A multi-energy complementary zero-carbon toll station construction process optimization method based on energy distribution

Abstract

The present invention discloses a method for optimizing the construction process of a multi-energy complementary zero-carbon toll station based on energy distribution, which relates to the field of toll station construction. The method includes: predicting the electricity demand in the toll station, obtaining the power supply distribution output of the energy equipment based on the electricity demand, and conducting a surplus power sale transaction according to the power supply distribution output result and the power purchase and sales agreement; predicting the load demand in the toll station, adjusting the supply mode of the geothermal heat pump based on the load demand, and determining the heat output of the geothermal heat pump in combination with the real-time temperature and frequency conversion control technology in the toll station; combining the power supply distribution output result, the surplus power sale transaction result, and the heat output result of the geothermal heat pump as an operation process optimization strategy to optimize the multi-energy complementary zero-carbon construction process of the toll station. The present invention ensures that when there is surplus electricity, it can be reasonably sold to the electricity market based on the surplus electricity sale transaction conducted under the power purchase and sales agreement, thereby maximizing the economic value of electricity resources.

Description

Technical Field

[0001] The present invention relates to toll station construction, and in particular to a method for optimizing the construction process of a multi-energy complementary zero-carbon toll station based on energy distribution. Background Art

[0002] As one of the main sources of carbon emissions, the transportation industry is gradually developing towards a low-carbon or even zero-carbon direction. The concept of "zero-carbon toll stations" is based on this trend. As important nodes in the transportation network, toll stations have large energy demands, including lighting, heating, cooling, vehicle charging and daily services. They can combine various new energy technologies to achieve energy self-sufficiency at toll stations and upload excess electricity to the power grid. This can not only reduce carbon emissions, but also reduce energy costs and maximize economic benefits.

[0003] Traditional toll stations usually rely on fossil fuel power generation or conventional power grid power supply. This energy supply method not only leads to high energy consumption, but also produces a large amount of carbon dioxide emissions, which cannot meet the current requirements of low-carbon development. At present, most toll stations rely on a single form of energy (such as power grid power supply) and lack the complementarity and balance of multiple energy sources. As a result, they cannot maintain normal operations when encountering extreme weather or energy supply interruptions. At the same time, the energy management systems of existing toll stations are usually relatively simple and difficult to perform intelligent scheduling according to actual conditions, resulting in low energy utilization efficiency and widespread energy waste. In addition, when the power generation of renewable energy sources such as photovoltaics and wind power exceeds demand, the excess electricity of existing toll stations cannot be effectively processed, which easily leads to energy waste.

[0004] Currently, no effective solutions have been proposed for the problems in related technologies. Summary of the Invention

[0005] In response to the problems in the related technology, the present invention proposes a multi-energy complementary zero-carbon toll station construction process optimization method based on energy distribution to overcome the above-mentioned technical problems existing in the existing related technology.

[0006] To this end, the specific technical solutions adopted in the present invention are as follows:

[0007] A multi-energy complementary zero-carbon toll station construction process optimization method based on energy distribution, including:

[0008] Predict electricity demand within the toll station, obtain the power distribution output of energy equipment based on the power demand, and conduct excess power sales transactions based on the power distribution output results and power purchase and sales agreements;

[0009] Predict the load demand within the toll station, adjust the geothermal heat pump supply mode based on the load demand, and determine the heat output of the geothermal heat pump by combining the real-time temperature within the toll station with variable frequency control technology;

[0010] The power supply distribution output results, excess power sales transaction results and geothermal pump heat output results are combined as an operation process optimization strategy to optimize the multi-energy complementary zero-carbon construction process of the toll station.

[0011] Preferably, predicting the electricity demand in the toll station, obtaining the power distribution output of the energy equipment based on the electricity demand, and conducting a surplus power sale transaction according to the power distribution output result and the power purchase and sale agreement include:

[0012] Obtain historical charging data of charging piles in toll stations and historical power consumption data of living service areas, and combine evidence theory with convolutional neural network technology to predict power demand in toll stations;

[0013] Build a power distribution model based on power demand and the dynamic characteristics of energy equipment power supply, determine the power distribution output of energy equipment, and judge the remaining energy storage capacity of energy equipment;

[0014] Combining the remaining stored energy with the energy generation rate, we can analyze the amount of movable energy available at any time in energy equipment, provided that the electricity consumption of charging stations and living service areas is met.

[0015] The movable energy amount is combined with the power purchase and sale agreement to carry out excess energy sale transaction processing, and the sale time and sales quantity in the excess energy sale transaction processing process are determined according to the real-time electricity price.

[0016] Preferably, the historical charging data of the charging piles in the toll station and the historical power consumption data of the living service area are obtained, and the power demand in the toll station is predicted by combining evidence theory and convolutional neural network technology, including:

[0017] A charging demand matrix is established based on the number of charging piles in the toll station. The charging demand matrix is decomposed into several types of charging modes using the non-negative matrix factorization method to determine the charging scale and size of several types of charging modes in the toll station.

[0018] Generate a base matrix and a coefficient matrix according to the charging scale and the charging scale, and multiply the rows and columns of the base matrix and the coefficient matrix corresponding to the charging mode to obtain a dimensional matrix;

[0019] Obtain historical charging data of charging piles at toll stations and substitute the same-dimensional matrix as input into the graph convolutional neural network to capture the effective information between charging patterns and charging data and predict the power demand of charging piles;

[0020] Obtain historical power consumption data of the living service area within the toll station, and obtain the power demand in the living area based on the historical power consumption development trend and evidence theory, and combine the power demand of the charging piles to obtain the total power demand of the toll station.

[0021] Preferably, obtaining historical power consumption data of the living service area within the toll station and obtaining the power demand in the living area based on the historical power consumption development trend and evidence theory includes:

[0022] Obtain historical power consumption data for each sub-area within the toll station's living service area, and generate a set of power demand forecasts for each sub-area based on the historical power consumption data and seasonal characteristics;

[0023] The basic probability distribution matrix is predicted based on the electricity demand forecast set and the properties of the electrical equipment in the sub-region, and the electricity demand forecast set is synthesized using evidence theory.

[0024] Based on the synthesis results, evidence conflict analysis is performed on the electricity demand forecast set to obtain the credibility function and plausibility function of the electricity demand forecast set, and the credibility function is converted into a probability distribution according to the probability conversion formula;

[0025] The probability distribution of electricity demand in each sub-area is obtained according to the distribution results, and the probability distribution is combined with the basic probability allocation matrix to obtain the electricity demand of the sub-area, and the electricity demand of each sub-area is integrated to obtain the electricity demand in the living area.

[0026] Preferably, building a power distribution model based on power demand and the dynamic characteristics of power supply of energy equipment, determining the power distribution output of the energy equipment, and judging the remaining energy storage capacity of the energy equipment include:

[0027] According to the power generation characteristics and energy storage characteristics of energy equipment, the minimum expected frequency of power distribution of any power supply equipment is analyzed based on the energy storage characteristics, and the minimum power generation objective function of any power supply equipment is defined using the power generation characteristics;

[0028] Based on the Naive Bayesian approach, the maximum a posteriori hypothesis is made for the electricity demand at the toll station, and the maximum a posteriori hypothesis process is smoothed. The dynamic allocation parameters are calibrated according to the processing results.

[0029] The energy consumption of energy equipment during the power supply process is analyzed by combining dynamic allocation parameters, minimum expected frequency and minimum power generation objective function. The objective function of the power supply allocation model is expressed in octets based on Naive Bayes.

[0030] The boundary conditions of the power supply distribution model are set based on the dynamic distribution balance of energy equipment, and the constructed power supply distribution model is obtained by combining the objective function;

[0031] The power distribution model is used to determine the power distribution output of any power supply device, and the remaining energy storage capacity of the energy device is obtained based on the difference between the energy storage capacity of the energy device and the power distribution output.

[0032] Preferably, the power distribution model is expressed as:

[0033] ;

[0034] Where F(t) represents the power distribution of the t-th power supply device, e represents energy consumption, α1 represents the probability that the power distribution output reaches high uniformity, α2 represents the probability that the power distribution output reaches low uniformity, υ represents the objective function of the power distribution model, β represents the minimum power generation target value of any power supply device, and T min represents the minimum expected frequency, and ε represents the dynamic allocation parameter.

[0035] Preferably, combining the movable energy amount with the power purchase and sale agreement to carry out excess energy sale transaction processing, and determining the sale time and sale quantity in the excess energy sale transaction processing according to the real-time electricity price includes:

[0036] Combine the available energy volume with the power purchase and sales agreement to define the rules for selling excess energy, and connect it to the power company's smart meter system to automatically record and upload excess energy output data;

[0037] Obtain historical electricity price data, reconstruct the phase space of the historical electricity price data time series, analyze the phase point of the historical electricity price at any time point, and the closest point to the phase point;

[0038] Obtain the distance between the phase point and its closest point, and traverse the distances between all phase points and their corresponding closest points in the phase space to obtain the dynamic evolution law. Based on the dynamic evolution law, analyze the evolution time series of electricity prices;

[0039] The real-time electricity price at any time is predicted based on the evolving time series, and the time and quantity of excess energy sales transactions are determined according to the level of the real-time electricity price.

[0040] Preferably, predicting the load demand in the toll station, adjusting the supply mode of the geothermal heat pump based on the load demand, and determining the heat output of the geothermal heat pump in combination with the real-time temperature in the toll station and the variable frequency control technology include:

[0041] Obtain historical heating and cooling data within the toll station, and combine seasonal factors with edge distribution technology to predict the heating or cooling load demand of the toll station in any time period;

[0042] determining a temperature requirement within the toll station according to the load demand, determining a supply mode of the geothermal heat pump based on the temperature demand, and adjusting the supply mode of the geothermal heat pump according to the determination result;

[0043] Adjust the supply of geothermal heat pumps based on the real-time temperature and load demand within the toll station, and calculate the optimal operating frequency of the geothermal heat pumps by combining variable frequency control technology with the characteristics of the geothermal heat pumps.

[0044] The heat output result of the geothermal heat pump is output based on the optimal operating frequency and supply, and the optimal operating frequency is adjusted according to real-time feedback to optimize the operating efficiency of the geothermal heat pump.

[0045] Preferably, obtaining historical heating and cooling data within the toll station and combining seasonal factors with marginal distribution technology to predict the heating or cooling load demand of the toll station in any time period includes:

[0046] Based on the historical operation data of toll stations, historical heating and cooling data are obtained. Based on the obtained results, an estimation sample containing the two variables of heating and cooling is constructed. The distribution function value of the estimated sample under seasonal factors is obtained through non-parametric estimation method.

[0047] Construct a conditional matrix based on the marginal distribution function value and the estimated sample, and use the conditional matrix to predict the probability of each data value appearing in the estimated sample and the corresponding marginal value;

[0048] Based on the upper and lower bounds of the pre-set load demand interval, the expected probability of the data value within the load demand interval is analyzed in combination with the probability and marginal value, and the marginal distribution matrix of the data value is obtained using the expected probability;

[0049] The marginal distribution matrix is inversely calculated to obtain the demand forecast interval for heating and cooling at the toll station, and the heating or cooling load demand at the toll station is determined from the demand forecast interval according to the time period.

[0050] Preferably, the probability of occurrence of a data value and the calculation formula of the marginal value are:

[0051] ;

[0052] Where S i represents the probability of the i-th data value appearing in the estimated sample, T i represents the distribution function value of the i-th data value, P represents the characteristic value of the estimated sample under seasonal factors, E i represents the edge value of the i-th data value, H(i,m) represents the joint probability mass function of the data value i and the conditional matrix m, Represents the load size of data value i in the mth conditional matrix.

[0053] The beneficial effects of the present invention are:

[0054] 1. The present invention proposes a multi-energy complementary zero-carbon toll station construction process optimization method based on energy distribution, which aims to achieve efficient operation and zero-carbon goals of toll stations by comprehensively predicting and optimizing multiple energy factors such as power supply, load demand, and geothermal pump heating mode. By predicting the electricity demand of the toll station, it is possible to plan the energy supply method in advance and optimize the distribution of different energy sources based on the prediction results. In addition, according to the load demand, the heating mode of the geothermal pump will be dynamically adjusted so that the heating and cooling load demands are accurately met, avoiding excessive heating or cooling and improving energy efficiency. At the same time, through the sale of excess electricity based on the power purchase and sales agreement, it is ensured that when there is excess electricity, it can be reasonably sold to the power market, which can not only effectively reduce the burden on the power grid, but also bring additional income to the toll station and maximize the economic value of power resources.

[0055] 2. Through precise demand forecasting, intelligent power supply distribution, energy storage management, power sales and transactions, and the maximum use of green energy, the present invention can improve energy utilization efficiency, optimize power transactions to obtain economic benefits, reduce carbon emissions, enhance system stability and reliability, and reduce overall operating costs. At the same time, it improves the intelligence level of toll stations and provides strong support for achieving zero-carbon goals. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 This is a principle block diagram of a method for optimizing the construction process of a multi-energy complementary zero-carbon toll station based on energy distribution according to an embodiment of the present invention;

[0058] Figure 2 This is a principle block diagram of a multi-energy complementary zero-carbon toll station in a method for optimizing the construction process of a multi-energy complementary zero-carbon toll station based on energy distribution according to an embodiment of the present invention;

[0059] Figure 3 This is a principle block diagram of a photovoltaic power generation module in a method for optimizing the construction process of a multi-energy complementary zero-carbon toll station based on energy distribution according to an embodiment of the present invention;

[0060] Figure 4 This is a principle block diagram of a wind power generation module in a method for optimizing the construction process of a multi-energy complementary zero-carbon toll station based on energy distribution according to an embodiment of the present invention;

[0061] Figure 5This is a principle block diagram of a geothermal heating and cooling module in a multi-energy complementary zero-carbon toll station construction process optimization method based on energy distribution according to an embodiment of the present invention. DETAILED DESCRIPTION

[0062] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention. They are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. By referring to these contents, ordinary technicians in this field should be able to understand other possible implementation methods and the advantages of the present invention.

[0063] According to an embodiment of the present invention, a method for optimizing the construction process of a multi-energy complementary zero-carbon toll station based on energy distribution is provided.

[0064] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, the multi-energy complementary zero-carbon toll station construction process optimization method based on energy distribution according to an embodiment of the present invention includes:

[0065] Step S1: predict the electricity demand in the toll station, obtain the power supply distribution output of the energy equipment based on the electricity demand, and conduct a surplus power sale transaction according to the power supply distribution output result and the power purchase and sales agreement.

[0066] In one embodiment, predicting electricity demand within a toll station, obtaining power distribution output of energy equipment based on the power demand, and conducting a transaction for excess power sale in accordance with a power purchase and sale agreement based on the power distribution output result include:

[0067] Obtain historical charging data of charging piles in toll stations and historical power consumption data of living service areas, and combine evidence theory with convolutional neural network technology to predict power demand in toll stations;

[0068] Build a power distribution model based on power demand and the dynamic characteristics of energy equipment power supply, determine the power distribution output of energy equipment, and judge the remaining energy storage capacity of energy equipment;

[0069] Combining the remaining stored energy with the energy generation rate, we can analyze the amount of movable energy available at any time in energy equipment, provided that the electricity consumption of charging stations and living service areas is met.

[0070] The movable energy amount is combined with the power purchase and sale agreement to carry out excess energy sale transaction processing, and the sale time and sales quantity in the excess energy sale transaction processing process are determined according to the real-time electricity price.

[0071] Specifically, when obtaining the historical charging data of the charging piles in the toll station and the historical power consumption data of the living service area, and combining evidence theory with convolutional neural network technology to predict the electricity demand in the toll station, a charging demand matrix can be established based on the number of charging piles in the toll station, and the charging demand matrix can be decomposed into several types of charging modes according to the non-negative matrix decomposition method to judge the charging scale and charging scale of several types of charging modes in the toll station; a basis matrix and a coefficient matrix are generated according to the charging scale and charging scale, and the rows and columns of the corresponding charging modes in the basis matrix and the coefficient matrix are multiplied to obtain a dimension matrix; the historical charging data of the charging piles in the toll station are obtained, and the same-dimensional matrix is substituted into the graph convolutional neural network as input to capture the effective information between the charging mode and the charging data, and predict the electricity demand of the charging piles; the historical power consumption data of the living service area in the toll station is obtained, and the electricity demand in the living area is obtained according to the historical power consumption development trend and evidence theory, and the total electricity demand of the toll station is obtained by combining the electricity demand of the charging piles.

[0072] It should be explained that when obtaining the total electricity demand at a toll station, the historical charging data of all charging piles in the toll station can be collected. The data content includes the charging power, charging time, charging frequency, charging amount, etc. of each charging pile in different time periods. According to the number of charging piles in the toll station, the charging mode of the charging piles (such as the charging behavior of different electric vehicles) and the charging data in different time periods, a charging demand matrix is constructed. The rows of the matrix represent different time periods (such as hourly data of each day), and the columns represent the charging demand of different charging piles. Each row represents the charging demand of all charging piles in a certain time period, and each column represents the charging demand of a certain charging pile in all time periods.

[0073] Non-negative matrix factorization (NMF) decomposes the charging demand matrix into two non-negative matrices, namely the basis matrix and the coefficient matrix. This decomposition helps to extract the potential charging patterns in the charging demand matrix:

[0074] Base matrix: contains potential charging modes, representing the charging demand of each charging pile under different charging modes; coefficient matrix: represents the charging intensity of each charging mode in different time periods.

[0075] The goal of NMF is to find the basis matrix (W) and the coefficient matrix (H) such that: X ≈ WH, where X represents the charging demand matrix, W represents the basis matrix, and H represents the coefficient matrix. In this way, the charging demand can be decomposed into several types of charging modes, and the charging scale of different modes can be calculated.

[0076] By analyzing each element in the coefficient matrix, the charging scale of each charging mode is determined. The charging scale can be defined as the total charging amount of the charging mode in a specific time period, or the load size when multiple charging piles use the charging mode at the same time. If the coefficient of a charging mode is large, it means that the charging demand of this mode in this time period is large, and more charging piles or higher power may be required. If the coefficient of the charging mode is small, it means that the charging demand of this mode is low, which may be an occasional demand for a specific charging pile.

[0077] The basis matrix obtained through NMF decomposition represents the characteristics of the charging mode. Each row represents a charging mode, and each column represents the charging demand of a charging pile. The coefficient matrix represents the intensity of each charging mode in different time periods. Each row represents a time period, and each column represents the intensity of a charging mode (i.e., the demand for that mode at that moment).

[0078] Multiply the corresponding rows and columns of the basis matrix and the coefficient matrix to obtain a new dimensional matrix. This matrix reflects the relationship between different charging modes and charging piles, and further helps capture the characteristics and trends of charging data. Each element of the dimensional matrix corresponds to a combination of a charging mode and a charging pile, reflecting the demand performance of a specific charging mode on a specific charging pile. The historical charging data (such as the historical charging power and duration of the charging pile) and the dimensional matrix are passed as input data to the graph convolutional neural network (GCN). GCN can capture spatial or temporal dependencies in graph structured data through convolution operations.

[0079] During the graph construction process, information such as the relationships between charging stations and changes in charging patterns is represented through the graph structure. In a graph convolutional neural network, nodes represent charging stations or charging patterns, and edges represent the relationships between them (such as similarities in charging behavior). Through the graph convolutional layer, the GCN model can capture effective information between charging patterns and charging stations, capturing potential patterns and trends. For example, GCN can help identify which charging stations have similar charging behaviors during similar time periods.

[0080] Evidence theory (also known as the Dempster-Shafer theory) can handle uncertainty by combining evidence from different sources (such as historical electricity consumption data and environmental factors) to obtain credibility about future electricity demand in living areas. By combining historical electricity consumption data with other influencing factors (such as weather and holidays), evidence theory can be used to infer and predict electricity demand in living areas. The key to evidence theory is to give weights to different data sources based on the relative importance of evidence and to synthesize the final prediction results through the Dempster synthesis rule.

[0081] Specifically, when obtaining the historical power consumption data of the living service area in the toll station and obtaining the power demand in the living area based on the historical power consumption development trend and evidence theory, the historical power consumption data of each sub-area in the living service area of the toll station can be obtained, and a power demand forecast set in each sub-area can be generated based on the historical power consumption data and seasonal properties; the basic probability distribution matrix is predicted based on the power demand forecast set and the properties of the power equipment in the sub-area, and the power demand forecast set is synthesized using evidence theory; based on the synthesis result, evidence conflict analysis is performed on the power demand forecast set to obtain the credibility function and plausibility function of the power demand forecast set, and the credibility function is converted into a probability distribution according to the probability conversion formula; the probability distribution of the power demand of each sub-area is obtained based on the distribution result, and the probability distribution and the basic probability distribution matrix are combined with the power demand of the sub-area, and the power demand of each sub-area is integrated to obtain the power demand in the living area.

[0082] It should be explained that in the process of obtaining electricity demand in the living area, it is necessary to collect historical electricity consumption data for each sub-area within the toll station's living service area. Each sub-area (such as restaurants, shops, rest areas, etc.) has independent electricity consumption data. This data may include electricity consumption in each sub-area at different time periods (such as hours, days, and months). This historical data is time series data, so the electricity consumption pattern of each sub-area can be analyzed based on time and seasonal trends. At the same time, electricity demand is significantly affected by seasonal factors. For example, air conditioning load increases in the summer, while heating load increases in the winter. Based on the seasonal changes in historical data, the electricity demand trend of each sub-area in different seasons can be inferred. For example, electricity demand in the summer may increase significantly due to the increased frequency of air conditioning use, while in the winter it may increase due to the use of heating equipment.

[0083] Combining historical data and seasonal factors, we predict the electricity demand of each sub-region in different seasons and time periods. Through time series analysis or other statistical methods (such as ARIMA and seasonal decomposition), we generate a forecast set containing the estimated electricity demand for different time periods and seasons. Different electrical equipment (such as air conditioners, lighting, and electric equipment) has different electricity consumption characteristics. At this stage, we need to generate a basic probability allocation matrix (BPA matrix) based on the properties of each electrical equipment in the sub-region (such as power consumption and frequency of use). The BPA matrix represents the initial probability distribution of the electricity demand forecast for each electrical equipment under given conditions.

[0084] The electricity demand forecast set for each subregion is combined with a basic probability distribution matrix to describe the probability distribution of different devices in each subregion during future electricity demand periods. This matrix reflects the likelihood and confidence of different forecast results. The electricity demand forecast sets for each subregion are synthesized using evidence theory. Evidence theory generates more accurate electricity demand forecasts by combining evidence from different sources (such as historical data, seasonal trends, and device characteristics). Specifically, the Dempster-Shafer synthesis rule is used to combine different evidence sets (forecast results) to produce a new synthesis result. The synthesis result is based on the synthesis of multiple different data sources and can effectively handle uncertainty and conflict. For each subregion, the synthesis rule combines the known forecast set with its confidence (confidence level) to output a new, comprehensive forecast result.

[0085] During the synthesis process, conflicts between different pieces of evidence may occur. The goal of conflict analysis is to identify and resolve conflicts between different pieces of evidence to ensure the accuracy of the synthesis results. By calculating the degree of conflict between different pieces of evidence, the relevance and credibility of each piece of evidence can be judged. If the conflict is too large, it may be necessary to adjust the weight of the evidence or reprocess the data.

[0086] The credibility function indicates the reliability of each prediction result and reflects the credibility of the prediction result after synthesis. The higher the credibility, the more reliable the prediction result. The credibility function is usually calculated by the support in the evidence theory. The support reflects the degree of support of the evidence for a certain prediction result. The plausibility function indicates the credibility of a certain prediction result (i.e., a measure of uncertainty) and is used to describe the possibility of a certain prediction result under the current evidence. The probability conversion formula is used to convert the credibility function into a probability distribution. The credibility function and the plausibility function are tools for uncertainty assessment and can be converted into specific probability distributions through the probability conversion formula. These distributions describe different possibilities of electricity demand. The core idea of the conversion formula is to convert the credibility function into a probability density function, thereby obtaining different probability distributions of electricity demand.

[0087] The probability conversion results are used to obtain the probability distribution of electricity demand for each sub-region. These probability distributions reflect the uncertainty and range of each sub-region's future electricity demand. Key statistics, such as expected value (i.e., the most likely electricity demand), variance (i.e., uncertainty), and confidence interval, are extracted from the probability distributions. These statistics help further optimize electricity demand forecasting and resource allocation. The probability distributions of electricity demand for each sub-region are combined with the basic probability allocation matrix and integrated into an electricity demand forecast for the entire living service area using a weighted average or composite rule. The electricity demand for each sub-region is then combined, taking into account the weight of each sub-region (such as area, number of devices, and importance), to ultimately obtain an electricity demand forecast for the entire living area.

[0088] Specifically, when constructing a power supply distribution model based on power demand and the dynamic power supply characteristics of energy equipment, determining the power supply distribution output of the energy equipment, and judging the remaining energy storage capacity of the energy equipment, the minimum expected frequency of power supply distribution of any power supply equipment can be analyzed based on the energy storage characteristics according to the power generation characteristics and energy storage characteristics of the energy equipment, and the minimum power generation objective function of any power supply equipment can be defined using the power generation characteristics; based on the naive Bayesian method, a maximum a posteriori hypothesis is made for the power demand of the toll station, and the maximum a posteriori hypothesis process is smoothed, and the dynamic distribution parameters are calibrated according to the processing results; the dynamic distribution parameters, the minimum expected frequency, and the minimum power generation objective function are combined to analyze the energy consumption of the energy equipment during the power supply process, and the objective function of the power supply distribution model is expressed in an octet manner based on the naive Bayesian method; the boundary conditions of the power supply distribution model are set based on the dynamic distribution balance of the energy equipment, and the constructed power supply distribution model is obtained in combination with the objective function; the power supply distribution output of any power supply equipment is determined using the power supply distribution model, and the remaining energy storage capacity of the energy equipment is obtained based on the difference between the energy storage capacity of the energy equipment and the power supply distribution output.

[0089] Preferably, the power distribution model is expressed as:

[0090] ;

[0091] Where F(t) represents the power distribution of the t-th power supply device, e represents energy consumption, α1 represents the probability that the power distribution output reaches high uniformity, α2 represents the probability that the power distribution output reaches low uniformity, υ represents the objective function of the power distribution model, β represents the minimum power generation target value of any power supply device, and T min represents the minimum expected frequency, and ε represents the dynamic allocation parameter.

[0092] It should be explained that in the process of building the power distribution model, it is necessary to analyze the minimum expected power supply frequency and target power generation that each device can provide within a given time based on the power generation and energy storage characteristics of the energy equipment:

[0093] Power generation characteristics: Each power supply device (such as solar power generation and wind power generation) has different power generation capabilities under different environmental conditions. This characteristic can be modeled by the relationship between the device's output power and time;

[0094] Energy storage characteristics: Energy storage equipment has limitations on maximum storage capacity and charge and discharge efficiency. The discharge and charging processes of the energy storage system need to take these characteristics into consideration to ensure that the maximum energy storage capacity is not exceeded.

[0095] Based on these characteristics, the minimum expected frequency that any power supply device can provide under specific conditions is analyzed, that is, at what frequency the device needs to provide power within a given time.

[0096] In order to ensure that energy equipment can provide a stable power supply without overloading, an objective function can be established based on the characteristics of the power generation equipment to calculate the minimum power generation target to ensure that the power generation during the power supply process is not less than the equipment's demand:

[0097] ;

[0098] Where, P gen Indicates the amount of electricity generated, E min Represents the minimum power generation requirement, A represents the time range, and minimizing the objective function will help find the optimal power supply under the power generation characteristics of the equipment.

[0099] The Naive Bayes classifier can infer the electricity demand of a toll booth based on known historical data (such as electricity demand history, equipment status, and weather conditions). Using the Maximum A Posteriori (MAP) method, the most likely electricity demand can be inferred based on known prior information:

[0100] Based on historical data (electricity demand) and equipment characteristics (power generation, energy storage, etc.), the Bayesian formula is used for inference. The electricity demand inferred by the maximum a posteriori hypothesis may be affected by noise and fluctuations. Therefore, this process is smoothed, such as using sliding average or Kalman filtering technology to eliminate noise, smooth data and improve prediction accuracy. The results obtained after smoothing can be used as the basis for dynamic allocation parameters for the next step of power supply allocation.

[0101] Based on the smoothed maximum a posteriori hypothesis results, the dynamic allocation parameters are calibrated. These parameters are used to represent the allocation rules during the power supply process to ensure that the system load and the power output of the power supply equipment can match the power demand. Specifically:

[0102] Based on historical data and electricity demand forecasts, the electricity demand for each time period and each sub-area is calibrated; based on the power generation characteristics and energy storage characteristics of the equipment, the power supply distribution parameters are dynamically adjusted to meet real-time needs.

[0103] Based on the naive Bayes classification results and dynamic allocation parameters, the objective function of the power distribution model can be expressed as an octet, which contains the following elements:

[0104] The eight-tuple of power generation, power demand, remaining energy storage, time period, minimum expected frequency, power differential (e.g., the difference between the device's power generation and demand), maximum energy storage capacity, and energy consumption cost describes the core goal of the power distribution model: how to reasonably allocate power generation to meet power demand in different time periods, while taking into account the device's power generation capacity, energy storage limitations, and cost.

[0105] When designing the objective function, it is necessary to ensure the dynamic balance of power distribution. That is, the difference between power generation and power demand does not lead to equipment overload or overcharging, thereby maintaining the stability and reliability of energy equipment. To ensure the feasibility and stability of the model, it is necessary to set appropriate boundary conditions. These conditions usually include:

[0106] Equipment capacity limitations: the maximum power generation and energy storage capacity of each power supply device;

[0107] Demand limit: The power demand cannot exceed the maximum power provided by the equipment;

[0108] Storage Limitation: The amount of energy stored in an energy storage device cannot exceed its maximum capacity.

[0109] According to the objective function, boundary conditions and dynamic allocation parameters, a power supply distribution model is finally constructed. The power output of any power supply device can be determined using the constructed power supply distribution model.

[0110] Specifically, when analyzing the amount of available energy at any given moment in an energy device, the energy generation rate is the amount of electricity generated by an energy device (such as solar energy, wind energy, etc.) per unit time, based on the combination of remaining stored energy and energy generation rate. For example, the energy generation rate of a solar power generation system depends on solar radiation intensity, weather conditions, and system efficiency; the energy generation rate of a wind power generation system depends on wind speed and generator efficiency. The energy generation rate is calculated as p gen (r)=E produce (r) / Δr,p gen (r) represents the energy generation rate at time r, E produce (r) represents the amount of electricity generated per unit time, such as the amount of electricity generated per hour.

[0111] The amount of available energy refers to the remaining energy that can be provided by energy equipment while meeting the electricity needs of charging stations and living service areas. Its calculation process includes the following steps:

[0112] The electricity demand of the charging piles is added together with the electricity demand of the living service area to obtain the overall electricity demand. Based on the total electricity demand, the amount of energy required within a specific time period (such as 1 hour, 1 day, etc.) is calculated. If there are multiple energy devices in the system (such as solar power generation, wind power generation, energy storage batteries, etc.), the required energy amount needs to be calculated based on the output characteristics of each device.

[0113] The amount of available energy is the result of combining the remaining stored energy and the energy generation rate, as shown in the following formula:

[0114] ;

[0115] Where, E movable Indicates the amount of movable energy, E remaining Indicates the remaining stored energy, Indicates the total energy generated by the energy equipment in the time period T, P totaldemand Indicates the amount of energy required to meet the electricity demand of charging stations and living service areas.

[0116] If the amount of movable energy is greater than 0, it means that the energy equipment can provide the remaining movable energy for sale or storage after meeting the electricity demand; if the amount of movable energy is 0 or a negative value, it means that the storage capacity and generation rate of the energy equipment are not enough to meet the electricity demand, and it may be necessary to purchase electricity from the power grid or dispatch other backup energy equipment.

[0117] Specifically, when combining the movable energy amount with the power purchase and sales agreement to process the excess energy sale transaction, and determining the sale time and sale quantity in the excess energy sale transaction process based on the real-time electricity price, the movable energy amount can be combined with the power purchase and sales agreement to define the excess energy sale rules, and connected to the power company's smart meter system to automatically record and upload the output data of the excess energy; obtain historical electricity price data, and reconstruct the phase space of the historical electricity price data time series, analyze the phase point of the historical electricity price at any time point, and the closest point of the phase point; obtain the distance between the phase point and its closest point, and traverse all phase points in the phase space and the distance between the corresponding closest points to obtain a dynamic evolution law, and analyze the evolution time series of the electricity price based on the dynamic evolution law; predict the real-time electricity price at any time based on the evolution time series, and determine the time and sale quantity of the excess energy sale transaction based on the high or low real-time electricity price.

[0118] It should be noted that when determining the timing and quantity of excess energy sales transactions, it is necessary to combine the available energy (such as the remaining power of the energy storage system or the amount of renewable energy generation) and the power purchase and sale agreement to define the rules for the sale of excess energy:

[0119] Available energy: refers to surplus energy that can be sold, such as electricity stored in energy storage devices or excess electricity generated from renewable energy devices (such as solar and wind power);

[0120] Power purchase and sales agreement: It is a contractual agreement between the power company and the user, which stipulates the basic conditions, unit price, transaction time, etc. for power purchase and sale.

[0121] Based on these contents, define the rules for selling excess energy, including:

[0122] Maximum amount of energy sold per transaction;

[0123] The price and time window for selling electricity (based on the power company's regulations and grid demand);

[0124] Trading restrictions on electricity sales (e.g., whether sales are allowed within a certain time period, upper limit on the amount of electricity that can be sold, etc.);

[0125] These rules are connected to the power company's smart meter system, allowing excess energy output data to be automatically recorded and uploaded, ensuring real-time and accurate transactions.

[0126] In order to predict future real-time electricity prices, it is necessary to conduct an in-depth analysis of historical electricity price data. The specific steps are as follows:

[0127] By obtaining historical electricity price data from power companies or related data sources, this data is typically time series data, representing electricity price fluctuations over a period of time (e.g., hourly electricity prices). Phase space reconstruction is a method of nonlinear time series analysis used to map time series data into a high-dimensional space to reveal the dynamics within it. Phase space reconstruction is performed based on historical electricity price data. The specific method is as follows:

[0128] Selecting the delay time and embedding dimension: First, select the delay time and embedding dimension for time series reconstruction. These two factors determine how to extract meaningful features from the time series. Using the delay time and embedding dimension, historical electricity price data is mapped into a high-dimensional phase space, yielding corresponding "phase points." Each point in the phase space represents the state of the electricity price data at a specific point in time.

[0129] The phase point is the position of the historical electricity price in the phase space, which represents the dynamic characteristics of the electricity price change; the closest point is the point in the phase space that is closest to the current phase point, which indicates the emergence of similar states in the electricity price time series.

[0130] By analyzing historical electricity price data, we can calculate the distance between any phase point and its closest point, generating a distance matrix. This distance matrix reflects the similarity between electricity price states and helps us understand the patterns and regularities of electricity price changes.

[0131] By reconstructing the phase space and calculating the distances between phase points, we can analyze the dynamic evolution of historical electricity prices. Specifically, by traversing all phase points and their closest points in the phase space and calculating the distances between phase points, we can reveal the dynamic laws of electricity price evolution. At the same time, based on the distance matrix, we can analyze the evolution time series of electricity prices and find out the patterns and trends of electricity price changes, such as the frequency and amplitude of electricity price fluctuations; the cyclical and trend changes in electricity prices; and the sudden change points of electricity prices. These analyses can help predict the future trend of electricity prices.

[0132] Based on the time series of electricity price evolution, time series prediction methods (such as ARIMA and LSTM neural networks) are used to predict the real-time electricity price at a certain point in the future. The goal of this step is to predict the future trend of electricity prices based on the dynamic evolution of historical electricity prices. Based on the predicted real-time electricity price, a strategy for selling excess energy can be formulated:

[0133] If the real-time electricity price is high, it means that the demand in the electricity market is large. At this time, selling excess energy can generate higher profits. Therefore, during periods of high electricity prices, priority should be given to selling excess energy. If the electricity price is low, the profits from selling excess energy are low, and you can choose to delay the sale, or decide whether to sell it based on the system's energy storage capacity.

[0134] The amount of electricity to be sold is determined based on the real-time electricity price and the remaining energy of the energy storage device. For example, if the electricity price is at its peak, you can choose to sell as much as possible; if the electricity price is low, you can consider selling a portion of it, or not selling it at all. Finally, based on the connection with the power company's smart meter system, automated transaction processing can be achieved.

[0135] In order to facilitate understanding of the above technical solutions of the present invention, the working principle or operation mode of the present invention in actual process is described in detail below.

[0136] Step 1: Predict the electricity demand in the toll station;

[0137] (1) Historical charging data of charging piles:

[0138] Assume that there are 10 charging piles in the toll station. The charging power of each charging pile is 22kW, the charging time is 1 hour, the charging frequency is 2 times per hour, and the charging capacity is 44kWh (charging power × charging time). The daily charging demand matrix size is 24*10, which represents the charging demand of each charging pile within 24 hours.

[0139] (2) Historical power consumption data of living service areas:

[0140] Assume that the living service area includes three sub-areas: restaurant, store, and rest area. The historical power consumption data of each sub-area is collected (for example, the daily power consumption of the restaurant is 300 kWh, the store is 150 kWh, and the rest area is 100 kWh). The collected power consumption data is a 24x3 matrix, which represents the power demand of each sub-area within 24 hours.

[0141] (3) Charging demand forecast based on charging pile data:

[0142] By recording data from the past 30 days, we can obtain a 30*24*10 charging demand matrix, which contains the charging demand of each charging pile in different time periods. By decomposing the charging demand matrix, we can obtain the basis matrix W (charging mode) and the coefficient matrix H (intensity of time period).

[0143] Basis matrix W: Each column represents the demand intensity of a charging pile under a specific charging mode. For example, the first column may indicate that more power is needed during peak charging period.

[0144] Coefficient matrix H: Each row represents the charging pattern intensity in each time period. For example, 7 to 9 pm may be the peak period for electricity consumption.

[0145] The dimension matrix calculated by the basis matrix and the coefficient matrix can capture the relationship between the charging mode and the charging data, which serves as the input of the graph convolutional neural network (GCN).

[0146] (4) Predicting electricity demand in living service areas based on evidence theory:

[0147] Based on historical data, we analyze the seasonal electricity demand in living areas. For example, the air conditioning load in restaurants may increase in summer, and the lighting load in stores varies with the seasons. By analyzing historical data and seasonal factors and combining evidence theory to integrate different prediction results, we can obtain the electricity demand forecast for each sub-area.

[0148] Combining the electricity demand of charging piles and living service areas, the total electricity demand of the toll station is obtained.

[0149] Charging demand: 10 charging stations, charging pattern and intensity predicted by NMF, assuming total charging demand is 500kWh / day;

[0150] Demand in living service areas: 300kWh / day for restaurants, 150kWh / day for shops, 100kWh / day for rest areas, with a total demand of 550kWh / day.

[0151] Total electricity demand: 500kWh + 550kWh = 1050kWh / day.

[0152] Step 2: Build a power supply distribution model;

[0153] (1) Analyze the characteristics of energy equipment:

[0154] Assume that two energy devices are used:

[0155] Photovoltaic power generation system: maximum power is 50kW, average power generation is 400kWh / day;

[0156] Wind power generation system: maximum power is 30kW, average power generation is 300kWh / day;

[0157] Energy storage equipment: The maximum energy storage capacity is 500kWh, and the current storage capacity is 200kWh.

[0158] (2) Power supply distribution model:

[0159] Through naive Bayesian classification and dynamic allocation parameter calibration, the current electricity demand and power generation capacity are analyzed. Assuming a 24-hour time period, the hourly power generation and energy storage allocation is determined based on the charging demand pattern predicted by the NMF and the needs of the living service area. For example, during the peak charging period (7-9 pm), the output of solar and wind power is increased.

[0160] Step 3: Calculate the amount of movable energy;

[0161] Assume that the remaining energy storage capacity is 200kWh in a certain period of time; the energy generation rate is 20kW for solar power and 15kW for wind power.

[0162] Charging demand: Assume that the charging demand during this period is 300kWh and the demand in the living service area is 150kWh.

[0163] According to the power generation of energy equipment: P gentotal = (20kW + 15kW) × 1hr = 35kWh; the calculation of movable energy is: E movable =200kWh (remaining energy storage) + 35kWh (generated energy) −450kWh (total demand) = −215kWh. Since the amount of movable energy is negative, it means that the current energy storage and generated energy are not enough to meet the electricity demand.

[0164] Step 4: Excess energy sales transaction;

[0165] Assume that the agreement stipulates that a maximum of 100 kWh can be sold per hour at a price of 0.15 ¥ / kWh. Through phase space reconstruction and time series analysis of historical electricity price data, it is assumed that the future electricity price will be 0.20 ¥ / kWh. At this time, the price is higher and the excess energy can be sold first. Since the current movable energy amount is negative, there is no available electricity to sell.

[0166] During the power distribution process, if the available energy of the energy equipment is greater than 0, the system will automatically start the transaction process to sell the excess electricity. If the available energy is less than 0, it may be necessary to purchase electricity from the grid or dispatch backup energy. The analysis and prediction of real-time electricity prices help choose the optimal time to sell and maximize economic benefits.

[0167] Step S2: predict the load demand in the toll station, adjust the supply mode of the geothermal heat pump based on the load demand, and determine the heat output of the geothermal heat pump in combination with the real-time temperature in the toll station and the variable frequency control technology.

[0168] In one embodiment, predicting the load demand within a toll station, adjusting the supply mode of the geothermal heat pump based on the load demand, and determining the heat output of the geothermal heat pump in combination with the real-time temperature within the toll station and variable frequency control technology include:

[0169] Obtain historical heating and cooling data within the toll station, and combine seasonal factors with edge distribution technology to predict the heating or cooling load demand of the toll station in any time period;

[0170] determining a temperature requirement within the toll station according to the load demand, determining a supply mode of the geothermal heat pump based on the temperature demand, and adjusting the supply mode of the geothermal heat pump according to the determination result;

[0171] Adjust the supply of geothermal heat pumps based on the real-time temperature and load demand within the toll station, and calculate the optimal operating frequency of the geothermal heat pumps by combining variable frequency control technology with the characteristics of the geothermal heat pumps.

[0172] The heat output result of the geothermal heat pump is output based on the optimal operating frequency and supply, and the optimal operating frequency is adjusted according to real-time feedback to optimize the operating efficiency of the geothermal heat pump.

[0173] Specifically, when obtaining historical heating and cooling data in a toll station and combining seasonal factors with marginal distribution technology to predict the heating or cooling load demand of the toll station in any time period, the historical heating and cooling data can be obtained based on the historical operation data of the toll station, and an estimated sample containing the two variables of heating and cooling can be constructed based on the obtained results, and the distribution function value of the estimated sample under seasonal factors can be obtained by non-parametric estimation method; a conditional matrix is constructed based on the marginal distribution function value and the estimated sample, and the conditional matrix is used to predict the probability of each data value appearing in the estimated sample and the corresponding marginal value; based on the upper and lower bounds of the pre-set load demand interval, and combining the probability and marginal value, the expected probability of the data value within the load demand interval is analyzed, and the marginal distribution matrix of the data value is obtained using the expected probability; an inverse operation is performed on the marginal distribution matrix to obtain the demand forecast interval for heating and cooling of the toll station, and the heating or cooling load demand of the toll station is determined from the demand forecast interval according to the time period.

[0174] Among them, the calculation formula for the probability of data value occurrence and marginal value is:

[0175] ;

[0176] Where S i represents the probability of the i-th data value appearing in the estimated sample, T irepresents the distribution function value of the i-th data value, P represents the characteristic value of the estimated sample under seasonal factors, E i represents the edge value of the i-th data value, H(i,m) represents the joint probability mass function of the data value i and the conditional matrix m, Represents the load size of data value i in the mth conditional matrix.

[0177] It should be noted that when predicting the heating or cooling load demand within a toll station, it is necessary to collect historical heating and cooling data of the toll station. This data usually comes from the heating and air conditioning systems within the toll station and may include:

[0178] Heating load data: indicates the heating demand at the toll station in different time periods (such as daily hourly data); cooling load data: indicates the cooling demand at the toll station in different time periods. These data include demand fluctuations in different time periods under multiple seasons (such as winter and summer), which can reflect the impact of seasonal changes on heating and cooling loads.

[0179] Based on the historical heating and cooling data of toll stations, the two variables of heating and cooling are constructed into an estimated sample, that is, each pair of data contains the heating and cooling demand. The heating demand and cooling demand in the same time period can be regarded as a two-variable data sample.

[0180] For example, on a winter day, the heating demand is 30kW and the cooling demand is 0kW; on a summer day, the heating demand is 0kW and the cooling demand is 25kW. In this way, a multidimensional sample set can be created, which can be used in the subsequent nonparametric estimation process.

[0181] Nonparametric estimation methods, such as kernel density estimation, are used to estimate the distribution function of sample data. This method does not rely on specific distributional assumptions about the data, but instead estimates its probability density function based on the data itself. For example, if we want to estimate the distribution of heating and cooling demand, nonparametric estimation methods will generate marginal distribution functions of heating and cooling demand based on the distribution characteristics of historical data. This means we can obtain probability density estimates of heating and cooling demand over different time periods.

[0182] After obtaining the distribution function value of the estimated sample, the next step is to construct a conditional matrix based on the relationship between the data. This matrix describes the distribution of another variable when a certain variable is known. For example:

[0183] The heating demand is a known condition, and the cooling demand is the variable to be estimated. In this case, the conditional matrix reflects the probability distribution of the cooling demand value under a given heating demand value. Through the relationship between the marginal distribution and the joint distribution, the probability of cooling demand occurring under specific conditions (such as a specific heating demand) can be calculated.

[0184] Assume that heating or cooling load demands have a certain range. For example, heating demand may range from 10kW to 50kW, while cooling demand may range from 0kW to 30kW. Based on the known marginal distribution, by calculating the probability of each data value occurring within different load demand intervals (such as 10kW to 50kW), we can obtain the expected probability, that is, the probability of heating or cooling demand most likely occurring within that interval. The expected probability helps to estimate the probability of heating or cooling demand falling within a specific load interval during a certain period of time. For example, in colder seasons, heating demand may be more likely to fall within the high load range.

[0185] By analyzing expected probabilities and marginal values, the marginal distribution matrix can describe the probability distribution of heating and cooling demand in different time periods. For example, the marginal distribution of heating demand may show different distribution characteristics of heating demand in different time periods (such as morning, evening or night); the marginal distribution of cooling demand may reflect the demand patterns during the day and night in summer. The marginal distribution matrix provides the predicted distribution of load demand at the toll station in different time periods through probability calculation.

[0186] The inverse operation process is to obtain the actual load demand forecast interval from the marginal distribution matrix. Assuming that the expected probability of heating demand in a specific time period is obtained, it can be converted into an actual demand forecast interval through the inverse operation. This process is:

[0187] Based on the calculated marginal distribution, we can identify the most likely range for heating or cooling load demand within a specific time period. For example, if the predicted heating load demand for a specific time period is between 15kW and 40kW, this range provides a reference value, indicating that the actual load demand during that time period has a high probability of falling within this range.

[0188] Based on the combination of the demand forecast interval and time period, the heating or cooling load demand of the toll station is finally obtained. For example: during a certain period in winter, the forecast range of the heating load demand is 15kW to 40kW. Combined with actual weather and historical data, the heating demand for a certain period may be finally determined to be 25kW. Similarly, during a certain period in summer, the cooling load demand may be predicted to be 20kW.

[0189] Therefore, based on historical data and seasonal factors, the heating and cooling load demand of toll stations is accurately predicted. The distribution of sample data is obtained through non-parametric estimation method. Combined with marginal distribution and conditional matrix, the expected probability in the demand interval is analyzed, and the demand forecast interval is obtained through inverse operation. Finally, the accurate heating or cooling load demand is determined. This method combines statistics, probability theory and non-parametric estimation technology to provide a scientific load demand forecasting tool for energy management of toll stations.

[0190] At the same time, when combining the real-time temperature and variable frequency control technology in the toll station to determine the heat output of the geothermal pump, it is necessary to calculate the corresponding temperature demand based on the load demand of the toll station. The load demand usually represents the required energy load, which is specifically manifested as the heat or cooling capacity required by the heating (or cooling) system.

[0191] In the case of heating, the load demand is closely related to the indoor temperature difference (the difference between the indoor temperature and the outside temperature). For example, when the outside temperature is lower than the set indoor temperature, the heating system needs to provide more heat.

[0192] In the case of cooling, the load demand is related to the difference between the indoor and outdoor temperatures, as well as the heat load in the room (e.g., heat generated by lighting and equipment operation).

[0193] Based on the load demand, the temperature demand can be estimated by the following formula: Q heat =c×(T inside -T outside ), where: Q heat represents the required heat (unit: kW or kWh); c represents the coefficient related to the thermal insulation performance and thermal conductivity of the toll station; T inside Indicates the target indoor temperature; T outside Represents the external ambient temperature. Through the relationship, determine the target temperature inside the toll station to meet the load demand.

[0194] When determining the supply mode of a geothermal heat pump based on temperature requirements, a geothermal heat pump utilizes the constant temperature properties of the subsoil to exchange heat. Based on the target temperature, the geothermal heat pump's supply mode can be determined: heating mode, where the geothermal heat pump draws heat from the subsoil and transfers it to the building to maintain the indoor temperature; cooling mode, where the geothermal heat pump draws heat from the building and releases it into the subsoil to lower the indoor temperature.

[0195] The geothermal heat pump's supply mode can be matched to the temperature demand and the pump's load capacity. For example, if the target temperature demand is high, the geothermal heat pump will provide a higher heat output in heating mode. Conversely, if the demand is low, the geothermal heat pump will operate at a lower load level. In winter heating mode, the geothermal heat pump's temperature control may need to adjust the supply water temperature between 35°C and 45°C to accommodate different heating demands. For higher heating demands, the pump's output capacity may need to be increased. In summer cooling mode, the geothermal heat pump's output needs to be adjusted inversely to maintain a lower temperature differential.

[0196] The geothermal heat pump's supply is adjusted based on real-time indoor temperature and load demand. To optimize energy efficiency and comfort, the geothermal heat pump's workload needs to be dynamically adjusted based on real-time temperature data and load demand. Temperature sensors installed in toll booths monitor indoor temperatures in real time. This data is fed into the control system, compared with the target temperature, and used to adjust the geothermal heat pump's operating status.

[0197] Winter heating: If the indoor temperature is lower than the set target temperature and the load demand increases, the geothermal heat pump will need more heat output to quickly restore the indoor temperature. If the indoor temperature is close to the set value, the geothermal heat pump will reduce the output to maintain a stable indoor temperature.

[0198] Summer cooling: In cooling mode, as the outside temperature changes, the load demand will fluctuate, and the output of the geothermal pump will be adjusted in real time according to these changes.

[0199] Variable Frequency Drive (VFD) technology regulates motor speed based on load demand. In geothermal heat pump systems, VFD adjusts the pump's operating frequency, thereby regulating heat output, based on load demand. Based on the difference between the indoor temperature and the target temperature, the control system calculates an operating frequency appropriate for the current load. When the load demand is low, the geothermal heat pump operates at a lower frequency, outputting less heat. When the load demand is high, the operating frequency increases, increasing the heat output. The relationship between operating frequency and heat output is that a geothermal heat pump's heat output is roughly proportional to its operating frequency. By optimizing the operating frequency, the system can achieve a balance between energy conservation and load adaptability.

[0200] The heat output of a geothermal heat pump can be estimated approximately by the following relationship: Q output =K heat ×f pump Where: Q output Indicates the heat output of the geothermal pump; K heat represents a constant related to the characteristics of the pump; f pump It indicates the operating frequency of the geothermal heat pump. With the adjustment of the frequency, the system can flexibly adjust the heating amount according to the actual load demand.

[0201] By continuously monitoring temperature, load demand, and system performance, real-time feedback is used to adjust the operating frequency of the geothermal heat pumps, thereby optimizing their operating efficiency. Real-time temperature and load data are fed back to the geothermal heat pump control system through sensors and the control system. Based on this feedback, the control system dynamically adjusts: increasing or decreasing the frequency of the geothermal heat pumps and adjusting heat output to respond to temperature changes.

[0202] Based on real-time feedback, the operating frequency of the geothermal heat pump will be optimized according to the following principles:

[0203] Reduce frequency when load demand is low, reducing energy consumption;

[0204] Increase frequency when load demand is high to ensure temperature requirements are met.

[0205] This optimization strategy is achieved through variable frequency control technology, ensuring that the geothermal heat pump can operate at optimal efficiency under different operating conditions and minimize energy waste.

[0206] Therefore, based on real-time temperature and load requirements, combined with variable frequency control technology and geothermal heat pump characteristics, the supply mode and operating frequency of the geothermal heat pump can be flexibly adjusted to ensure that the heating (or cooling) load is met while optimizing energy efficiency.

[0207] In step S3, the power distribution output results, the excess power sale transaction results and the heat output results of the geothermal pump are combined as an operation process optimization strategy to optimize the multi-energy complementary zero-carbon construction process of the toll station.

[0208] In one embodiment, when combining the power distribution output results, excess power sales transaction results, and geothermal pump heat output results as an operation process optimization strategy to optimize the multi-energy complementary zero-carbon construction process of a toll station, data from various energy systems can be integrated into a unified platform for real-time monitoring and management, including:

[0209] Power distribution output: data from renewable energy generation systems such as photovoltaic and wind power, indicating the energy supply situation in each time period;

[0210] Excess power sales transaction results: Based on the difference between power supply and demand, the transaction volume and price of excess power are calculated;

[0211] Heat output results of geothermal heat pump: Changes in real-time temperature demand and load demand determine the working status and heat output of the geothermal heat pump.

[0212] This information is collected and processed through smart sensors, data acquisition systems, and real-time data analysis platforms to ensure that the system always maintains accurate control of energy supply and demand.

[0213] The goal of a multi-energy complementary system is to improve energy efficiency and reduce carbon emissions by rationally configuring different energy systems (such as photovoltaic, wind, geothermal, etc.). The specific steps are as follows:

[0214] Using historical load demand data and weather forecast models, we can predict future load demands for each energy system. Based on real-time power supply and load demand data, we can optimize the matching of different energy sources. For example, if solar and wind power are sufficient, they can be used to meet the heating or cooling needs of a building. The heat output of the heat pump can be coordinated with the power supply (especially from renewable energy sources) to ensure that the load demand of the geothermal heat pump is met and that green electricity is used as much as possible.

[0215] In a multi-energy complementary system, ensuring the stability of power supply is key, while also maximizing the sale of excess power to achieve economic benefits. Battery energy storage systems, among other means, can be used to store excess renewable electricity to address power shortages during peak demand periods or unstable weather. Dynamic decisions about whether to sell excess power can be made based on power demand forecasts and real-time electricity prices. For example, when power demand is low and prices are high, more power can be sold to maximize economic benefits. When excess power is stored in the energy storage system, it needs to be released at the appropriate time to balance the load and avoid power system instability caused by excessive storage or sales.

[0216] The heat output of geothermal heat pumps needs to be adjusted based on demand and energy availability to ensure comfort while maximizing energy efficiency. The operating frequency of geothermal heat pumps is dynamically adjusted based on real-time power supply conditions and building load demands. If electricity supply is sufficient and price is low, geothermal heat pump output is prioritized to meet heating or cooling needs. If electricity demand is high, the operating frequency can be appropriately reduced. Climate changes have a direct impact on building temperature requirements, so it is necessary to incorporate meteorological data into load forecasting models in real time. For example, if cold weather is predicted in advance, geothermal heat pumps can be adjusted in advance to ensure adequate heating.

[0217] The core goal of the entire optimization process is to maximize the use of renewable energy by flexibly dispatching various energy systems, rationally allocating power supply and demand, and combining the heating and cooling load requirements of geothermal pumps to ultimately achieve the multi-energy complementarity and zero-carbon goals of the toll station.

[0218] like Figure 2 As shown in the overall architecture diagram of the method for building a multi-energy complementary zero-carbon toll station, the control of the toll station includes photovoltaic power generation modules, wind power generation modules, energy storage modules, power consumption, and intelligent control systems. In the implementation of photovoltaic power generation modules in power supply applications, this embodiment adopts high-efficiency monocrystalline silicon photovoltaic modules to ensure the maximum light energy conversion efficiency in a limited space. The power output range of the modules can be flexibly configured according to the actual needs of the toll station. The photovoltaic modules are installed on the roof of the toll station or the ceiling of the parking lot, and an adjustable angle bracket structure is used to ensure that the inclination angle of the modules matches the local latitude to maximize light absorption.

[0219] like Figure 3 and Figure 4 As shown in the photovoltaic power generation module structure diagram and the wind power generation module structure diagram, the specific structure of the photovoltaic power generation module includes photovoltaic components, inverters, DC / AC converters, energy storage systems, and control systems; the specific structure of the wind power generation module includes wind turbines, generators, control systems, and energy storage modules; the photovoltaic power generation system converts DC power into AC power through an inverter and connects it to the internal power grid of the toll station. The inverter is equipped with an intelligent grid-connected control function, which can monitor the power generation status of the photovoltaic system in real time and automatically adjust the grid-connected output to adapt to the power demand of the toll station. At the same time, it selects the appropriate Vertical or horizontal axis wind turbines, the blades of the generator are made of composite materials with high strength and corrosion resistance, suitable for long-term outdoor use. The wind turbine is installed on a reinforced tower, and the tower foundation adopts concrete cast-in-place pile technology to ensure the stability of the generator under severe weather conditions. The tower height is optimized according to local wind speed conditions to improve wind capture efficiency. The wind power generation system is equipped with an intelligent control unit that can automatically adjust the operating status of the generator according to wind speed changes to optimize power generation efficiency and extend equipment life. The control system is linked with the energy management module of the toll station to adjust the output power of wind power generation in real time.

[0220] The energy storage and conversion power module uses lithium-ion batteries as its primary energy storage device. Lithium-ion batteries are an ideal energy storage option due to their high energy density, long cycle life, and stable performance. The battery capacity is designed based on the toll station's daily power consumption and peak and valley power demands. The energy storage system is equipped with an advanced battery management system (BMS), which monitors key parameters such as battery voltage, current, and temperature in real time to ensure the battery pack operates within safe ranges. The BMS also provides a balanced charging function to prevent overcharging or over-discharging, thereby extending battery life. The energy storage system is connected to the toll station's internal power grid via a bidirectional inverter. The bidirectional inverter not only converts the DC power from the energy storage batteries into AC power for the toll station but also stores excess power in the batteries when there is excess photovoltaic or wind power generation. Furthermore, the inverter automatically dispatches power output from the photovoltaic, wind, and energy storage systems based on real-time energy supply and demand, ensuring a balanced power supply at the toll station and prioritizing renewable energy to reduce reliance on the grid.

[0221] The toll stations proposed in this embodiment are equipped with both fast and standard charging stations to meet the charging needs of different types of new energy vehicles. Fast charging stations utilize high-power DC charging technology, enabling high-capacity charging for vehicles in a short period of time. Standard charging stations are suitable for vehicles parked for extended periods. The charging stations are connected to the toll station's internal power grid via independent power interfaces equipped with smart meters that monitor power consumption in real time during charging and upload the data to the energy management module. The power interfaces also include load management capabilities to prevent grid overloads caused by large-scale charging.

[0222] The intelligent charging management system dynamically allocates the output power of charging piles based on the real-time power load within the toll station, prioritizing the normal operation of other key equipment at the toll station. The system also supports remote control, allowing administrators to view and adjust the operating status of each charging pile in real time via mobile terminals. The charging piles are equipped with a touchscreen user interface, support multiple payment methods (such as mobile payments and IC cards), and display real-time charging progress and cost information. The system integrates big data analysis capabilities, enabling predictions and optimization based on historical charging data to enhance the user experience.

[0223] This embodiment integrates the living and service areas within the toll station (such as lounges, restaurants, and shops) with an energy management system, ensuring that these areas are powered by renewable energy, with priority given to renewable energy. The power supply system includes built-in overload protection to ensure stable power even during peak demand periods. The living area lighting system utilizes energy-saving LED lamps, coupled with an intelligent control system that automatically adjusts brightness based on natural light intensity and occupant activity. Home appliances (such as air conditioners and refrigerators) are equipped with smart sockets that automatically shut off when idle, further reducing energy consumption.

[0224] Each type of equipment in the living service area is equipped with an independent energy consumption monitoring device to record power usage in real time. The energy consumption monitoring system is linked to the central energy management module, which can identify high-energy-consuming equipment and provide energy-saving suggestions. The system continuously optimizes the energy usage pattern of the living service area through big data analysis and machine learning algorithms. Through the real-time feedback mechanism, the system can automatically adjust the working mode of certain equipment or remind administrators to intervene manually to ensure that energy consumption is always kept at the lowest level.

[0225] The photovoltaic and wind power generation systems proposed in this embodiment are both equipped with grid-connected inverters, which can convert excess electrical energy into alternating current that meets grid standards. The grid-connected inverters support multiple grid-connected protocols and can seamlessly interface with the grid-connected requirements set by local power grid companies. The grid-connected inverters have built-in anti-islanding effect protection devices to ensure automatic disconnection in the event of a grid failure, avoiding unnecessary impact and risks to the grid. The inverters are also equipped with multiple protection mechanisms such as overvoltage, undervoltage, overcurrent, and short circuit to ensure the safety of the grid-connected process.

[0226] This embodiment integrates an electricity trading management module. By connecting to the local power company's smart meter system, it automatically records and uploads excess power output data. The system can automatically calculate and determine the time and quantity of electricity sales based on real-time electricity prices or signed power purchase and sales agreements, thereby maximizing economic benefits.

[0227] According to the actual operation of the toll station, the electricity sales contract can be dynamically adjusted. For example, the proportion of electricity sales can be increased in seasons with large photovoltaic or wind power generation. Conversely, when the power generation is insufficient, electricity sales can be reduced or priority can be given to meeting the electricity demand within the station. The system also supports negotiations with power companies to establish customized electricity purchase and sales contracts to ensure the long-term stability of revenue. To ensure the power quality during the power sales process, the present invention optimizes the design of the power transmission lines, adopts low-loss and high-efficiency cable materials, and sets a reasonable line layout to reduce energy loss during the transmission process. The system is equipped with a power quality monitoring device that can monitor and adjust key parameters such as power frequency and voltage in real time to ensure that the power output to the power grid meets national or regional power quality standards. The monitoring data will be fed back to the central control system in real time. If an abnormal situation is found, the system will automatically adjust the output or issue an alarm prompt.

[0228] like Figure 5 As can be seen from the geothermal heating and cooling module shown, the specific structure of the shallow + medium and deep geothermal heating and cooling module includes an energy storage module, a geothermal well, a geothermal pump, and a control system. In this embodiment, a shallow geothermal well is arranged near the toll station, and shallow geothermal resources are collected through geothermal pump technology. Shallow geothermal wells are usually less than 100 meters deep and use the stable temperature below the surface to heat and cool the toll station buildings. In areas where conditions permit, toll stations can further utilize medium- and deep-layer geothermal resources. The depth of medium- and deep-layer geothermal wells can reach 1,000 meters or deeper, which can provide a higher temperature difference for more efficient heating or cooling. Through reinjection technology, the sustainable use of geothermal resources is ensured. Geothermal energy is used to achieve heating and cooling through the geothermal pump system. The geothermal pump system intelligently switches the heating or cooling mode according to the load demand of the building to provide a constant temperature indoor environment. The system integrates variable frequency control technology and can adjust the heat output in real time according to the indoor temperature to improve energy utilization efficiency. The geothermal heating and cooling system is linked with the energy management module of the toll station to adjust the intensity of heating and cooling according to seasonal changes and actual needs to ensure the comfort of the indoor environment while achieving optimal energy utilization.

[0229] Furthermore, through the comprehensive use of multiple technologies such as photovoltaic power generation, wind power generation, energy storage and conversion, geothermal heating and cooling, new energy vehicle charging, and the sale of excess electricity to the grid, a self-sufficient, energy-cycling, and energy-efficient zero-carbon toll station has been built. Through the organic integration and intelligent management of multiple technologies, the toll station can not only achieve self-balance and independent supply of energy, but also sell excess renewable energy electricity to further improve economic benefits.

[0230] Photovoltaic and wind power generation technologies provide the toll station's primary power source, with an energy storage system regulating power supply stability. Geothermal energy provides efficient heating and cooling for the toll station, ensuring the building's temperature control requirements. The energy management system monitors and dynamically schedules the production, storage, and use of various energy sources in real time, achieving optimal energy distribution and maximizing energy efficiency. By selling excess electricity to the grid, the toll station not only achieves self-sufficiency but also generates additional revenue and reduces operating costs. Intelligent management of the power sales system ensures transparent and efficient electricity trading, thereby achieving zero carbon emissions for the toll station. By fully utilizing renewable energy and intelligent management technologies, reliance on traditional fossil fuels is reduced, promoting environmental protection and sustainable development goals.

[0231] Through the above detailed technical solution, this embodiment effectively achieves the invention purpose of building a zero-carbon toll station. It not only realizes the comprehensive utilization and management of energy in technology, but also ensures efficient operation and improved economic benefits through intelligent systems.

[0232] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A multi-energy complementary zero-carbon toll station construction process optimization method based on energy distribution, characterized in that: include: Predict electricity demand within the toll station, obtain the power distribution output of energy equipment based on the power demand, and conduct excess power sales transactions based on the power distribution output results and power purchase and sales agreements; Predict the load demand within the toll station, adjust the geothermal heat pump supply mode based on the load demand, and determine the heat output of the geothermal heat pump by combining the real-time temperature within the toll station with variable frequency control technology; The power distribution output results, excess power sales transaction results and geothermal pump heat output results are combined as an operation process optimization strategy to optimize the multi-energy complementary zero-carbon construction process of the toll station; The method of predicting electricity demand in a toll station, obtaining the power distribution output of energy equipment based on the power demand, and conducting a transaction for selling excess electricity according to the power distribution output and the power purchase and sales agreement includes: Obtain historical charging data of charging piles in toll stations and historical power consumption data of living service areas, and combine evidence theory with convolutional neural network technology to predict power demand in toll stations; Build a power distribution model based on power demand and the dynamic characteristics of energy equipment power supply, determine the power distribution output of energy equipment, and judge the remaining energy storage capacity of energy equipment; Combining the remaining stored energy with the energy generation rate, we can analyze the amount of movable energy available at any time in energy equipment, provided that the electricity consumption of charging stations and living service areas is met. Combine the available energy with the power purchase and sale agreement to process excess energy sales transactions, and determine the sales time and quantity during the excess energy sales transaction process based on real-time electricity prices; The acquisition of historical charging data of charging piles in toll stations and historical power consumption data of living service areas, combined with evidence theory and convolutional neural network technology, predicts the power demand in toll stations, including: A charging demand matrix is established based on the number of charging piles in the toll station. The charging demand matrix is decomposed into several types of charging modes using the non-negative matrix factorization method to determine the charging scale and size of several types of charging modes in the toll station. Generate a base matrix and a coefficient matrix according to the charging scale and the charging scale, and multiply the rows and columns of the base matrix and the coefficient matrix corresponding to the charging mode to obtain a dimensional matrix; Obtain historical charging data of charging piles at toll stations and substitute the same-dimensional matrix as input into the graph convolutional neural network to capture the effective information between charging patterns and charging data and predict the power demand of charging piles; Obtain historical power consumption data of the living service area within the toll station, and obtain the power demand in the living area based on the historical power consumption development trend and evidence theory, and combine the power demand of the charging piles to obtain the total power demand of the toll station.

2. The method for optimizing the construction process of a multi-energy complementary zero-carbon toll station based on energy distribution according to claim 1 is characterized in that: The acquisition of historical power consumption data of the living service area within the toll station and the acquisition of power demand within the living area based on the historical power consumption development trend and evidence theory include: Obtain historical power consumption data for each sub-area within the toll station's living service area, and generate a set of power demand forecasts for each sub-area based on the historical power consumption data and seasonal characteristics; The basic probability distribution matrix is predicted based on the electricity demand forecast set and the properties of the electrical equipment in the sub-region, and the electricity demand forecast set is synthesized using evidence theory. Based on the synthesis results, evidence conflict analysis is performed on the electricity demand forecast set to obtain the credibility function and plausibility function of the electricity demand forecast set, and the credibility function is converted into a probability distribution according to the probability conversion formula; The probability distribution of electricity demand in each sub-area is obtained according to the distribution results, and the probability distribution is combined with the basic probability allocation matrix to obtain the electricity demand of the sub-area, and the electricity demand of each sub-area is integrated to obtain the electricity demand in the living area.

3. The method for optimizing the construction process of a multi-energy complementary zero-carbon toll station based on energy distribution according to claim 2 is characterized in that: The power supply distribution model is constructed based on the power demand and the dynamic characteristics of the power supply of the energy equipment, the power supply distribution output of the energy equipment is determined, and the remaining storage energy of the energy equipment is judged, which includes: According to the power generation characteristics and energy storage characteristics of energy equipment, the minimum expected frequency of power distribution of any power supply equipment is analyzed based on the energy storage characteristics, and the minimum power generation objective function of any power supply equipment is defined using the power generation characteristics; Based on the Naive Bayesian approach, the maximum a posteriori hypothesis is made for the electricity demand at the toll station, and the maximum a posteriori hypothesis process is smoothed. The dynamic allocation parameters are calibrated according to the processing results. The energy consumption of energy equipment during the power supply process is analyzed by combining dynamic allocation parameters, minimum expected frequency and minimum power generation objective function. The objective function of the power supply allocation model is expressed in octets based on Naive Bayes. The boundary conditions of the power supply distribution model are set based on the dynamic distribution balance of energy equipment, and the constructed power supply distribution model is obtained by combining the objective function; The power distribution model is used to determine the power distribution output of any power supply device, and the remaining energy storage capacity of the energy device is obtained based on the difference between the energy storage capacity of the energy device and the power distribution output.

4. The method for optimizing the construction process of a multi-energy complementary zero-carbon toll station based on energy distribution according to claim 3 is characterized in that: The expression of the power supply distribution model is: ； Where F(t) represents the power distribution of the t-th power supply device, e represents energy consumption, α1 represents the probability that the power distribution output reaches high uniformity, α2 represents the probability that the power distribution output reaches low uniformity, υ represents the objective function of the power distribution model, β represents the minimum power generation target value of any power supply device, and T min represents the minimum expected frequency, and ε represents the dynamic allocation parameter.

5. The method for optimizing the construction process of a multi-energy complementary zero-carbon toll station based on energy distribution according to claim 4 is characterized in that: The process of combining the movable energy amount with the power purchase and sale agreement to carry out excess energy sale transaction processing, and determining the sale time and sale quantity in the excess energy sale transaction processing according to the real-time electricity price, includes: Combine the available energy volume with the power purchase and sales agreement to define the rules for selling excess energy, and connect it to the power company's smart meter system to automatically record and upload excess energy output data; Obtain historical electricity price data, reconstruct the phase space of the historical electricity price data time series, analyze the phase point of the historical electricity price at any time point, and the closest point to the phase point; Obtain the distance between the phase point and its closest point, and traverse the distances between all phase points and their corresponding closest points in the phase space to obtain the dynamic evolution law. Based on the dynamic evolution law, analyze the evolution time series of electricity prices; The real-time electricity price at any time is predicted based on the evolving time series, and the time and quantity of excess energy sales transactions are determined according to the level of the real-time electricity price.

6. The method for optimizing the construction process of a multi-energy complementary zero-carbon toll station based on energy distribution according to claim 1 is characterized in that: The method of predicting the load demand in the toll station, adjusting the supply mode of the geothermal heat pump based on the load demand, and determining the heat output of the geothermal heat pump in combination with the real-time temperature in the toll station and the variable frequency control technology includes: Obtain historical heating and cooling data within the toll station, and combine seasonal factors with edge distribution technology to predict the heating or cooling load demand of the toll station in any time period; determining a temperature requirement within the toll station according to the load demand, determining a supply mode of the geothermal heat pump based on the temperature demand, and adjusting the supply mode of the geothermal heat pump according to the determination result; Adjust the supply of geothermal heat pumps based on the real-time temperature and load demand within the toll station, and calculate the optimal operating frequency of the geothermal heat pumps by combining variable frequency control technology with the characteristics of the geothermal heat pumps. The heat output result of the geothermal heat pump is output based on the optimal operating frequency and supply, and the optimal operating frequency is adjusted according to real-time feedback to optimize the operating efficiency of the geothermal heat pump.

7. The method for optimizing the construction process of a multi-energy complementary zero-carbon toll station based on energy distribution according to claim 6 is characterized in that: The acquisition of historical heating and cooling data within the toll station and the prediction of the heating or cooling load demand of the toll station in any time period by combining seasonal factors and marginal distribution technology include: Based on the historical operation data of toll stations, historical heating and cooling data are obtained. Based on the obtained results, an estimation sample containing the two variables of heating and cooling is constructed. The distribution function value of the estimated sample under seasonal factors is obtained through non-parametric estimation method. Construct a conditional matrix based on the marginal distribution function value and the estimated sample, and use the conditional matrix to predict the probability of each data value appearing in the estimated sample and the corresponding marginal value; Based on the upper and lower bounds of the pre-set load demand interval, the expected probability of the data value within the load demand interval is analyzed in combination with the probability and marginal value, and the marginal distribution matrix of the data value is obtained using the expected probability; The marginal distribution matrix is inversely calculated to obtain the demand forecast interval for heating and cooling at the toll station, and the heating or cooling load demand at the toll station is determined from the demand forecast interval according to the time period.

8. The method for optimizing the construction process of a multi-energy complementary zero-carbon toll station based on energy distribution according to claim 7 is characterized in that: The calculation formula for the probability of occurrence of the data value and the marginal value is: ； Where S i represents the probability of the i-th data value appearing in the estimated sample, T i represents the distribution function value of the i-th data value, P represents the characteristic value of the estimated sample under seasonal factors, E i represents the edge value of the i-th data value, H(i,m) represents the joint probability mass function of the data value i and the conditional matrix m, Represents the load size of data value i in the mth conditional matrix.

Images