Methods, devices, equipment, and storage media for dynamic photovoltaic power consumption optimization in highway service areas

Abstract

This invention discloses a method, apparatus, equipment, and storage medium for dynamic photovoltaic (PV) absorption optimization in highway service areas. The method includes: preprocessing multi-source heterogeneous data from highway service areas to obtain data to be analyzed; performing correlation analysis on the data to be analyzed to obtain coupling information of influencing factors; performing load forecasting and PV power generation forecasting based on load data, PV power generation data, and coupling information of influencing factors; evaluating the PV absorption capacity of service areas for each time period based on the load forecasting information and PV power generation forecasting information to obtain the PV absorption assessment results for each time period; constructing a PV absorption optimization model; and optimizing PV absorption based on the PV absorption optimization model and the PV absorption assessment results of service areas. This significantly improves the local absorption rate of PV power generation in highway service areas, reduces energy waste, lowers the overall energy cost of service areas, and improves energy utilization efficiency and power supply reliability.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic power consumption optimization, and in particular to a method, apparatus, equipment and storage medium for dynamic photovoltaic power consumption optimization in highway service areas. Background Technology

[0002] Highway service areas, as crucial nodes in the transportation network, consume enormous amounts of energy and are areas of high electricity load, exhibiting typical characteristics such as high overall load, regional load imbalance, and significant periodic fluctuations. To reduce carbon emission and operating costs, the construction of distributed photovoltaic (PV) power generation systems in service areas has become a trend. However, PV power generation inherently possesses intermittent and fluctuating characteristics, and its power generation curve often fails to match the complex and ever-changing electricity demand curve of service areas, resulting in poor PV absorption capacity and energy waste. Currently, the absorption of PV power generation in highway service areas generally faces multiple challenges. On the one hand, existing technologies often lack a deep understanding of the complex electricity consumption scenarios in service areas; on the other hand, existing methods lack effective dynamic adjustment means to address the regional imbalance and periodic fluctuations in service area load. Therefore, the current inability to effectively analyze the impact of multi-dimensional influencing factors on service area load demand and PV power generation in complex electricity consumption scenarios hinders the effective improvement of PV absorption capacity in service areas, leading to persistently high curtailment rates, increased energy costs, and unstable power supply in highway service areas. Summary of the Invention

[0003] The main objective of this invention is to provide a method, apparatus, equipment, and storage medium for dynamic photovoltaic (PV) absorption optimization in highway service areas. This invention aims to address the technical problem that existing technologies have failed to effectively analyze the impact of multi-dimensional influencing factors on the load demand and PV power generation in complex power consumption scenarios in service areas, resulting in low PV absorption optimization capabilities in highway service areas.

[0004] To achieve the above objectives, the present invention provides a method for optimizing dynamic photovoltaic power consumption in highway service areas, the method comprising the following steps:

[0005] Data is collected from highway service areas, and the collected multi-source heterogeneous data is preprocessed to obtain data to be analyzed. The highway service area includes multiple sub-areas, and the data to be analyzed includes load data, photovoltaic power generation data, and relevant data of factors affecting load data and photovoltaic power generation data in each sub-area. The influencing factors include traffic flow, meteorological environment, time, energy storage system status, and grid interaction status.

[0006] The data to be analyzed is subjected to correlation analysis to obtain the coupling information of influencing factors. The coupling information of influencing factors includes the coupling relationship between each influencing factor and the load data of each sub-region, as well as the coupling relationship between each influencing factor and the photovoltaic power generation data.

[0007] Based on the load data and the coupling information of the influencing factors, a load prediction model for each sub-region is constructed, and load prediction is performed through the load prediction model to obtain the load prediction information for each sub-region.

[0008] A photovoltaic power generation prediction model is constructed based on the photovoltaic power generation data and the coupling information of the influencing factors, and photovoltaic power generation prediction is performed through the photovoltaic power generation prediction model to obtain photovoltaic power generation prediction information.

[0009] The photovoltaic absorption capacity of the service area for each time period is evaluated based on the load forecast information and the photovoltaic power generation forecast information to obtain the photovoltaic absorption assessment results of the service area for each time period. The photovoltaic absorption assessment results of the service area include the photovoltaic absorption assessment results of each sub-region.

[0010] A photovoltaic (PV) grid connection optimization model is constructed, and PV grid connection optimization is performed based on the PV grid connection optimization model and the PV grid connection assessment results of the service area.

[0011] Optionally, the step of assessing the photovoltaic absorption capacity of the service area for each time period based on the load forecast information and the photovoltaic power generation forecast information, and obtaining the photovoltaic absorption assessment results of the service area for each time period, includes:

[0012] The current irradiance and time information are monitored, and the current switching confidence level is determined based on the monitoring results. The current switching confidence level is calculated based on the following confidence function:

[0013]

[0014] in, Indicates at time Mode switching confidence, At any moment Real-time total irradiance on the horizontal plane, Indicates the irradiance threshold. This indicates the deviation of the current time from the sunrise or sunset time. Indicates the maximum time deviation. This indicates switching sensitivity parameters, which are used to control the steepness of the confidence function curve;

[0015] In response to the current switching confidence level satisfying the prediction mode switching condition, the current prediction mode is switched, and the current prediction mode includes daytime prediction mode and nighttime prediction mode;

[0016] Monitor the day-night prediction results of the daytime prediction model and the nighttime prediction model, wherein the day-night prediction results include daytime prediction results and nighttime prediction results;

[0017] Based on the day and night forecast results, holiday correction coefficients, load forecast information, and photovoltaic power generation forecast information, the photovoltaic absorption capacity of the service area for each time period is evaluated to obtain the photovoltaic absorption evaluation results of the service area for each time period.

[0018] Optionally, the response after the current switching confidence level satisfies the prediction mode switching condition further includes:

[0019] Determine the duration of the transition period for switching forecasting modes;

[0020] During the transition period, photovoltaic output is predicted based on a hybrid prediction model, which is based on the following formula:

[0021]

[0022]

[0023] in, This represents the predicted photovoltaic output under the hybrid forecasting model. This represents the predicted photovoltaic output value of the daytime forecasting model during the transition period. This represents the predicted photovoltaic output value for the nighttime forecasting mode during the transition period. Indicates the error compensation term. This represents the dynamic weights used to predict values ​​during a smooth transition. Represents the time constant. The switching time refers to the moment when the current switching confidence level meets the prediction mode switching condition.

[0024] At the end of the transition period, the step of switching the current forecast mode, which includes a daytime forecast mode and a nighttime forecast mode, is performed.

[0025] Optionally, the daytime forecasting model includes:

[0026] Monitor traffic flow change information, and calculate the shading power loss parameter and daytime charging demand forecast based on the traffic flow change information. Perform photovoltaic output forecast based on the shading power loss parameter and the daytime charging demand forecast. The traffic flow change information includes the vehicle speed and vehicle type in the traffic flow.

[0027] The shielding power loss parameter is calculated based on the following formula:

[0028]

[0029] in, This represents the parameter indicating the power loss due to shading. Indicates time Irradiance, This represents the total area of ​​the photovoltaic array. This represents the average shading efficiency. Indicates the vehicle's speed. Indicates vehicle type. Indicates the dynamic occlusion coefficient;

[0030] The predicted daytime charging demand is calculated based on the following formula:

[0031]

[0032] in, Indicates time Forecast of daytime charging demand, Indicates time The number of new energy vehicles Indicates time The proportion of new energy vehicles and These represent the rated power of fast charging stations and slow charging stations, respectively. This represents the cloud cover correction factor. Indicates time Cloud cover.

[0033] The nighttime prediction model includes:

[0034] The base load of each sub-region is predicted and determined:

[0035]

[0036] in, Indicates time Basic load capacity, Indicates the first The basic load dynamic weights for each sub-region are dynamically adjusted based on holidays, weather, and / or grid load conditions. Indicates the first Each sub-region at the same historical time point Actual load data;

[0037] To predict sudden charging events, determine the probability of sudden charging events within the prediction time window:

[0038]

[0039]

[0040] in, Indicates the time period Inside, it happened The probability of a sudden charging event. Represents a random variable. This indicates the actual number of sudden charging events that occurred. Indicates the forecast time window, Indicates at time The incidence of sudden charging incidents, Indicates the baseline incidence rate. This represents the holiday adjustment factor. Indicates holiday-related variable parameters. Indicates the weather warning level. This indicates the weather adjustment factor. Indicates the power grid load status. Indicates the power grid load adjustment coefficient;

[0041] The number of sudden charging events within the prediction time window is determined based on the probability of the sudden charging event, and the emergency charging power is determined based on the number of sudden charging events.

[0042]

[0043] in, Indicates time The emergency charging power refers to the additional charging power required due to a sudden event. This indicates the rated power of the fast charging station. This represents the power derating factor. Indicates the prediction time window The number of sudden charging incidents within the area;

[0044] Photovoltaic output is predicted based on the base load of each sub-region and the emergency charging power.

[0045] Optionally, the assessment of the photovoltaic absorption capacity of the service area for each time period based on the day-night forecast results, holiday correction coefficients, load forecast information, and photovoltaic power generation forecast information, to obtain the photovoltaic absorption assessment results for the service area for each time period, includes:

[0046] Based on the daytime forecast results, the shading power loss parameters and the predicted daytime charging demand are obtained. The photovoltaic power generation forecast information is then corrected based on the shading power loss parameters to obtain the target photovoltaic power generation forecast value, as shown in the following formula:

[0047]

[0048] in, This represents the target photovoltaic power generation forecast. This represents the uncorrected baseline forecast value of photovoltaic power generation in the photovoltaic power generation forecast information. This represents the parameter indicating the power loss due to shading.

[0049] Based on the daytime charging demand forecast, the basic load forecast value of the charging pile area in the load forecast information is corrected to obtain the daytime load forecast value of the charging pile area, referring to the following formula:

[0050]

[0051] in, This represents the predicted daytime load for the charging station area. This represents the predicted load base value for the charging pile area. This indicates the predicted daytime charging demand. This represents the error compensation term for load forecasting;

[0052] Determine the total nighttime load forecast based on the nighttime forecast results:

[0053]

[0054] in, This represents the predicted total load for the night. Indicates time Basic load capacity, Indicates time Emergency charging power;

[0055] The load forecast information is corrected based on the daytime load forecast value and the nighttime total load forecast value of the charging pile area to obtain the target load forecast value;

[0056] A coupled prediction model is constructed based on the target load forecast, the target photovoltaic power generation forecast, and the holiday correction coefficient. The photovoltaic absorption capacity of the service area in each time period is evaluated through the coupled prediction model to obtain the photovoltaic absorption evaluation results of the service area in each time period.

[0057] Optionally, the construction of the photovoltaic power consumption optimization model includes:

[0058] Construct a first objective function and a second objective function. The first objective function is used to optimize the local photovoltaic grid integration rate, and the first objective function is defined by the following formula:

[0059]

[0060] in, Denotes the first objective function. Indicates the local grid connection rate of photovoltaic power. This indicates the total duration of the optimization cycle. Represented as time The photovoltaic power generation forecast is determined based on the photovoltaic power generation forecast information output by the photovoltaic power generation forecast model. Indicates time The actual photovoltaic power generation consumed by the load of highway service areas. Represents positive numbers;

[0061] The second objective function is used to optimize the overall energy cost, and the second objective function is defined by the following formula:

[0062]

[0063] in, This represents the second objective function. Indicates the overall energy cost. Indicates time Time-of-use electricity pricing for the power grid The power grid interaction power is represented by the time interval. The power purchased from the power grid, where a positive value for the power grid interaction indicates that power is drawn from the grid, and a negative value indicates that power is supplied to the grid. This represents the operation and maintenance cost coefficient per unit power charge and discharge of an energy storage system. Indicates time The charging and discharging power of the energy storage system;

[0064] Construct a comprehensive optimization objective function based on the first objective function and the second objective function:

[0065]

[0066] in, This represents the comprehensive optimization objective function. This represents the optimization weight coefficient. This indicates a preset energy cost threshold;

[0067] A photovoltaic power consumption optimization model is constructed based on the comprehensive optimization objective function.

[0068] Optionally, constructing the photovoltaic grid integration optimization model based on the comprehensive optimization objective function includes:

[0069] Obtain demand information for each sub-area of ​​the highway service area, and construct constraints based on the demand information. The constraints include power balance constraints, energy storage system constraints, grid interaction constraints, and zoned power supply priority constraints.

[0070] The power balance constraints include:

[0071]

[0072]

[0073] in, Indicates the grid connection capacity of highway service areas. Indicates time The The load demand of each sub-region is determined based on the load forecast information output by the load forecasting model. Indicates the number of sub-regions;

[0074] The constraints of the energy storage system include state of charge constraints and charge / discharge power constraints. The state of charge constraints include:

[0075]

[0076]

[0077] in, express The state of charge of the energy storage system at any given time. This indicates the lower limit of the energy storage's state of charge. This indicates the upper limit of the energy storage state of charge. express The state of charge of the energy storage system at any given time. Indicates energy storage charging efficiency. express The charging power of the energy storage system at any given time. express The discharge power of the energy storage system at any given time. Indicates the energy storage discharge efficiency. This indicates the total capacity of the energy storage system. Indicates a time interval;

[0078] The charging and discharging power constraints include:

[0079]

[0080]

[0081] in, Indicates the rated power of the equipment in the energy storage system;

[0082] The power grid interaction constraints include:

[0083]

[0084] in, Indicates the upper limit of grid access capacity;

[0085] The zoned power supply priority constraints include:

[0086]

[0087] in, , and They represent the first Priority coefficients for each sub-region;

[0088] A photovoltaic power consumption optimization model is constructed based on the constraints and the comprehensive optimization objective function.

[0089] Furthermore, to achieve the above objectives, the present invention also proposes a dynamic photovoltaic power absorption optimization device for highway service areas, the device comprising:

[0090] The data processing module is used to collect data from highway service areas and preprocess the collected multi-source heterogeneous data to obtain data to be analyzed. The highway service area includes multiple sub-areas. The data to be analyzed includes load data, photovoltaic power generation data, and related data of factors affecting load data and photovoltaic power generation data in each sub-area. The influencing factors include traffic flow, meteorological environment, time, energy storage system status, and grid interaction status.

[0091] The coupling correlation analysis module is used to perform correlation analysis on the data to be analyzed and obtain the coupling information of influencing factors. The coupling information of influencing factors includes the coupling relationship between each influencing factor and the load data of each sub-region, as well as the coupling relationship between each influencing factor and the photovoltaic power generation data.

[0092] The load forecasting module is used to construct a load forecasting model for each sub-region based on the load data and the coupling information of the influencing factors, and to perform load forecasting through the load forecasting model to obtain load forecasting information for each sub-region.

[0093] The photovoltaic power generation prediction module is used to construct a photovoltaic power generation prediction model based on the photovoltaic power generation data and the coupling information of the influencing factors, and to predict photovoltaic power generation through the photovoltaic power generation prediction model to obtain photovoltaic power generation prediction information.

[0094] The photovoltaic absorption assessment module is used to assess the photovoltaic absorption capacity of the service area for each time period based on the load forecast information and the photovoltaic power generation forecast information, and obtain the photovoltaic absorption assessment results of the service area for each time period. The photovoltaic absorption assessment results of the service area include the photovoltaic absorption assessment results of each sub-region.

[0095] The photovoltaic (PV) grid connection optimization module is used to construct a PV grid connection optimization model and optimize PV grid connection based on the PV grid connection optimization model and the PV grid connection assessment results of the service area.

[0096] In addition, to achieve the above objectives, this application also proposes a dynamic photovoltaic power absorption optimization device for highway service areas. The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the dynamic photovoltaic power absorption optimization method for highway service areas as described above.

[0097] In addition, to achieve the above objectives, this application also proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for optimizing the dynamic photovoltaic power consumption in highway service areas.

[0098] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the above-described method for optimizing the dynamic absorption of photovoltaic power in highway service areas.

[0099] This invention collects data from highway service areas and preprocesses the collected multi-source heterogeneous data to obtain data to be analyzed. The highway service area includes multiple sub-regions. The data to be analyzed includes load data, photovoltaic (PV) power generation data, and related data of factors affecting the load and PV power generation data of each sub-region. These influencing factors include traffic flow, weather conditions, time, energy storage system status, and grid interaction status. Correlation analysis is performed on the data to be analyzed to obtain coupling information of the influencing factors. This coupling information includes the coupling relationship between each influencing factor and the load data of each sub-region, as well as the coupling relationship between each influencing factor and the PV power generation data. Based on the load data and the coupling information of the influencing factors, a load prediction model for each sub-region is constructed, and load prediction is performed using the load prediction model to obtain load prediction information for each sub-region. Similarly, a PV power generation prediction model is constructed based on the PV power generation data and the coupling information of the influencing factors, and PV power generation prediction is performed using the PV power generation prediction model to obtain PV power generation prediction information. Finally, based on the load prediction information and the PV power generation data… The power generation forecast information is used to assess the photovoltaic (PV) absorption capacity of service areas at different time periods, obtaining the PV absorption assessment results for each time period. These assessment results include the PV absorption assessment results for each sub-region. A PV absorption optimization model is constructed, and PV absorption optimization is performed based on this model and the PV absorption assessment results. This invention analyzes multi-source heterogeneous data from highway servers to obtain the coupling relationship between multiple influencing factors and the load data and PV power generation data of each sub-region. This effectively addresses the problem of load imbalance and periodic drastic fluctuations in different service areas, achieving accurate prediction of PV power generation and regional load. Based on load forecast information and PV power generation forecast information, the PV absorption capacity of service areas at different time periods is assessed to determine whether there is a surplus or shortage of PV power in the service area. Dynamic PV absorption optimization is performed through the PV absorption optimization model, effectively improving the PV absorption capacity of service areas, reducing the curtailment rate, better adapting to the characteristics of PV power generation in highway service areas, reducing the overall energy cost of service areas, and improving energy utilization efficiency and power supply reliability. Attached Figure Description

[0100] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0101] Figure 1 This is a schematic diagram of the structure of the photovoltaic dynamic absorption optimization equipment in the highway service area, which is part of the hardware operating environment of the embodiment of the present invention.

[0102] Figure 2 This is a flowchart illustrating the first embodiment of the photovoltaic dynamic absorption optimization method for highway service areas according to the present invention.

[0103] Figure 3 This is a structural diagram of the photovoltaic-load joint prediction model in one embodiment of the photovoltaic dynamic absorption optimization method for highway service areas of the present invention;

[0104] Figure 4 This is a schematic diagram of the dual-mode architecture of the day-night differential prediction algorithm in one embodiment of the photovoltaic dynamic consumption optimization method for highway service areas of the present invention;

[0105] Figure 5 This is a flowchart illustrating the second embodiment of the photovoltaic dynamic absorption optimization method for highway service areas according to the present invention.

[0106] Figure 6 This is a structural block diagram of the first embodiment of the photovoltaic dynamic absorption optimization device for highway service areas according to the present invention.

[0107] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0108] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0109] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a highway service area photovoltaic dynamic absorption optimization device, which is part of the hardware operating environment of the embodiment of the present invention.

[0110] like Figure 1As shown, the photovoltaic dynamic absorption optimization equipment for the highway service area 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. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0111] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the photovoltaic dynamic absorption optimization equipment for highway service areas. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0112] like Figure 1 As shown, the memory 1005, which is a computer-readable storage medium, may include an operating system, a network communication module, a user interface module, and a photovoltaic dynamic absorption optimization program for highway service areas.

[0113] exist Figure 1 In the illustrated highway service area photovoltaic dynamic absorption optimization device, 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 memory 1005 in the highway service area photovoltaic dynamic absorption optimization device of the present invention can be set in the highway service area photovoltaic dynamic absorption optimization device, and the highway service area photovoltaic dynamic absorption optimization device calls the highway service area photovoltaic dynamic absorption optimization program stored in the memory 1005 through the processor 1001 and executes the highway service area photovoltaic dynamic absorption optimization method provided in the embodiment of the present invention.

[0114] This invention provides a method for optimizing the dynamic absorption of photovoltaic power in highway service areas, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the method for optimizing dynamic photovoltaic power consumption in highway service areas according to the present invention.

[0115] In this embodiment, the method for optimizing the dynamic absorption of photovoltaic power in highway service areas includes the following steps:

[0116] Step S10: Collect data from highway service areas and preprocess the collected multi-source heterogeneous data to obtain the data to be analyzed.

[0117] It should be noted that this embodiment is applied to the optimization of photovoltaic (PV) absorption capacity in highway service areas, achieving more efficient absorption and intelligent energy management of PV power generation in these areas. The core of this approach is to overcome the limitations of traditional methods in accurately predicting regional loads and PV power generation under specific service area conditions, leading to inaccurate PV absorption capacity assessments and an inability to effectively and promptly implement reasonable optimization strategies. This embodiment integrates multi-source data from both inside and outside the service area to accurately predict PV power generation and regional loads. It then uses intelligent scheduling algorithms to dynamically optimize PV power flow, energy storage charging and discharging, and adjustable load response. This maximizes the local absorption rate of PV power generation in the service area, reduces curtailment, effectively addresses regional load imbalances and drastic periodic fluctuations, reduces overall energy costs in the service area, and improves energy efficiency and power supply reliability.

[0118] It should be understood that the executing entity of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or a terminal electronic device capable of performing the above functions. The following description uses a highway service area photovoltaic dynamic absorption optimization device (hereinafter referred to as the optimization device) as an example to illustrate this embodiment and the following embodiments.

[0119] It should be noted that the highway service area includes multiple sub-areas, which can be various functional areas of the highway service area (e.g., charging pile area, catering and commercial area, public lighting area, office and living area). Since the electricity demand of different sub-areas varies significantly in terms of time distribution and peak load (e.g., high load on charging piles and commercial areas during the day, and mainly lighting and some standby load at night), this embodiment achieves load balance analysis of the service area by predicting the load information of each sub-area.

[0120] It should be noted that the data to be analyzed includes load data, photovoltaic power generation data, and related data of factors affecting load data and photovoltaic power generation data in each sub-region. These factors include traffic flow, meteorological environment, time, energy storage system status, and grid interaction status.

[0121] In some embodiments, the optimization device collects multi-source heterogeneous data from highway service areas in real time, including but not limited to the following data:

[0122] Photovoltaic power generation data: real-time power generation, irradiance, module temperature, etc. of each photovoltaic array;

[0123] Zoned load data: By deploying smart metering terminals in key areas such as charging pile areas, catering and commercial areas, lighting areas, and office areas within the service area, real-time power consumption, voltage, and current of each area are collected;

[0124] Environmental meteorological data: temperature, humidity, wind speed, and future weather conditions provided by local meteorological stations or authoritative weather forecasts;

[0125] Traffic flow data: Real-time traffic flow, holiday forecast traffic flow, and vehicle type (affecting charging demand) data are obtained from the highway management system via an interface;

[0126] Energy storage system status data: State of charge (SOC), charge and discharge power, battery temperature, state of health (SOH), etc. of energy storage units;

[0127] Grid interaction data: power and electricity price information (time-of-use pricing, peak-valley pricing) exchanged with the public power grid.

[0128] Step S20: Perform correlation analysis on the data to be analyzed to obtain coupling information of influencing factors.

[0129] It should be noted that the influencing factor coupling information includes the coupling relationship between each influencing factor and the load data of each sub-region, as well as the coupling relationship between each influencing factor and the photovoltaic power generation data.

[0130] In practical implementation, the optimization equipment uses data collaborative processing to clean, align, and fuse the collected multi-source heterogeneous data to construct a unified data view of energy operation in the service area. Data correlation analysis technology is used to identify the coupling relationship between factors such as traffic flow, weather, and time (hours, dates, seasons, holidays) and the load and photovoltaic power generation of each zone.

[0131] Step S30: Construct a load forecasting model for each sub-region based on the load data and the coupling information of the influencing factors, and perform load forecasting through the load forecasting model to obtain load forecasting information for each sub-region.

[0132] In practice, the optimization equipment can be based on historical load data and integrate real-time weather information, predicted traffic flow data, holiday factors, electricity price signals, etc., and use machine learning algorithms (such as LSTM, GRU, or ensemble learning models) to establish a high-precision service area regional and multi-time scale (e.g., ultra-short-term 15 minutes, short-term 1 hour, medium-term 24 hours) load prediction model.

[0133] Step S40: Construct a photovoltaic power generation prediction model based on the photovoltaic power generation data and the coupling information of the influencing factors, and use the photovoltaic power generation prediction model to predict photovoltaic power generation and obtain photovoltaic power generation prediction information.

[0134] In practical implementation, the optimization equipment can establish a high-precision photovoltaic power generation prediction model based on historical power generation data, real-time meteorological data, and numerical weather forecasts. The core data for constructing the photovoltaic power generation prediction model may include, but is not limited to, the following core data:

[0135] Historical power generation data: Includes 15-minute output curves of photovoltaic arrays for the past 3 months (covering at least the entire cycle), output characteristics under different weather types (sunny, cloudy, rainy, snowy), and output degradation records at extreme temperatures (such as modules overheating to 60°C in summer);

[0136] Meteorological data: In addition to basic temperature, humidity, and wind speed, focus on supplementing irradiance-related data (total horizontal irradiance GHI, direct normal irradiance DNI, diffuse irradiance DHI), cloud cover (proportion of high / medium / low clouds), and atmospheric transparency (aerosol optical thickness AOD).

[0137] Spatiotemporal correlation data: installation parameters of photovoltaic arrays (tilt angle, azimuth angle, distribution of shading objects, such as the fixed shading range of service area buildings and trees), and traffic flow data (used for daytime dynamic shading calculation).

[0138] Step S50: Evaluate the photovoltaic absorption capacity of the service area for each time period based on the load forecast information and the photovoltaic power generation forecast information, and obtain the photovoltaic absorption evaluation results of the service area for each time period.

[0139] It should be noted that the photovoltaic absorption assessment results of the service area include the photovoltaic absorption assessment results of each sub-area.

[0140] In practice, the optimization equipment can compare the predicted photovoltaic power generation with the predicted electricity load to assess the photovoltaic absorption capacity of the service area for each time period and determine whether there is a surplus or shortage of photovoltaic power.

[0141] In some embodiments, the optimization device can employ different prediction models to achieve a day-night differentiated prediction algorithm, thereby improving prediction accuracy, based on the different characteristics of photovoltaic power generation and load during the day and night.

[0142] In some embodiments, the optimization device can construct a photovoltaic-load joint forecasting model to predict photovoltaic output and the load of each sub-region (including charging piles and commercial areas), referring to... Figure 3 , Figure 3The diagram shows the structure of a photovoltaic-load joint prediction model in one embodiment. The photovoltaic-load joint prediction model includes an input layer, a multi-dimensional data fusion layer, and an attention allocation layer. The input layer receives photovoltaic features, load features, and traffic flow features. The multi-dimensional features are input to the multi-dimensional data fusion layer for fusion processing. Through shading effect compensation, spatiotemporal coding, and context vector analysis, attention allocation is performed, and feature weighting is performed based on the attention allocation results.

[0143] Furthermore, to improve the accuracy of photovoltaic power generation forecasting, in some embodiments, the forecasting mode is adaptively switched according to the current day-night state by combining the load characteristics of different time periods, thereby achieving day-night differentiated forecasting. The above step S50 may include:

[0144] Step S501: Monitor the current irradiance and time information, and determine the current switching confidence level based on the monitoring results;

[0145] Step S502: In response to the current switching confidence level satisfying the prediction mode switching condition, the current prediction mode is switched, and the current prediction mode includes daytime prediction mode and nighttime prediction mode;

[0146] Step S503: Monitor the day-night prediction results of the daytime prediction model and the nighttime prediction model, wherein the day-night prediction results include daytime prediction results and nighttime prediction results;

[0147] Step S504: Based on the day and night forecast results, holiday correction coefficients, load forecast information, and photovoltaic power generation forecast information, evaluate the photovoltaic absorption capacity of the service area for each time period to obtain the photovoltaic absorption assessment results of the service area for each time period.

[0148] Understandably, the optimization device can determine whether to switch the current prediction mode based on a composite logic of irradiance threshold and clock signal. The primary criterion is real-time GHI (total irradiance on the horizontal plane) (e.g., total irradiance on the horizontal plane > 50W / m²); the secondary criterion is the clock signal (e.g., dynamic calibration of an astronomical clock ±30 minutes).

[0149] It should be understood that the optimization device can determine the current switching confidence level by monitoring current irradiance and time information, and based on the monitoring results. The purpose of the switching confidence level assessment is to determine whether a switch to the prediction mode (daytime / nighttime) is necessary at the current moment. The current switching confidence level is calculated based on the following confidence function:

[0150]

[0151] in, Indicates at time The confidence level for mode switching (the confidence level for mode switching ranges from 0 to 1; the closer the value is to 1, the more likely it is that the prediction mode should be switched). At any moment Real-time total horizontal irradiance (W / m²). Indicates the irradiance threshold (W / m²); This indicates the deviation of the current time from the sunrise or sunset time (in absolute values ​​in minutes). This indicates the maximum time deviation (in minutes, for example, it can be set to 30 minutes). This indicates switching sensitivity parameters, which are used to control the steepness of the confidence function curve; This is a constant term, an empirical correction value, used to balance the weights of the primary and secondary criteria.

[0152] Understandably, the optimization equipment constructs a dynamic map of charging demand by combining the forecast results of daytime and nighttime modes, and introduces a holiday correction coefficient. By comparing the forecast of photovoltaic power generation and the forecast of electricity load, it assesses the photovoltaic absorption capacity of the service area for each time period, determines whether there is a surplus or shortage of photovoltaic power, and focuses on the absorption capacity during peak holiday periods when there are large differences in traffic flow between day and night.

[0153] It should be noted that this embodiment employs a day-night differentiated prediction algorithm, constructing prediction models for daytime shading effects, charging demand, and nighttime base load and sudden charging demand, thereby improving prediction accuracy, reducing curtailment rate, and better adapting to the characteristics of photovoltaic power generation in highway service areas. (Refer to...) Figure 4 , Figure 4 This is a schematic diagram of the dual-mode architecture of the day-night differential prediction algorithm in one embodiment. The daytime mode includes vehicle flow growth rate monitoring, charging demand prediction, photovoltaic-storage-charging collaborative optimization, and charging pile power allocation; the nighttime mode includes basic load prediction, emergency charging demand identification, load superposition output, and energy storage scheduling optimization.

[0154] Furthermore, to avoid abrupt changes in prediction results during mode switching, some embodiments employ a hybrid prediction method during mode switching. Step S502 above may include:

[0155] Step S5021: Determine the duration of the transition period for switching prediction modes;

[0156] Step S5022: During the transition period, photovoltaic power output is predicted based on the hybrid prediction mode;

[0157] Step S5023: When the transition period ends, perform the step of switching the current forecast mode, which includes a daytime forecast mode and a nighttime forecast mode.

[0158] It should be noted that, to avoid abrupt changes in prediction results during mode switching, the optimization device can employ a hybrid prediction window mechanism to execute a hybrid prediction mode (e.g., a weighted average of the predictions before and after the switch). When a sudden change in traffic flow triggers an emergency mode switch, the hybrid prediction mode is defined by the following formula:

[0159]

[0160] in, This represents the photovoltaic power output forecast under the hybrid forecasting mode (unit: kW). This represents the predicted photovoltaic output (unit: kW) during the daytime forecasting mode during the transition period. This represents the predicted photovoltaic output (unit: kW) during the nighttime forecasting mode during the transition period. Indicates the error compensation term (unit: kW); This represents the dynamic weights (dimensionless), which are used to predict values ​​during a smooth transition.

[0161] The dynamic weights are determined based on a weighting function: at the switching time, the weights gradually transition from 1 (using only daytime mode forecasts) to 0 (using only nighttime mode forecasts) to achieve a smooth mode switch. The weighting function is defined by the following formula:

[0162]

[0163] in, Represents the time constant (unit: minutes). The switching time (in minutes) indicates the moment when the current switching confidence level meets the prediction mode switching conditions.

[0164] Furthermore, in order to accurately analyze the impact of daytime traffic flow on photovoltaic power generation forecasting and the impact of sudden charging events at night, thereby improving the forecasting accuracy of daytime and nighttime modes, in some embodiments, the daytime forecasting mode includes:

[0165] The system monitors traffic flow changes and calculates shading power loss parameters and daytime charging demand forecasts based on these information. It then forecasts photovoltaic output based on the shading power loss parameters and daytime charging demand forecasts. The traffic flow changes include vehicle speeds and vehicle types within the traffic flow.

[0166] It should be noted that the optimization equipment uses the differential calculation of traffic flow growth rate (dN / dt) combined with vehicle type correction factors for dynamic shading compensation, thereby reducing shading effect errors. Traffic flow is classified by type, and a vehicle type-shading area mapping table is established. The shading power loss parameters are calculated using the following formula:

[0167]

[0168] in, This represents the parameter indicating the power loss due to shading. Indicates time Irradiance (W / m²) This represents the total area of ​​the photovoltaic array (m²). This represents the average shading efficiency (e.g., based on empirical values, it can be set to 0.15-0.3). Indicates the vehicle's speed (km / h); Indicates the type of vehicle (e.g., car, truck, etc.). Indicates the dynamic occlusion coefficient;

[0169] The dynamic shading coefficient is determined based on the vehicle type, using the following formula:

[0170]

[0171] In practical implementation, the optimized equipment can dynamically predict charging demand by combining real-time traffic flow composition and average charging power. An LSTM model is used to dynamically update the proportion of new energy vehicles. The daytime charging demand forecast is calculated based on the following formula:

[0172]

[0173] in, Indicates time Forecast of daytime charging demand, Indicates time The number of new energy vehicles Indicates time The proportion of new energy vehicles and These represent the rated power of fast charging stations and slow charging stations, respectively. This represents the cloud cover correction factor. Indicates time Cloud cover.

[0174] In some embodiments, the optimization device analyzes the impact of sudden charging events on load forecasting results in a nighttime forecasting mode, wherein the nighttime forecasting mode includes:

[0175] The basic load of each sub-region is predicted and determined;

[0176] Predict sudden charging events and determine the probability of sudden charging events within the prediction time window;

[0177] The number of sudden charging events within the prediction time window is determined based on the probability of the sudden charging event, and the emergency charging power is determined based on the number of sudden charging events.

[0178] Photovoltaic output is predicted based on the base load of each sub-region and the emergency charging power.

[0179] It should be noted that the nighttime forecasting model can predict the combined effect of base load and sudden charging demand. The optimized equipment can predict the base load of each sub-region based on the functional areas of the service area:

[0180]

[0181] in, Indicates time Basic load capacity, Indicates the first The basic load dynamic weights for each sub-region are dynamically adjusted based on holidays, weather, and / or grid load conditions. Indicates the first Each sub-region at the same historical time point Actual load data.

[0182] It should be noted that the optimized equipment can use a modified Poisson process to predict sudden charging demand, and the probability of sudden charging events is predicted with reference to the following formula:

[0183]

[0184]

[0185] in, Indicates the time period Inside, it happened The probability of a sudden charging event is described by a Poisson process, which describes the probability of a random event (here referring to a sudden charging event) occurring within a certain period of time. Represents a random variable. This indicates the actual number of sudden charging events that occurred. Indicates the forecast time window (unit: minutes). Indicates at time The rate of sudden charging events (unit: times / minute).

[0186] The key to the improved Poisson process lies in, It is dynamic and adjusts according to factors such as time, holidays, and weather. The calculation formula is as follows:

[0187]

[0188] in, This represents the baseline occurrence rate (unit: e.g., times / minute), which is the average occurrence rate of sudden charging events under conditions of no holidays, good weather, and normal grid load. This value is usually determined through statistical analysis of historical data.

[0189] This indicates the holiday adjustment factor; This parameter represents a holiday / holiday period (0 or 1). If the current time is a holiday / holiday, then... ,otherwise ;

[0190] Indicates the weather adjustment factor; This indicates the weather warning level (values ​​range from 0 to 1). When the grid load exceeds the threshold, it is set to 1, which indicates grid congestion and may reduce the weight of charging piles.

[0191] Indicates the power grid load adjustment coefficient; Indicates the power grid load status (values ​​range from 0 to 1).

[0192] Indicates the power grid load adjustment coefficient;

[0193] The superimposed emergency charging power is calculated using the following formula:

[0194]

[0195] in, Indicates time The emergency charging power (unit: kW) refers to the additional charging power required due to a sudden event (such as a large number of vehicles arriving at the service area to charge at the same time). This indicates the rated power of the fast charging station (unit: kW). This represents the power derating factor (with a value of 0-1), used to reduce charging power when the grid capacity is insufficient or other situations require limiting charging power, in order to avoid grid overload. Indicates the prediction time window The number of sudden charging events within the timeframe is predicted by an improved Poisson process.

[0196] Furthermore, in order to accurately correct the load forecast results and photovoltaic power generation forecast results, in some embodiments, the optimization device performs load forecast correction and photovoltaic power generation forecast correction by combining the forecast results of daytime forecast mode and nighttime forecast mode. Step S504 above may include:

[0197] Step S5041: Based on the daytime forecast results, obtain the shading power loss parameters and the daytime charging demand forecast, and correct the photovoltaic power generation forecast information based on the shading power loss parameters to obtain the target photovoltaic power generation forecast value.

[0198] Step S5042: Based on the daytime charging demand forecast, the basic load forecast value of the charging pile area in the load forecast information is corrected to obtain the daytime load forecast value of the charging pile area.

[0199] Step S5043: Determine the predicted total load value for the night based on the nighttime forecast results;

[0200] Step S5044: Correct the load forecast information based on the daytime load forecast value and the nighttime total load forecast value of the charging pile area to obtain the target load forecast value;

[0201] Step S5045: Construct a coupled prediction model based on the target load forecast, the target photovoltaic power generation forecast, and the holiday correction coefficient, and evaluate the photovoltaic absorption capacity of the service area for each time period through the coupled prediction model to obtain the photovoltaic absorption evaluation results of the service area for each time period.

[0202] It should be noted that the photovoltaic power generation forecast information is a basic forecast value based on historical photovoltaic power generation forecast data and multiple influencing factors. It does not consider dynamic shading caused by traffic flow (such as vehicles blocking photovoltaic panels). This embodiment analyzes the shading power loss parameters through daytime forecasting models and corrects the photovoltaic power generation forecast information based on the shading power loss parameters, referring to the following formula:

[0203]

[0204] in, This represents the target photovoltaic power generation forecast. This represents the uncorrected baseline forecast value of photovoltaic power generation in the photovoltaic power generation forecast information. This represents the parameter indicating the power loss due to shading.

[0205] It should be noted that the load forecast information includes the basic load forecast value of the charging pile area, but does not fully correlate the dynamic relationship between traffic flow and charging demand. This embodiment analyzes the daytime charging demand forecast through a daytime forecasting model (the charging demand is calculated based on traffic flow, and the basic load forecast is dynamically adjusted to ensure that the load of the charging pile area matches the actual traffic flow). The basic load forecast value of the charging pile area is corrected based on the daytime charging demand forecast, referring to the following formula:

[0206]

[0207] in, This represents the predicted daytime load for the charging station area. This represents the predicted load base value for the charging pile area. This indicates the predicted daytime charging demand. This represents the error compensation term for load forecasting.

[0208] It should be noted that the load forecast information does not take into account the dynamic changes in nighttime load. This embodiment analyzes the base load at night and the emergency charging power caused by sudden charging events through the nighttime forecast model, and determines the total nighttime load forecast value based on the nighttime forecast results, referring to the following formula:

[0209]

[0210] in, This represents the predicted total load for the night. Indicates time Basic load capacity, Indicates time Emergency charging power.

[0211] Understandably, the optimization equipment corrects photovoltaic power generation forecasts and load forecasts through daytime and nighttime forecasting modes, thereby achieving accurate forecasting by combining day and night differences and enabling accurate dynamic assessment of photovoltaic absorption capacity at different times.

[0212] Step S60: Construct a photovoltaic power consumption optimization model, and optimize photovoltaic power consumption based on the photovoltaic power consumption optimization model and the photovoltaic power consumption assessment results of the service area.

[0213] It should be noted that the photovoltaic (PV) grid connection optimization model can be a multi-objective optimization model. In some embodiments, the optimization equipment can establish a multi-objective optimization model for PV grid connection with the optimization objectives of maximizing the local PV grid connection rate and minimizing the comprehensive energy cost of the service area.

[0214] In practical implementation, the optimization equipment can construct a photovoltaic absorption optimization model with the local photovoltaic absorption rate and comprehensive energy cost as optimization objectives. By maximizing the local photovoltaic absorption rate and minimizing the comprehensive energy cost through the photovoltaic absorption optimization model, the photovoltaic absorption of highway service areas can be optimized.

[0215] This embodiment collects data from highway service areas and preprocesses the collected multi-source heterogeneous data to obtain data to be analyzed. The highway service areas include multiple sub-regions. The data to be analyzed includes load data, photovoltaic (PV) power generation data, and related data of factors affecting the load and PV power generation data for each sub-region. These influencing factors include traffic flow, weather conditions, time, energy storage system status, and grid interaction status. Correlation analysis is performed on the data to be analyzed to obtain coupling information of the influencing factors. This coupling information includes the coupling relationship between each influencing factor and the load data of each sub-region, as well as the coupling relationship between each influencing factor and the PV power generation data. Based on the load data and the coupling information of the influencing factors, a load prediction model for each sub-region is constructed, and load prediction is performed using the load prediction model to obtain load prediction information for each sub-region. Similarly, a PV power generation prediction model is constructed based on the PV power generation data and the coupling information of the influencing factors, and PV power generation prediction is performed using the PV power generation prediction model to obtain PV power generation prediction information. Based on the load prediction information and the PV power generation data... The power generation forecast information is used to assess the photovoltaic (PV) absorption capacity of service areas for each time period, obtaining the PV absorption assessment results for each time period. The PV absorption assessment results include the PV absorption assessment results of each sub-region. A PV absorption optimization model is constructed, and PV absorption optimization is performed based on the PV absorption optimization model and the PV absorption assessment results of the service areas. Because this embodiment analyzes the multi-source heterogeneous data of the highway server, it obtains the coupling relationship between multiple influencing factors and the load data and PV power generation data of each sub-region, effectively addressing the problem of load imbalance and periodic drastic fluctuations in different areas of the service area, achieving accurate prediction of PV power generation and regional load, and assessing the PV absorption capacity of service areas for each time period based on load forecast information and PV power generation forecast information, thereby determining whether there is a surplus or shortage of PV power in the service area. Dynamic PV absorption optimization is performed through the PV absorption optimization model, effectively improving the PV absorption capacity of service areas, reducing the curtailment rate, better adapting to the characteristics of PV power generation in highway service areas, reducing the overall energy cost of service areas, and improving energy utilization efficiency and power supply reliability.

[0216] refer to Figure 5 , Figure 5 This is a flowchart illustrating the second embodiment of the photovoltaic dynamic absorption optimization method for highway service areas according to the present invention.

[0217] Based on the first embodiment described above, in this embodiment, step S60 further includes:

[0218] Step S601: Construct the first objective function and the second objective function.

[0219] It should be noted that the first objective function is used to optimize the local photovoltaic grid connection rate, and the first objective function is defined by the following formula:

[0220]

[0221] in, Denotes the first objective function. Indicates the local grid connection rate of photovoltaic power. Indicates the total duration of the optimization cycle (unit: hours, e.g., 24 hours). Represented as time The photovoltaic power generation forecast (unit: kW) is determined based on the photovoltaic power generation forecast information output by the photovoltaic power generation forecast model. Represents positive numbers; Indicates time The actual photovoltaic power generation consumed by the load of highway service areas (unit: kW), which is the sum of the power directly supplied to the load by photovoltaics and the amount of photovoltaic power discharged from energy storage, is calculated with reference to the following formula:

[0222]

[0223] It should be noted that the comprehensive energy cost may include the cost of purchasing electricity from the grid and the cost of charging and discharging losses of the energy storage system. The second objective function is used to optimize the comprehensive energy cost, and the second objective function refers to the following formula:

[0224]

[0225] in, This represents the second objective function. Indicates the overall energy cost. Indicates time The time-of-use electricity price (unit: yuan / kWh, such as 1.2 yuan / kWh during peak hours and 0.3 yuan / kWh during off-peak hours); The power grid interaction power (unit: kW) represents the time interval. The power purchased from the power grid, where a positive power grid interaction power indicates power being taken from the power grid and a negative power grid interaction power indicates power being sent to the power grid; This represents the operation and maintenance cost coefficient per unit power charge and discharge of an energy storage system (unit: yuan / kWh, e.g., 0.1 yuan / kWh). Indicates time The charging and discharging power of the energy storage system (unit: kW, positive value is charging, negative value is discharging).

[0226] Step S602: Construct a comprehensive optimization objective function based on the first objective function and the second objective function.

[0227] It should be noted that, since there is a certain trade-off between the two objectives (such as increasing the absorption rate may increase energy storage costs in the short term), this embodiment uses a weighted coefficient method to transform the dual objectives into a single objective optimization (the weights can be dynamically adjusted according to the operational needs of the service area), and constructs a comprehensive optimization objective function, as shown in the following formula:

[0228]

[0229] in, This represents the comprehensive optimization objective function. Indicates the optimization weight coefficient ( (e.g., when prioritizing consumption or cost). This represents the preset energy cost threshold, i.e., the maximum possible energy cost (used for normalization). (To avoid the influence of dimensions).

[0230] Step S603: Construct a photovoltaic power consumption optimization model based on the comprehensive optimization objective function.

[0231] In some embodiments, the optimization device may consider the load demand of different sub-regions and the impact of photovoltaic power generation, construct constraints, and construct a photovoltaic consumption optimization model based on the constraints and the comprehensive optimization objective function.

[0232] Furthermore, in order to balance the constraints of multiple factors, step S603 above may include:

[0233] Step S6031: Obtain demand information for each sub-area of ​​the highway service area, and construct constraints based on the demand information.

[0234] It should be noted that the constraints include power balance constraints, energy storage system constraints, grid interaction constraints, and zoned power supply priority constraints.

[0235] In some embodiments, the optimization device may consider constraints such as real-time / predicted load demand in each zone, real-time / predicted photovoltaic power generation, upper and lower limits of energy storage SOC and charging and discharging power constraints, grid interaction power limits, line / equipment capacity constraints, and power supply priorities in each area (such as priority for charging piles and emergency systems).

[0236] It should be noted that the power balance constraint is that the total power supply (photovoltaic + energy storage + grid power purchase) at each moment must equal the total load demand. The power balance constraint includes:

[0237]

[0238]

[0239] in, Indicates the grid connection capacity of highway service areas. Indicates time The The load demand of each sub-region is determined based on the load forecast information output by the load forecasting model. Indicates the number of sub-regions.

[0240] It should be noted that the constraints of the energy storage system include state of charge (SOC) constraints and charge / discharge power constraints. SOC constraints can ensure that the energy storage system's SOC remains within a safe range (avoiding overcharging and over-discharging). These SOC constraints include:

[0241]

[0242]

[0243] in, express The state of charge of the energy storage system at any given time. This indicates the lower limit of the energy storage's state of charge. This indicates the upper limit of the energy storage state of charge. express The state of charge of the energy storage system at any given time. Indicates energy storage charging efficiency. express The charging power of the energy storage system at any given time. express The discharge power of the energy storage system at any given time. Indicates the energy storage discharge efficiency. This indicates the total capacity of the energy storage system. Indicates a time interval;

[0244] The charge / discharge power constraint condition is used to ensure that the charge / discharge power does not exceed the rated power of the equipment. The charge / discharge power constraint condition includes:

[0245]

[0246]

[0247] in, Indicates the rated power of the equipment in the energy storage system;

[0248] The grid interaction constraint is used to ensure that the power purchased from the grid does not exceed the grid access capacity limit. The grid interaction constraint includes:

[0249]

[0250] in, Indicates the upper limit of grid access capacity;

[0251] The zoned power supply priority constraint is used to ensure that the load of high-priority areas (such as charging pile areas and emergency power supply systems) is satisfied first. The zoned power supply priority constraint includes:

[0252]

[0253] in, , and They represent the first Priority coefficient of each sub-region (high priority region) , , (Closer to 1 ensures priority allocation of electricity).

[0254] Step S6032: Construct a photovoltaic power consumption optimization model based on the constraints and the comprehensive optimization objective function.

[0255] In some embodiments, the optimization device can realize dynamic photovoltaic absorption based on intelligent scheduling algorithms, specifically including: based on the photovoltaic-load joint forecast results (including load forecast information of each sub-region, photovoltaic power generation forecast information, and forecast results of daytime forecast mode and nighttime forecast mode), under the constraints of power balance and energy storage safety, generating dynamic strategies for photovoltaic power allocation, energy storage charging and discharging, and flexible load adjustment in real time, ultimately achieving "efficient photovoltaic absorption + optimal cost + reliable power supply".

[0256] The intelligent scheduling algorithm adopts a hierarchical collaborative design, using a three-tier architecture of "real-time perception - rolling optimization - hierarchical execution" to adapt to the characteristics of service areas such as "high-frequency fluctuations (e.g., sudden changes in traffic flow) + multi-device collaboration (photovoltaics / energy storage / charging piles)". The specific architecture is shown in Table 1 below. Table 1 is a schematic diagram of the intelligent scheduling algorithm architecture:

[0257] Table 1. Schematic diagram of intelligent scheduling algorithm architecture

[0258]

[0259] In some embodiments, the optimization device may classify the load into levels based on a priority classification criterion, including:

[0260] ① Primary load: charging pile area (especially emergency charging vehicles), emergency power supply system (fire protection / monitoring);

[0261] ② Secondary load: Catering area (business hours 8:00-22:00), office area;

[0262] ③ Level 3 loads: Public lighting (off-peak hours 22:00-6:00), advertising screens and other non-essential loads.

[0263] Optimized equipment can employ a dynamic adjustment mechanism for power distribution:

[0264]

[0265] in, Indicates the first The real-time weight of each sub-region (dynamically adjusted according to traffic flow and time period, such as increasing the weight of the charging pile area by 20% when traffic flow surges). express Time assigned to the first Photovoltaic power of each sub-region.

[0266] In some embodiments, the optimization equipment may employ a redundancy mechanism when photovoltaic output is excessive ( The remaining power is preferentially charged into energy storage. Charge at 100% power. (Charge at 50% power).

[0267] In some embodiments, the charging strategy of an energy storage system may include priority logic and a discharging strategy.

[0268] Priority logic could be to prioritize using redundant photovoltaic power for charging, with the charging power being:

[0269]

[0270] in, This is for photovoltaic redundant power; This refers to the rated charging power for energy storage.

[0271] The discharge strategy can be to discharge only when photovoltaic output is insufficient (to make up for the load gap), with the following discharge power:

[0272]

[0273] in, The load shortfall is due to insufficient photovoltaic power; 0.2 is the SOC safety lower limit coefficient; the constraint is... (Avoid over-discharge), depth of discharge ≤ 80%.

[0274] In some embodiments, the optimization device may employ a flexible load response module for charging pile adjustment and air conditioning adjustment, wherein the charging pile adjustment includes:

[0275] When photovoltaic redundancy is enabled: Increase the power limit to 100% of the rated value (default 80%) to shorten charging time;

[0276] When solar power is insufficient: reduce the power of non-emergency charging piles to 60% of the rated value, and prioritize the basic load.

[0277] Air conditioning control includes:

[0278] During daytime solar redundancy: Lower the summer temperature setpoint by 2°C (raise the winter temperature setpoint by 2°C) and increase the load by 10%;

[0279] When solar power is insufficient at night: Increase the summer temperature setting by 2°C (decrease the winter temperature setting by 2°C) and reduce the load by 10%.

[0280] In some embodiments, the optimization device may employ a scenario-based scheduling strategy for scenario optimization scheduling, as shown in Table 2 below. Table 2 is a scenario scheduling strategy design table:

[0281] Table 2, Scenario Scheduling Strategy Design Table

[0282]

[0283] In some embodiments, based on a three-tier architecture of "central decision-making - edge execution - device response," the optimization strategy is accurately implemented throughout the entire process from instruction generation to physical execution, as shown in Table 3 below:

[0284] Table 3, Schematic diagram of optimization strategy architecture

[0285]

[0286] Optimization equipment can be used to optimize photovoltaic power consumption through a rolling optimization strategy. For example, with an optimization cycle of 15 minutes, the prediction model and scheduling strategy are continuously corrected using the latest measured data to achieve a closed-loop iteration of "prediction-decision-execution-feedback". The process is as follows:

[0287] Data synchronization and deviation analysis: The central layer receives three types of key deviation data uploaded by the edge layer every 15 minutes:

[0288] (1) Photovoltaic power output deviation:

[0289]

[0290] in: The predicted value is from step 2;

[0291] (2) Load deviation:

[0292]

[0293] (3) Energy storage SOC deviation:

[0294]

[0295] Example: If If the actual output is lower than the forecast, it is marked as "photovoltaic forecast is too high".

[0296] Dynamic correction of the prediction model: Optimized equipment can update the photovoltaic prediction model and the joint load prediction model based on deviation data.

[0297] (1) Fine-tuning the weight parameters of the LSTM network:

[0298]

[0299] in: For learning rate, The loss function;

[0300] (2) Corrected traffic flow-photovoltaic shading coefficient: If the measured shading loss is 10% higher than the prediction, then (Dynamic occlusion factor) increased by 0.02.

[0301] Optimization strategy regeneration: The central layer substitutes the corrected prediction data into the multi-objective optimization model for photovoltaic power consumption and solves the problem again.

[0302]

[0303] in: (Consumption rate) and All costs are calculated based on the new predicted values, and optimization instructions for the next cycle are output, for example:

[0304] (1) Photovoltaic allocation ratio: The charging pile area is adjusted from 60% to 65% (due to the upward adjustment of the charging load forecast).

[0305] (2) Energy storage discharge power: increased from 100kW to 120kW (due to the downward revision of photovoltaic output forecast).

[0306] Constraints are adaptively adjusted: if they occur in 3 consecutive periods If the actual energy storage capacity is lower than the forecast, the SOC constraint will be dynamically tightened (e.g., reduced from 90% to 85% to avoid overcharging risk).

[0307]

[0308] Anomaly Handling: A three-tiered response mechanism is established to address unexpected scenarios such as equipment failure and data interruption, ensuring stable system operation. Refer to Table 4, which illustrates the anomaly handling process.

[0309] Table 4, Schematic diagram of exception handling

[0310]

[0311] This embodiment constructs a first objective function and a second objective function. The first objective function is used to optimize the local photovoltaic grid integration rate, and the second objective function is used to optimize the overall energy cost. Based on the first objective function and the second objective function, a comprehensive optimization objective function is constructed. Based on the comprehensive optimization objective function, a photovoltaic grid integration optimization model is constructed, thereby achieving multi-objective fusion optimization. This not only significantly improves the local photovoltaic grid integration rate, but also effectively reduces the overall energy cost of service areas, reduces the curtailment rate, and better adapts to the characteristics of photovoltaic power generation in highway service areas.

[0312] Furthermore, this embodiment of the invention also proposes a computer-readable storage medium storing a dynamic photovoltaic power consumption optimization program for highway service areas. When the dynamic photovoltaic power consumption optimization program for highway service areas is executed by a processor, it implements the steps of the dynamic photovoltaic power consumption optimization method for highway service areas as described above.

[0313] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0314] The aforementioned computer-readable storage medium may be included in the photovoltaic dynamic absorption optimization equipment for highway service areas; or it may exist independently and not be installed in the photovoltaic dynamic absorption optimization equipment for highway service areas.

[0315] Furthermore, this invention also proposes a computer program product, including a dynamic photovoltaic power consumption optimization program for highway service areas. When the dynamic photovoltaic power consumption optimization program for highway service areas is executed by a processor, it implements the steps of the dynamic photovoltaic power consumption optimization method for highway service areas as described above.

[0316] The specific implementation of the computer program product of the present invention is basically the same as the embodiments of the above-mentioned method for optimizing the dynamic absorption of photovoltaic power in highway service areas, and will not be repeated here.

[0317] Reference Figure 6 , Figure 6 This is a structural block diagram of the first embodiment of the photovoltaic dynamic absorption optimization device for highway service areas according to the present invention.

[0318] like Figure 6 As shown, the photovoltaic dynamic absorption optimization device for highway service areas proposed in this embodiment of the invention includes:

[0319] The data processing module 10 is used to collect data from the highway service area and preprocess the collected multi-source heterogeneous data to obtain the data to be analyzed. The highway service area includes multiple sub-areas. The data to be analyzed includes load data, photovoltaic power generation data, and related data of factors affecting load data and photovoltaic power generation data in each sub-area. The factors affecting load data and photovoltaic power generation data include traffic flow, meteorological environment, time, energy storage system status, and grid interaction status.

[0320] The coupling correlation analysis module 20 is used to perform correlation analysis on the data to be analyzed and obtain the coupling information of influencing factors. The coupling information of influencing factors includes the coupling relationship between each influencing factor and the load data of each sub-region, as well as the coupling relationship between each influencing factor and the photovoltaic power generation data.

[0321] The load forecasting module 30 is used to construct a load forecasting model for each sub-region based on the load data and the coupling information of the influencing factors, and to perform load forecasting through the load forecasting model to obtain load forecasting information for each sub-region.

[0322] The photovoltaic power generation prediction module 40 is used to construct a photovoltaic power generation prediction model based on the photovoltaic power generation data and the coupling information of the influencing factors, and to predict photovoltaic power generation through the photovoltaic power generation prediction model to obtain photovoltaic power generation prediction information.

[0323] The photovoltaic absorption assessment module 50 is used to assess the photovoltaic absorption capacity of the service area for each time period based on the load forecast information and the photovoltaic power generation forecast information, and obtain the photovoltaic absorption assessment results of the service area for each time period. The photovoltaic absorption assessment results of the service area include the photovoltaic absorption assessment results of each sub-region.

[0324] The photovoltaic power consumption optimization module 60 is used to construct a photovoltaic power consumption optimization model and to optimize photovoltaic power consumption based on the photovoltaic power consumption optimization model and the photovoltaic power consumption assessment results of the service area.

[0325] This embodiment collects data from highway service areas and preprocesses the collected multi-source heterogeneous data to obtain data to be analyzed. The highway service areas include multiple sub-regions. The data to be analyzed includes load data, photovoltaic (PV) power generation data, and related data of factors affecting the load and PV power generation data for each sub-region. These influencing factors include traffic flow, weather conditions, time, energy storage system status, and grid interaction status. Correlation analysis is performed on the data to be analyzed to obtain coupling information of the influencing factors. This coupling information includes the coupling relationship between each influencing factor and the load data of each sub-region, as well as the coupling relationship between each influencing factor and the PV power generation data. Based on the load data and the coupling information of the influencing factors, a load prediction model for each sub-region is constructed, and load prediction is performed using the load prediction model to obtain load prediction information for each sub-region. Similarly, a PV power generation prediction model is constructed based on the PV power generation data and the coupling information of the influencing factors, and PV power generation prediction is performed using the PV power generation prediction model to obtain PV power generation prediction information. Based on the load prediction information and the PV power generation data... The power generation forecast information is used to assess the photovoltaic (PV) absorption capacity of service areas for each time period, obtaining the PV absorption assessment results for each time period. The PV absorption assessment results include the PV absorption assessment results of each sub-region. A PV absorption optimization model is constructed, and PV absorption optimization is performed based on the PV absorption optimization model and the PV absorption assessment results of the service areas. Because this embodiment analyzes the multi-source heterogeneous data of the highway server, it obtains the coupling relationship between multiple influencing factors and the load data and PV power generation data of each sub-region, effectively addressing the problem of load imbalance and periodic drastic fluctuations in different areas of the service area, achieving accurate prediction of PV power generation and regional load, and assessing the PV absorption capacity of service areas for each time period based on load forecast information and PV power generation forecast information, thereby determining whether there is a surplus or shortage of PV power in the service area. Dynamic PV absorption optimization is performed through the PV absorption optimization model, effectively improving the PV absorption capacity of service areas, reducing the curtailment rate, better adapting to the characteristics of PV power generation in highway service areas, reducing the overall energy cost of service areas, and improving energy utilization efficiency and power supply reliability.

[0326] The photovoltaic dynamic absorption optimization device for highway service areas provided in this application adopts the photovoltaic dynamic absorption optimization method for highway service areas in the above embodiments, and can solve the technical problem of photovoltaic dynamic absorption optimization in highway service areas. Compared with the prior art, the beneficial effects of the photovoltaic dynamic absorption optimization device for highway service areas provided in this application are the same as the beneficial effects of the photovoltaic dynamic absorption optimization method for highway service areas provided in the above embodiments, and other technical features in the photovoltaic dynamic absorption optimization device for highway service areas are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0327] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0328] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0329] In addition, for technical details not described in detail in this embodiment, please refer to the method for optimizing the dynamic absorption of photovoltaic power in highway service areas provided in any embodiment of the present invention, which will not be repeated here.

[0330] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0331] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0332] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0333] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for optimizing dynamic photovoltaic power consumption in highway service areas, characterized in that, The method for optimizing the dynamic absorption of photovoltaic power in highway service areas includes: Data is collected from highway service areas, and the collected multi-source heterogeneous data is preprocessed to obtain data to be analyzed. The highway service area includes multiple sub-areas, and the data to be analyzed includes load data, photovoltaic power generation data, and relevant data of factors affecting load data and photovoltaic power generation data in each sub-area. The influencing factors include traffic flow, meteorological environment, time, energy storage system status, and grid interaction status. The data to be analyzed is subjected to correlation analysis to obtain the coupling information of influencing factors. The coupling information of influencing factors includes the coupling relationship between each influencing factor and the load data of each sub-region, as well as the coupling relationship between each influencing factor and the photovoltaic power generation data. Based on the load data and the coupling information of the influencing factors, a load prediction model for each sub-region is constructed, and load prediction is performed through the load prediction model to obtain the load prediction information for each sub-region. A photovoltaic power generation prediction model is constructed based on the photovoltaic power generation data and the coupling information of the influencing factors, and photovoltaic power generation prediction is performed through the photovoltaic power generation prediction model to obtain photovoltaic power generation prediction information. The photovoltaic absorption capacity of the service area for each time period is evaluated based on the load forecast information and the photovoltaic power generation forecast information to obtain the photovoltaic absorption assessment results of the service area for each time period. The photovoltaic absorption assessment results of the service area include the photovoltaic absorption assessment results of each sub-region. A photovoltaic (PV) grid connection optimization model is constructed, and PV grid connection optimization is performed based on the PV grid connection optimization model and the PV grid connection assessment results of the service area. The assessment of the photovoltaic absorption capacity of the service area for each time period based on the load forecast information and the photovoltaic power generation forecast information, to obtain the photovoltaic absorption assessment results for the service area for each time period, includes: The current irradiance and time information are monitored, and the current switching confidence level is determined based on the monitoring results. The current switching confidence level is calculated based on the following confidence function: in, Indicates at time Mode switching confidence, At any moment Real-time total irradiance on the horizontal plane, Indicates the irradiance threshold. This indicates the deviation of the current time from the sunrise or sunset time. Indicates the maximum time deviation. This indicates switching sensitivity parameters, which are used to control the steepness of the confidence function curve; In response to the current switching confidence level satisfying the prediction mode switching condition, the current prediction mode is switched, and the current prediction mode includes daytime prediction mode and nighttime prediction mode; Monitor the day-night prediction results of the daytime prediction model and the nighttime prediction model, wherein the day-night prediction results include daytime prediction results and nighttime prediction results; Based on the day and night forecast results, holiday correction coefficients, load forecast information and photovoltaic power generation forecast information, the photovoltaic absorption capacity of the service area in each time period is evaluated to obtain the photovoltaic absorption evaluation results of the service area in each time period. The daytime forecasting model includes: Monitor traffic flow change information, and calculate the shading power loss parameter and daytime charging demand forecast based on the traffic flow change information. Perform photovoltaic output forecast based on the shading power loss parameter and the daytime charging demand forecast. The traffic flow change information includes the vehicle speed and vehicle type in the traffic flow. The shielding power loss parameter is calculated based on the following formula: in, This represents the parameter indicating the power loss due to shading. Indicates time Irradiance, This represents the total area of ​​the photovoltaic array. This represents the average shading efficiency. Indicates the vehicle's speed. Indicates vehicle type. Indicates the dynamic occlusion coefficient; The predicted daytime charging demand is calculated based on the following formula: in, Indicates time Forecast of daytime charging demand, Indicates time The number of new energy vehicles Indicates time The proportion of new energy vehicles and These represent the rated power of fast charging stations and slow charging stations, respectively. This represents the cloud cover correction factor. Indicates time Cloud cover; The nighttime prediction model includes: The base load of each sub-region is predicted and determined: in, Indicates time Basic load capacity, Indicates the first The basic load dynamic weights for each sub-region are dynamically adjusted based on holidays, weather, and / or grid load conditions. Indicates the first Each sub-region at the same historical time point Actual load data; To predict sudden charging events, determine the probability of sudden charging events within the prediction time window: in, Indicates the time period Inside, it happened The probability of a sudden charging event. Represents a random variable. This indicates the actual number of sudden charging events that occurred. Indicates the forecast time window, Indicates at time The incidence of sudden charging incidents, Indicates the baseline incidence rate. This represents the holiday adjustment factor. Indicates holiday-related variable parameters. Indicates the weather warning level. This indicates the weather adjustment factor. Indicates the power grid load status. Indicates the power grid load adjustment coefficient; The number of sudden charging events within the prediction time window is determined based on the probability of the sudden charging event, and the emergency charging power is determined based on the number of sudden charging events. in, Indicates time The emergency charging power refers to the additional charging power required due to a sudden event. This indicates the rated power of the fast charging station. This represents the power derating factor. Indicates the prediction time window The number of sudden charging incidents within the area; Photovoltaic output prediction is performed based on the base load of each sub-region and the emergency charging power. The construction of the photovoltaic power consumption optimization model includes: Construct a first objective function and a second objective function. The first objective function is used to optimize the local photovoltaic grid integration rate, and the second objective function is used to optimize the overall energy cost. A comprehensive optimization objective function is constructed based on the first objective function and the second objective function; A photovoltaic power consumption optimization model is constructed based on the comprehensive optimization objective function.

2. The method for optimizing dynamic photovoltaic power consumption in highway service areas as described in claim 1, characterized in that, The response after the current switching confidence level satisfies the predicted mode switching condition further includes: Determine the duration of the transition period for switching forecasting modes; During the transition period, photovoltaic output is predicted based on a hybrid prediction model, which is based on the following formula: in, This represents the predicted photovoltaic output under the hybrid forecasting model. This represents the predicted photovoltaic output value of the daytime forecasting model during the transition period. This represents the predicted photovoltaic output value for the nighttime forecasting mode during the transition period. Indicates the error compensation term. This represents the dynamic weights used to predict values ​​during a smooth transition. Represents the time constant. The switching time refers to the moment when the current switching confidence level meets the prediction mode switching condition. At the end of the transition period, the step of switching the current forecast mode, which includes a daytime forecast mode and a nighttime forecast mode, is performed.

3. The method for optimizing dynamic photovoltaic power consumption in highway service areas as described in claim 2, characterized in that, The assessment of the photovoltaic absorption capacity of the service area for each time period is based on the day-night forecast results, holiday correction coefficients, load forecast information, and photovoltaic power generation forecast information, to obtain the photovoltaic absorption assessment results for the service area for each time period, including: Based on the daytime forecast results, the shading power loss parameters and the predicted daytime charging demand are obtained. The photovoltaic power generation forecast information is then corrected based on the shading power loss parameters to obtain the target photovoltaic power generation forecast value, as shown in the following formula: in, This represents the target photovoltaic power generation forecast. This represents the uncorrected baseline forecast value of photovoltaic power generation in the photovoltaic power generation forecast information. This represents the parameter indicating the power loss due to shading. Based on the daytime charging demand forecast, the basic load forecast value of the charging pile area in the load forecast information is corrected to obtain the daytime load forecast value of the charging pile area, referring to the following formula: in, This represents the predicted daytime load for the charging station area. This represents the predicted load base value for the charging pile area. This indicates the predicted daytime charging demand. This represents the error compensation term for load forecasting; Determine the total nighttime load forecast based on the nighttime forecast results: in, This represents the predicted total load for the night. Indicates time Basic load capacity, Indicates time Emergency charging power; The load forecast information is corrected based on the daytime load forecast value and the nighttime total load forecast value of the charging pile area to obtain the target load forecast value; A coupled prediction model is constructed based on the target load forecast, the target photovoltaic power generation forecast, and the holiday correction coefficient. The photovoltaic absorption capacity of the service area in each time period is evaluated using the coupled prediction model to obtain the photovoltaic absorption evaluation results of the service area in each time period.

4. The method for optimizing dynamic photovoltaic power consumption in highway service areas as described in claim 1, characterized in that, The first objective function is defined by the following formula: in, Denotes the first objective function. Indicates the local grid connection rate of photovoltaic power. This indicates the total duration of the optimization cycle. Represented as time The photovoltaic power generation forecast is determined based on the photovoltaic power generation forecast information output by the photovoltaic power generation forecast model. Indicates time The actual photovoltaic power generation consumed by the load of highway service areas. Represents positive numbers; The second objective function is defined by the following formula: in, This represents the second objective function. Indicates the overall energy cost. Indicates time Time-of-use electricity pricing for the power grid The power grid interaction power is represented by the time interval. The power purchased from the power grid, where a positive value for the power grid interaction indicates that power is drawn from the grid, and a negative value indicates that power is supplied to the grid. This represents the operation and maintenance cost coefficient per unit power charge and discharge of an energy storage system. Indicates time The charging and discharging power of the energy storage system; The comprehensive optimization objective function is defined by the following formula: in, This represents the comprehensive optimization objective function. This represents the optimization weight coefficient. This indicates the preset energy cost threshold.

5. The method for optimizing dynamic photovoltaic power consumption in highway service areas as described in claim 4, characterized in that, The step of constructing a photovoltaic power consumption optimization model based on the comprehensive optimization objective function includes: Obtain demand information for each sub-area of ​​the highway service area, and construct constraints based on the demand information. The constraints include power balance constraints, energy storage system constraints, grid interaction constraints, and zoned power supply priority constraints. The power balance constraints include: in, Indicates the grid connection capacity of highway service areas. Indicates time The The load demand of each sub-region is determined based on the load forecast information output by the load forecasting model. Indicates the number of sub-regions; The constraints of the energy storage system include state of charge constraints and charge / discharge power constraints. The state of charge constraints include: in, express The state of charge of the energy storage system at any given time. This indicates the lower limit of the energy storage's state of charge. This indicates the upper limit of the energy storage state of charge. express The state of charge of the energy storage system at any given time. Indicates energy storage charging efficiency. express The charging power of the energy storage system at any given time. express The discharge power of the energy storage system at any given time. Indicates the energy storage discharge efficiency. This indicates the total capacity of the energy storage system. Indicates a time interval; The charging and discharging power constraints include: in, Indicates the rated power of the equipment in the energy storage system; The power grid interaction constraints include: in, Indicates the upper limit of grid access capacity; The zoned power supply priority constraints include: in, , and They represent the first Priority coefficients for each sub-region; A photovoltaic power consumption optimization model is constructed based on the constraints and the comprehensive optimization objective function.

6. A dynamic photovoltaic power consumption optimization device for highway service areas, characterized in that, The photovoltaic dynamic absorption optimization device for highway service areas includes: The data processing module is used to collect data from highway service areas and preprocess the collected multi-source heterogeneous data to obtain data to be analyzed. The highway service area includes multiple sub-areas. The data to be analyzed includes load data, photovoltaic power generation data, and related data of factors affecting load data and photovoltaic power generation data in each sub-area. The influencing factors include traffic flow, meteorological environment, time, energy storage system status, and grid interaction status. The coupling correlation analysis module is used to perform correlation analysis on the data to be analyzed and obtain the coupling information of influencing factors. The coupling information of influencing factors includes the coupling relationship between each influencing factor and the load data of each sub-region, as well as the coupling relationship between each influencing factor and the photovoltaic power generation data. The load forecasting module is used to construct a load forecasting model for each sub-region based on the load data and the coupling information of the influencing factors, and to perform load forecasting through the load forecasting model to obtain load forecasting information for each sub-region. The photovoltaic power generation prediction module is used to construct a photovoltaic power generation prediction model based on the photovoltaic power generation data and the coupling information of the influencing factors, and to predict photovoltaic power generation through the photovoltaic power generation prediction model to obtain photovoltaic power generation prediction information. The photovoltaic absorption assessment module is used to assess the photovoltaic absorption capacity of the service area for each time period based on the load forecast information and the photovoltaic power generation forecast information, and obtain the photovoltaic absorption assessment results of the service area for each time period. The photovoltaic absorption assessment results of the service area include the photovoltaic absorption assessment results of each sub-region. The photovoltaic (PV) grid connection optimization module is used to construct a PV grid connection optimization model and optimize PV grid connection based on the PV grid connection optimization model and the PV grid connection assessment results of the service area. The photovoltaic grid integration assessment module is also used to monitor current irradiance and time information, and determine the current switching confidence level based on the monitoring results. The current switching confidence level is calculated based on the following confidence function: in, Indicates at time Mode switching confidence, At any moment Real-time total irradiance on the horizontal plane, Indicates the irradiance threshold. This indicates the deviation of the current time from the sunrise or sunset time. Indicates the maximum time deviation. This indicates switching sensitivity parameters, which are used to control the steepness of the confidence function curve; In response to the current switching confidence level meeting the prediction mode switching conditions, the current prediction mode is switched, which includes a daytime prediction mode and a nighttime prediction mode; the daytime and nighttime prediction results of the daytime and nighttime prediction modes are monitored, which include daytime prediction results and nighttime prediction results; based on the daytime and nighttime prediction results, holiday correction coefficients, load prediction information, and photovoltaic power generation prediction information, the photovoltaic absorption capacity of the service area for each time period is evaluated to obtain the photovoltaic absorption evaluation results of the service area for each time period; The daytime forecasting model includes: Monitor traffic flow change information, and calculate the shading power loss parameter and daytime charging demand forecast based on the traffic flow change information. Perform photovoltaic output forecast based on the shading power loss parameter and the daytime charging demand forecast. The traffic flow change information includes the vehicle speed and vehicle type in the traffic flow. The shielding power loss parameter is calculated based on the following formula: in, This represents the parameter indicating the power loss due to shading. Indicates time Irradiance, This represents the total area of ​​the photovoltaic array. This represents the average shading efficiency. Indicates the vehicle's speed. Indicates vehicle type. Indicates the dynamic occlusion coefficient; The predicted daytime charging demand is calculated based on the following formula: in, Indicates time Forecast of daytime charging demand, Indicates time The number of new energy vehicles Indicates time The proportion of new energy vehicles and These represent the rated power of fast charging stations and slow charging stations, respectively. This represents the cloud cover correction factor. Indicates time Cloud cover; The nighttime prediction model includes: The base load of each sub-region is predicted and determined: in, Indicates time Basic load capacity, Indicates the first The basic load dynamic weights for each sub-region are dynamically adjusted based on holidays, weather, and / or grid load conditions. Indicates the first Each sub-region at the same historical time point Actual load data; To predict sudden charging events, determine the probability of sudden charging events within the prediction time window: in, Indicates the time period Inside, it happened The probability of a sudden charging event. Represents a random variable. This indicates the actual number of sudden charging events that occurred. Indicates the forecast time window, Indicates at time The incidence of sudden charging incidents, Indicates the baseline incidence rate. This represents the holiday adjustment factor. Indicates holiday-related variable parameters. Indicates the weather warning level. This indicates the weather adjustment factor. Indicates the power grid load status. Indicates the power grid load adjustment coefficient; The number of sudden charging events within the prediction time window is determined based on the probability of the sudden charging event, and the emergency charging power is determined based on the number of sudden charging events. in, Indicates time The emergency charging power refers to the additional charging power required due to a sudden event. This indicates the rated power of the fast charging station. This represents the power derating factor. Indicates the prediction time window The number of sudden charging incidents within the area; Photovoltaic output prediction is performed based on the base load of each sub-region and the emergency charging power. The photovoltaic (PV) grid connection optimization module is further configured to construct a first objective function and a second objective function, wherein the first objective function is used to optimize the local PV grid connection rate and the second objective function is used to optimize the overall energy cost; a comprehensive optimization objective function is constructed based on the first objective function and the second objective function; and a PV grid connection optimization model is constructed based on the comprehensive optimization objective function.

7. A photovoltaic dynamic absorption optimization device for highway service areas, characterized in that, The photovoltaic dynamic absorption optimization device for highway service areas includes: a memory, a processor, and a photovoltaic dynamic absorption optimization program for highway service areas stored in the memory and executable on the processor. The photovoltaic dynamic absorption optimization program for highway service areas is configured to implement the photovoltaic dynamic absorption optimization method for highway service areas as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a dynamic photovoltaic power consumption optimization program for highway service areas, which, when executed by a processor, implements the dynamic photovoltaic power consumption optimization method for highway service areas as described in any one of claims 1 to 5.

Images