections adopts a dynamic adjustment strategy to automatically merge or split road sections according to the real-time traffic flow density to optimize data collection accuracy.

[0007] Optionally, in step S4, the measured energy consumption is calculated based on the vehicle flow data. , the calculation formula is: ; in, 、 、 、 The product of the probability of a passenger car, RV, bus and truck consuming energy in the next hour in this service area and the energy consumed. The vehicle flow data includes the number of passenger cars , Number of RVs , Number of buses , Number of trucks And the corresponding number of electric vehicles 、 、 、 ， 、 、 、 The energy consumption coefficient of the electric vehicle is dynamically calibrated by the charging pile utilization rate and the battery replacement frequency. 、 、 、 Dynamic updates via: Real-time collection of charging pile power data and battery replacement times; The energy consumption coefficient of the electric vehicle per unit stay time is fitted by combining the vehicle battery capacity and charging efficiency.

[0008] Optionally, in step S5, the time-related energy consumption is calculated based on the time data, including the number of hours affecting the energy consumption. , Week of the week affects energy consumption , Holidays affect energy consumption Long holidays affect energy consumption : ; ; ; ; in, Indicates the number of hours, Indicates the specific day of the week. , , Through historical energy consumption data fitting optimization, when the number of holidays is ≥ 5, The energy consumption changes caused by the number of commuters on Monday and Friday, The increase in energy consumption is caused by the increase in passenger traffic on weekends. Indicates whether the recorded data is from a holiday, with 0 indicating a non-holiday and 1 indicating a holiday. Indicates whether the recorded data is from a long holiday. 0 indicates a non-long holiday and 1 indicates a long holiday. =1 and prioritize calculation ; Holiday parameters and The value of is optimized in the following ways: Extract holiday energy consumption data from the past five years and classify and count them by holiday length; The least squares method was used to fit the linear and nonlinear effects of different holiday lengths on energy consumption.

[0009] Optionally, in step S6, the energy consumption of the opposite side is calculated based on the historical energy consumption data of the opposite service area. , the formula is: ; ; in, is the sigmoid function, is the fitted weight matrix, is the fitted bias matrix, is the impact rate of dynamic adjustment, is the historical data of the opposite service area. is the predicted energy consumption of the local service area, which is updated in real time based on the vehicle return probability; Dynamically adjust impact rate When , weather data is introduced as an additional input parameter, including: Get real-time rainfall, temperature and visibility data through the meteorological interface; According to the severity of the weather, the return probability is adjusted. The weight distribution of .

[0010] Optionally, the steps of step S7 include: Accumulate the measured energy consumption, time-affected energy consumption and opposite-side-affected energy consumption to obtain the total energy consumption forecast value; Calculations are performed in real time through embedded systems or programmable logic controllers, and interactive flow charts are generated to show the contribution ratio of each energy consumption component and the predicted confidence interval; Among them, interactive flowcharts enhance visualization in the following ways: Display the real-time distribution of vehicle density on each road section in the form of a heat map; The superimposed time axis sliding window supports users to conduct comparative analysis between historical prediction results and measured data.

[0011] Optionally, the method further includes a water consumption prediction module: The total energy consumption forecast value E is associated with the historical water consumption data to build an energy consumption-water consumption mapping model; The real-time water consumption prediction value W is output based on the mapping model, and the water pumps and water storage equipment in the service area are controlled through PLC linkage.

[0012] In a second aspect, the present application provides a semi-empirical hybrid high-speed service area consumption prediction device, which executes the method described above, including: The data processing module is used to obtain the vehicle flow data within the preset road section of the target service area, and divide the data collection interval according to the preset road section length through the highway toll station and monitoring system; A time extraction module is used to obtain time data, which includes the current hour. , day of the week 、Whether it is a holiday , whether it is a long holiday , where long holidays are defined as consecutive holidays ≥ 5 days; A data calling module is used to call the historical energy consumption data of the opposite service area from the database and align the current prediction period by timestamp; An energy consumption calculation module, used for calculating the measured energy consumption according to the vehicle flow data; A time calculation module, used to calculate the time-influenced energy consumption based on time data; A model building module is used to calculate the opposite side impact energy consumption based on the historical energy consumption data of the opposite side service area; The output module is used to accumulate the measured energy consumption, the time-affected energy consumption and the opposite-side-affected energy consumption to obtain the total energy consumption prediction value.

[0013] In a third aspect, the present application provides a computer device, comprising: a memory and a processor, wherein the processor executes the method described above when running computer instructions stored in the memory.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, comprising instructions, which, when executed on a computer, enable the computer to execute the method described above.

[0015] In summary, the present application includes the following beneficial technical effects: This application uses a method based on traffic data analysis to predict the energy and water consumption of highway service areas. It combines vehicle flow data, time information and specific vehicle type statistics, and uses a series of calculation models to accurately predict the energy and water consumption of service areas at different times and under different conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present application.

[0017] Figure 2 It is a flow chart of the first embodiment of the semi-empirical hybrid highway service area consumption prediction method of the present application.

[0018] Figure 3 It is a structural block diagram of the first embodiment of the semi-empirical hybrid high-speed service area consumption prediction device of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below through the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0020] Reference Figure 1 , Figure 1 A schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present application.

[0021] like Figure 1As shown, the computer device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0022] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the computer device, and may include more or less components than shown in the figure, or combine some components, or arrange the components differently.

[0023] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a semi-empirical hybrid high-speed service area consumption prediction program.

[0024] exist Figure 1 In the computer device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the present application can be set in the computer device, and the computer device calls the semi-empirical hybrid high-speed service area consumption prediction program stored in the memory 1005 through the processor 1001, and executes the semi-empirical hybrid high-speed service area consumption prediction method provided in the embodiment of the present application.

[0025] The present application embodiment provides a semi-empirical hybrid high-speed service area consumption prediction method, referring to Figure 2 , Figure 2 This is a flow chart of the first embodiment of the semi-empirical hybrid highway service area consumption prediction method of the present application.

[0026] In this embodiment, the semi-empirical hybrid high-speed service area consumption prediction method includes the following steps: Step S1. Obtain vehicle flow data within a preset road section of a target service area, and divide the data collection interval according to the preset road section length through a highway toll station and a monitoring system.

[0027] Obtain vehicle flow data within a preset road section of the target service area, the vehicle flow data includes the number of passenger cars ( ), Number of RVs ( ), the number of buses ( ), Number of trucks ( ) and the corresponding number of electric vehicles 、 、 、 ; Through highway toll stations and monitoring systems, the data collection intervals are divided according to the preset section lengths. The length of each section is 10-50 kilometers, and the total length is divided into 2-10 sections.

[0028] It should be noted that in step S1, the division of the preset road sections adopts a dynamic adjustment strategy, and the road sections are automatically merged or split according to the real-time traffic flow density to optimize the data collection accuracy.

[0029] It is understood that the subsequent parameters and glossaries in this implementation include: Energy consumption power (E): refers to the total amount of energy consumed by the service area per unit time, usually measured in kilowatt-hours (kWh).

[0030] Water consumption (W): refers to the total amount of water resources consumed in the service area per unit time, usually measured in cubic meters (m³).

[0031] Passenger flow (P): The total number of passengers visiting the service area per unit time, usually measured in (person-times).

[0032] Vehicle flow data: refers to data on the number and type of vehicles passing through collected from highway toll booths and cameras along the way.

[0033] (Hour): The hour of the day, usually counted from 0 to 23.

[0034] (day of week): The day of the week, from 1 (Monday) to 7 (Sunday).

[0035] (Holiday or not): Indicates whether the recorded data is from a holiday, represented by 0 (non-holiday) and 1 (holiday).

[0036] (Is it a long holiday): Indicates whether the recorded data comes from a long holiday, represented by 0 (non-long holiday) and 1 (long holiday).

[0037] Passenger car ( )、RV( )、Bus( ),truck( ): refers to the number of vehicles classified according to vehicle type.

[0038] Historical energy and water consumption data of the opposite service area: .

[0039] Step S2: Obtain time data.

[0040] Get time data, including the current hour , day of the week 、Whether it is a holiday , whether it is a long holiday , where long holidays are defined as consecutive holidays ≥ 5 days; Step S3: Retrieve the historical energy consumption data of the opposite service area from the database and align the current prediction period by timestamp.

[0041] Retrieve the historical energy consumption data of the opposite service area from the database , and align the current forecast period by timestamp; Step S4: Calculate the measured energy consumption according to the vehicle flow data.

[0042] Calculate the measured energy consumption based on the vehicle flow data , the calculation formula is: ; in, 、 、 、 The product of the probability of a passenger car, RV, bus and truck consuming energy in the next hour in this service area and the energy consumed. The vehicle flow data includes the number of passenger cars , Number of RVs , Number of buses , Number of trucks And the corresponding number of electric vehicles 、 、 、 ， 、 、 、 The energy consumption coefficient of the electric vehicle is dynamically calibrated through the charging pile utilization rate and battery replacement frequency.

[0043] It can be understood that in step S4, 、 、 、 Dynamically updated through the following methods: real-time collection of charging pile power data and battery replacement times; combining vehicle battery capacity and charging efficiency to fit the energy consumption coefficient of the electric vehicle per unit stay time.

[0044] Step S5: Calculate the time-influenced energy consumption based on the time data.

[0045] Calculate the time-based energy consumption, including the hours-based energy consumption , Week of the week affects energy consumption , Holidays affect energy consumption Long holidays affect energy consumption : ; ; ; ; in, , , Through historical energy consumption data fitting optimization, when the number of holidays is ≥ 5, set =1 and prioritize calculation .

[0046] It should be noted that in step S5, the holiday parameter and The value of is optimized in the following ways: Extract holiday energy consumption data from the past five years and classify and count them by holiday length; The least squares method was used to fit the linear and nonlinear effects of different holiday lengths on energy consumption.

[0047] Step S6: Calculate the opposite-side impact energy consumption based on the historical energy consumption data of the opposite-side service area.

[0048] Calculate the opposite side's impact energy consumption based on the historical energy consumption data of the opposite service area , the formula is: ; ; in, is the sigmoid function, is the fitted weight matrix, is the fitted bias matrix, is the impact rate of dynamic adjustment, is the historical data of the opposite service area. It is the predicted energy consumption of the local service area, which is updated in real time based on the vehicle return probability.

[0049] It should be noted that in step S6, the impact rate is dynamically adjusted. When , weather data is introduced as an additional input parameter, including: Get real-time rainfall, temperature and visibility data through the meteorological interface; According to the severity of the weather, the return probability is adjusted. The weight distribution of .

[0050] Step S7. Accumulate the measured energy consumption, time-affected energy consumption and opposite-side-affected energy consumption to obtain a total energy consumption prediction value; .

[0051] The calculations are performed in real time by an embedded system or programmable logic controller (PLC) and an interactive flow chart is generated to show the contribution ratio of each energy consumption component and the predicted confidence interval.

[0052] In a specific implementation, in step S7, the interactive flowchart enhances visualization in the following ways: displaying the real-time distribution of vehicle density in each road section in the form of a heat map; superimposing a time axis sliding window to support users to compare and analyze historical prediction results with measured data.

[0053] It can be understood that the method further includes a water consumption prediction module: associating the total energy consumption prediction value E with the historical water consumption data to construct an energy consumption-water consumption mapping model; outputting the real-time water consumption prediction value W based on the mapping model, and controlling the service area water pump and water storage equipment through PLC linkage.

[0054] It should be noted that the innovative features of this embodiment include: Hybrid modeling: integrating measured data with empirical formulas, taking into account both real-time and historical laws; Dynamic parameter optimization: real-time update of model parameters through charging pile data and weather information; Modeling of the contralateral tidal effect: introducing a probabilistic activation factor to accurately characterize the impact of return traffic; Embedded deployment: Lightweight algorithm, supporting PLC integration and visual interaction.

[0055] It can be understood that this embodiment can realize the energy consumption prediction during the commuting peak period, for example: Data collection: During the morning rush hour in a service area ( =8, Monday =1) Collected =120 vehicles, =20 vehicles; Calculation of actual energy consumption: =0.5 kWh / vehicle, =2.0 kWh / vehicle, then =120×0.5+20×2.0=100 kWh; Time impact: ; Contralateral effects: hypothesis =0.3, =80 kWh ， but =0.3×80=24 kWh; Total energy consumption: E=100+132+110+0+0+24=366 kWh; Water consumption prediction: According to the mapping model W=0.2E, the output is W=73.2 m³.

[0056] In a specific implementation, one of the methods of dynamic road segment adjustment may also include: When a road section is congested due to an accident, the system automatically splits it into three sections (original length 50 km → 3×17 km), improving data granularity; Updated Recalculate the distribution to 40,35,45 , the error will be reduced by 12%.

[0057] This embodiment uses a method based on traffic data analysis to predict the energy and water consumption of highway service areas. It combines vehicle flow data, time information and specific vehicle type statistics, and uses a series of calculation models to accurately predict the energy and water consumption of service areas at different times and under different conditions.

[0058] In addition, an embodiment of the present application also proposes a computer-readable storage medium, on which a program for semi-empirical hybrid high-speed service area consumption prediction is stored. When the program for semi-empirical hybrid high-speed service area consumption prediction is executed by a processor, the steps of the method for semi-empirical hybrid high-speed service area consumption prediction as described above are implemented.

[0059] Reference Figure 3 , Figure 3This is a structural block diagram of the first embodiment of the semi-empirical hybrid highway service area consumption prediction device of the present application.

[0060] like Figure 3 As shown, the semi-empirical hybrid high-speed service area consumption prediction device proposed in the embodiment of the present application includes: The data processing module 10 is used to obtain the vehicle flow data in the preset road section of the target service area, and divide the data collection interval according to the preset road section length through the highway toll station and the monitoring system; The time extraction module 20 is used to obtain time data, which includes the current hour. , day of the week 、Whether it is a holiday , whether it is a long holiday , where long holidays are defined as consecutive holidays ≥ 5 days; The data calling module 30 is used to call the historical energy consumption data of the opposite service area from the database and align the current prediction period according to the timestamp; An energy consumption calculation module 40, used to calculate the measured energy consumption according to the vehicle flow data; A time calculation module 50, for calculating the time-influenced energy consumption based on the time data; A model building module 60, for calculating the opposite side impact energy consumption based on the historical energy consumption data of the opposite side service area; The output module 70 is used to accumulate the measured energy consumption, the time-affected energy consumption and the opposite-side-affected energy consumption to obtain a total energy consumption prediction value.

[0061] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present application. In specific applications, technicians in this field can make settings as needed, and the present application does not impose any limitation on this.

[0062] This embodiment uses a method based on traffic data analysis to predict the energy and water consumption of highway service areas. It combines vehicle flow data, time information and specific vehicle type statistics, and uses a series of calculation models to accurately predict the energy and water consumption of service areas at different times and under different conditions.

[0063] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present application. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0064] In addition, for technical details not fully described in this embodiment, please refer to the semi-empirical hybrid highway service area consumption prediction method provided in any embodiment of the present application, which will not be repeated here.

[0065] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0066] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0067] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of each embodiment of the present application. The above is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. All equivalent structures or equivalent process changes made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are similarly included in the patent protection scope of the present application.

Claims

1. A semi-empirical hybrid high-speed service area consumption prediction method, characterized in that: include: S1. Obtain vehicle flow data within a preset section of the target service area, and divide the data collection interval according to the preset section length through the highway toll station and monitoring system; S2. Obtain time data, the time data includes the current hour , day of the week 、Whether it is a holiday , whether it is a long holiday , where long holidays are defined as consecutive holidays ≥ 5 days; S3. Call the historical energy consumption data of the opposite service area from the database and align the current forecast period by timestamp; S4. Calculate the measured energy consumption based on the vehicle flow data; S5. Calculate the time impact on energy consumption based on time data; S6. Calculate the energy consumption of the opposite side based on the historical energy consumption data of the opposite service area; S7. Accumulate the measured energy consumption, the time-affected energy consumption and the opposite-side-affected energy consumption to obtain a predicted value of the total energy consumption.

2. The semi-empirical hybrid high-speed service area consumption prediction method according to claim 1 is characterized in that: In step S1, the division of the preset road sections adopts a dynamic adjustment strategy, and the road sections are automatically merged or split according to the real-time traffic flow density to optimize the data collection accuracy.

3. The semi-empirical hybrid high-speed service area consumption prediction method according to claim 1 is characterized in that: In step S4, the measured energy consumption is calculated based on the vehicle flow data. , the calculation formula is: ； in, 、 、 、 The product of the probability of a passenger car, RV, bus and truck consuming energy in the next hour in this service area and the energy consumed. The vehicle flow data includes the number of passenger cars , Number of RVs , Number of buses , Number of trucks And the corresponding number of electric vehicles 、 、 、 ， 、 、 、 The energy consumption coefficient of the electric vehicle is dynamically calibrated by the charging pile utilization rate and the battery replacement frequency. 、 、 、 Dynamic updates via: Real-time collection of charging pile power data and battery replacement times; The energy consumption coefficient of the electric vehicle per unit stay time is fitted by combining the vehicle battery capacity and charging efficiency.

4. The semi-empirical hybrid high-speed service area consumption prediction method according to claim 1 is characterized in that: In step S5, the time-related energy consumption is calculated based on the time data, including the number of hours affecting the energy consumption. , Week of the week affects energy consumption , Holidays affect energy consumption Long holidays affect energy consumption : ； ； ； ； in, Indicates the number of hours, Indicates the specific day of the week. , , Through historical energy consumption data fitting optimization, when the number of holidays is ≥ 5, is the change in energy consumption caused by the number of commuters on Monday and Friday. The increase in energy consumption is caused by the increase in passenger traffic on weekends. Indicates whether the recorded data is from a holiday, with 0 indicating a non-holiday and 1 indicating a holiday. Indicates whether the recorded data is from a long holiday. 0 indicates a non-long holiday and 1 indicates a long holiday. =1 and prioritize calculation ; Holiday parameters and The value of is optimized in the following ways: Extract holiday energy consumption data from the past five years and classify and count them by holiday length; The least squares method was used to fit the linear and nonlinear effects of different holiday lengths on energy consumption.

5. The semi-empirical hybrid high-speed service area consumption prediction method according to claim 1 is characterized in that: In step S6, the energy consumption of the opposite service area is calculated based on the historical energy consumption data of the opposite service area. , the formula is: ； ； in, is the sigmoid function, is the fitted weight matrix, is the fitted bias matrix, is the impact rate of dynamic adjustment, is the historical data of the opposite service area. is the predicted energy consumption of the local service area, which is updated in real time based on the vehicle return probability; Dynamically adjust impact rate When , weather data is introduced as an additional input parameter, including: Get real-time rainfall, temperature and visibility data through the meteorological interface; According to the severity of the weather, the return probability is adjusted. The weight distribution of .

6. The semi-empirical hybrid high-speed service area consumption prediction method according to claim 1 is characterized in that: The steps of step S7 include: Accumulate the measured energy consumption, time-affected energy consumption and opposite-side-affected energy consumption to obtain the total energy consumption forecast value; Calculations are performed in real time through embedded systems or programmable logic controllers, and interactive flow charts are generated to show the contribution ratio of each energy consumption component and the predicted confidence interval; Among them, interactive flowcharts enhance visualization in the following ways: Display the real-time distribution of vehicle density on each road section in the form of a heat map; The superimposed time axis sliding window supports users to conduct comparative analysis between historical prediction results and measured data.

7. The semi-empirical hybrid high-speed service area consumption prediction method according to claim 1 is characterized in that: The method further comprises a water consumption prediction module: The total energy consumption forecast value E is associated with the historical water consumption data to build an energy consumption-water consumption mapping model; The real-time water consumption prediction value W is output based on the mapping model, and the water pumps and water storage equipment in the service area are controlled through PLC linkage.

8. A semi-empirical hybrid high-speed service area consumption prediction device, characterized in that: Executing the method according to claim 1, comprising: The data processing module is used to obtain the vehicle flow data within the preset road section of the target service area, and divide the data collection interval according to the preset road section length through the highway toll station and monitoring system; A time extraction module is used to obtain time data, which includes the current hour. , day of the week 、Whether it is a holiday , whether it is a long holiday , where long holidays are defined as consecutive holidays ≥ 5 days; A data calling module is used to call the historical energy consumption data of the opposite service area from the database and align the current prediction period by timestamp; An energy consumption calculation module, used to calculate the measured energy consumption according to the vehicle flow data; A time calculation module, used to calculate the time-influenced energy consumption based on time data; A model building module is used to calculate the opposite side impact energy consumption based on the historical energy consumption data of the opposite side service area; The output module is used to accumulate the measured energy consumption, the time-affected energy consumption and the opposite-side-affected energy consumption to obtain the total energy consumption prediction value.

9. A computer device, characterized in that: The device comprises: a memory and a processor, and when the processor runs the computer instructions stored in the memory, the processor executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The method comprises instructions, which, when executed on a computer, cause the computer to execute the method according to any one of claims 1 to 7.

Images