Multi-element market coupling park energy capacity optimal configuration method and system

Abstract

The invention discloses a multi-market coupled park energy capacity optimization configuration method and system, and the method comprises the steps: collecting the electricity market transaction price, the heat market supply and demand parameters and the carbon market emission quota information of park energy, and forming a market data set; based on historical market fluctuation data and park energy load characteristics, self-adaptively generating a coupling factor and constructing a multi-element market coupling model; an optimization constraint is constructed according to cost minimization, energy efficiency maximization and carbon emission requirements; applying constraints to obtain an optimal configuration scheme, and distributing equipment capacity to obtain operating parameters; and performing performance monitoring on the park energy equipment after parameter configuration, updating the multi-element market coupling model according to real-time updating of the market data set, and obtaining a target capacity configuration scheme when the capacity of the park energy equipment is optimized to a target state. According to the invention, the park energy configuration efficiency can be improved.

Description

Technical Field

[0001] This invention belongs to the field of energy allocation technology and relates to a method and system for optimizing the allocation of energy capacity in a multi-market coupled industrial park. Background Technology

[0002] Existing energy capacity configuration technologies for industrial parks are mostly limited to the independent optimization of a single energy market, failing to fully consider the coupling relationship between electricity, heat, and carbon markets, and lacking integration of external dynamic factors such as market price fluctuations and emission quota constraints. Furthermore, the limited coverage of data collection fails to comprehensively gather multi-market transaction information and park load characteristic data, resulting in a disconnect between the constructed models and actual market operation scenarios. Consequently, configuration schemes are ill-suited to the collaborative operation needs of diverse markets, leading to low energy resource utilization and insufficient configuration flexibility.

[0003] Existing optimization technologies often have overly simplistic constraints, focusing solely on cost control and failing to comprehensively consider multiple objectives such as energy efficiency improvement and carbon emission reduction. Furthermore, they lack dynamic adjustment mechanisms. Once the model is built, it's difficult to update the optimization logic based on real-time equipment performance and market supply and demand changes. This results in rigid and outdated configuration schemes that cannot respond to dynamic fluctuations in the park's energy load, further exacerbating energy waste and high operating costs. Therefore, improving the efficiency of optimizing the allocation of park energy capacity in conjunction with diverse market forces has become an urgent problem to be solved. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method and system for optimizing the allocation of energy capacity in a multi-market coupled industrial park.

[0005] The present invention adopts the following technical solution.

[0006] The first aspect of this invention proposes a method for optimizing the allocation of energy capacity in industrial parks through a multi-market coupling mechanism, comprising: Collect electricity market transaction prices, heat market supply and demand parameters, and carbon market emission quota information for the park's energy sector and compile them into a market data set for the park's energy sector; Based on historical market fluctuation data and park energy load characteristics, a distribution map of market coupling intensity of park energy is constructed, and then coupling factors of park energy are adaptively generated. Combined with market data set, a multi-market coupling model of park energy is dynamically constructed. Based on the aforementioned market data set, optimization constraints for park energy are constructed with the goals of minimizing costs, maximizing energy efficiency, and meeting carbon emission requirements. By applying the optimization constraints to the multi-market coupling model, an optimal energy allocation scheme for the park is obtained; The capacity of the park's energy equipment is allocated and verified according to the optimized configuration scheme to obtain the operating parameters of the park's energy equipment and configure the parameters of the park's energy equipment. The performance of the park's energy equipment after parameter configuration is monitored. Based on the real-time updates of the market data set, the multi-market coupling model is updated to optimize the capacity of the park's energy equipment to the target state, thus obtaining the target capacity configuration scheme for the park's energy equipment.

[0007] Preferably, the process of collecting and compiling the electricity market transaction prices, heat market supply and demand parameters, and carbon market emission quota information of the park's energy sector into a market data set for the park's energy sector includes: Collect information on electricity market transaction prices, heat market supply and demand parameters, and carbon market emission quotas for energy in the industrial park; Based on the electricity market transaction prices, a price data sequence for park energy is generated; based on the heat market supply and demand parameters, a set of supply and demand parameters for park energy is generated; based on the carbon market emission quota information, quota data records for park energy are generated. By eliminating outliers and redundant information from the price data sequence, the supply and demand parameter set, and the quota data record, a market data set for energy in the park is obtained.

[0008] Preferably, the step of constructing a market coupling intensity distribution map of park energy based on historical market fluctuation data and park energy load characteristics, adaptively generating coupling factors for park energy, and dynamically constructing a multi-market coupling model for park energy in conjunction with market data sets includes: Based on the time scale, historical market fluctuation data is decomposed into long-term trend components, cyclical fluctuation components, and short-term random components to obtain structured market data for energy in the park. Based on the energy consumption patterns of the park's energy load characteristics, the park's basic load, adjustable load, and critical load are identified, resulting in a set of load characteristic patterns for the park's energy. Spatiotemporal correlation matching is performed between different market variables in the structured market data and different loads in the load characteristic pattern set. The degree of influence of each market variable on different loads is calculated and quantified into a weight value to obtain the dynamic influence weight set of park energy. Using different market variables and different loads as the rows and columns of a matrix, and with the corresponding weight values ​​as the values ​​of the unit cells of the corresponding matrix, the dynamic influence weight set is reconstructed into a coupling strength evaluation matrix; The correlation strength among the electricity market, heat market and carbon market in the coupling strength assessment matrix is ​​quantified to construct a distribution map of market coupling strength of park energy, and the coupling factor of park energy is adaptively obtained. Based on the interaction between the electricity market, heat market, and carbon market in the aforementioned market coupling intensity distribution map, an initial coupling architecture for park energy is constructed. By inputting the market data set and the coupling factor into the initial coupling architecture, a multi-market coupling model for the park's energy is obtained.

[0009] Preferably, the quantification of the correlation strength among the electricity market, heat market, and carbon market in the coupling strength assessment matrix to construct a market coupling strength distribution map of the park's energy sector and adaptively obtain the coupling factor of the park's energy sector includes: Extract the electricity market index vector, heat market index vector, and carbon market index vector from the coupling strength assessment matrix to obtain a multi-market index vector set for energy in the park. The multi-market indicator vector set is projected into the vector space model, and the correlation strength between different markets in the coupling strength evaluation matrix is ​​determined based on the cosine value of the angle between the vectors, thus obtaining the primary correlation strength data of the park's energy. The primary correlation strength data is normalized to obtain the standardized correlation strength value of the park's energy. Using different markets as nodes and the standardized correlation strength value as edges, a market coupling strength distribution map of park energy is constructed; The final coupling strength coefficient is determined based on the connection density of the nodes in the market coupling strength distribution map. Based on the standardized correlation strength value and the final coupling strength coefficient, the coupling factor of the park's energy is determined.

[0010] Preferably, the step of constructing optimization constraints for park energy based on the market data set, with the objectives of minimizing costs, maximizing energy efficiency, and meeting carbon emission requirements, includes: Based on the market data set, energy procurement costs, equipment operation and maintenance costs, and market transaction costs are obtained to determine the cost elements of energy in the park, and the minimum target cost of energy in the park is constructed based on the cost elements. Track the conversion and transmission paths of energy in the park system, and determine the maximum energy efficiency target of the park's energy based on the energy efficiency of each link in the conversion and transmission path; Obtain direct and indirect emission data of energy in the park during the energy conversion process to obtain carbon emission constraints for energy in the park; By coordinating the minimum target cost, the maximum energy efficiency target, and the carbon emission constraint, the optimal constraints for energy in the park are obtained.

[0011] Preferably, applying the optimization constraints to the multi-market coupling model to obtain an optimized energy allocation scheme for the park includes: The optimization constraints are transformed into the boundary conditions of the multi-market coupling model, resulting in the coupling model after constraint injection. The energy allocation scenarios under different market conditions are simulated in the coupled model after the constraint injection to obtain the initial energy allocation scheme of the park; The feasibility of the initial configuration scheme is verified and its benefits are evaluated to obtain the scheme evaluation results. Based on the evaluation results of the proposed schemes, the optimal configuration scheme is selected from the initial configuration schemes to obtain the optimized configuration scheme for park energy.

[0012] Preferably, the step of selecting the optimal configuration scheme from the initial configuration schemes based on the scheme evaluation results to obtain the optimized configuration scheme for park energy includes: The economic indicators, energy efficiency indicators, and carbon emission indicators from the proposed scheme evaluation results are mapped into a matrix to obtain the comprehensive evaluation matrix of the park's energy schemes. The comprehensive evaluation matrix of the proposed scheme is normalized to obtain a standardized evaluation matrix for park energy. The normalized values ​​in the standardized evaluation matrix are weighted and fused based on preset indicator weights to generate a comprehensive score for the initial configuration scheme. The initial configuration schemes are sorted according to the comprehensive scores to obtain a sorted list of energy schemes for the park. The feasibility of the top-ranked schemes in the scheme ranking list is verified, and the schemes that pass the verification are output as the optimized energy allocation schemes for the park.

[0013] Preferably, the step of allocating and verifying the capacity of the park's energy equipment according to the optimized configuration scheme to obtain the operating parameters of the park's energy equipment for configuring the park's energy equipment parameters includes: Identify the capacity configuration requirements of photovoltaic power generation units, energy storage systems, and combined heat and power units in the optimized configuration scheme to obtain the capacity allocation task set for energy equipment in the park. Based on the capacity allocation task set, a capacity preset instruction is sent to the corresponding energy equipment to obtain the initial operating parameters of the energy equipment in the park. The initial operating parameters of the device are checked for compatibility to ensure the compatibility of the device operating parameters at the system level, and the coordinated operating parameters are obtained. The coordinated operating parameters are sent to the corresponding energy equipment for execution, and feedback on the operating status of the energy equipment in the park is obtained. Based on the equipment operation status feedback, the consistency of the actual operating parameters and the target parameters is verified and adjusted. The parameters that finally meet the consistency verification requirements are determined as the operating parameters of the park's energy equipment to configure the park's energy equipment parameters.

[0014] A second aspect of this invention proposes a multi-market coupled park energy capacity optimization allocation system, comprising: The data aggregation module is used to collect electricity market transaction prices, heat market supply and demand parameters, and carbon market emission quota information for the park's energy sector and aggregate them into a market data set for the park's energy sector. The model dynamic construction module is used to construct a distribution map of the market coupling intensity of park energy based on historical market fluctuation data and park energy load characteristics, and then adaptively generate the coupling factors of park energy, and dynamically construct a multi-market coupling model of park energy in combination with market data set. The constraint setting module is used to construct optimal constraints for park energy based on the market data set, with the goals of minimizing costs, maximizing energy efficiency, and meeting carbon emission requirements. An optimization generation module is used to apply the optimization constraints to the multi-market coupling model to obtain an optimized energy allocation scheme for the park. The capacity allocation module is used to allocate and verify the capacity of the park's energy equipment according to the optimized configuration scheme, and obtain the operating parameters of the park's energy equipment to configure the park's energy equipment parameters. The monitoring and optimization module is used to monitor the performance of the park's energy equipment after parameter configuration. Based on the real-time updates of the market data set, the module updates the multi-market coupling model to optimize the capacity of the park's energy equipment to the target state, thereby obtaining the target capacity configuration scheme for the park's energy equipment.

[0015] A third aspect of the present invention provides a terminal, including a processor and a storage medium; the storage medium is used to store instructions; the processor is used to perform operations according to the instructions to execute the steps of the method.

[0016] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method.

[0017] Compared with the prior art, the beneficial effects of the present invention include at least the following: This invention accurately collects and aggregates market data on electricity market transaction prices, heat market supply and demand parameters, and carbon market emission quotas across multiple dimensions within a park. This eliminates outliers and redundant information, resulting in a highly accurate, complete, and consistent market data set. This provides reliable foundational data for subsequent coupling factor generation and the construction of a multi-market coupling model, ensuring the scientific rigor of the park's energy capacity optimization. Furthermore, based on the structured decomposition results of historical market fluctuation data and pattern recognition results of the park's energy load characteristics, coupling factors are adaptively generated, and a multi-market coupling model is constructed. This model accurately captures the interactions between multiple markets, ensuring it fully aligns with actual market operation scenarios. This provides precise data support and a scientific model foundation for the park's energy capacity optimization, effectively improving the adaptability and rationality of the configuration scheme.

[0018] This invention constructs multi-objective optimization constraints based on cost minimization, energy efficiency maximization, and carbon emission requirements. After imposing constraints on a multi-market coupling model, it simulates multiple scenarios and selects the optimal configuration scheme. The energy equipment capacity of the park is allocated according to the scheme, and the synergy of operating parameters is verified. At the same time, the equipment performance is monitored in real time, and the model is updated according to market data until the equipment capacity is optimized to the target state. This ensures that the configuration scheme takes into account economy, energy efficiency, and environmental protection, and can dynamically adapt to market and load changes, effectively improving the accuracy, stability, and overall benefits of park energy capacity configuration. Attached Figure Description

[0019] Figure 1 A flowchart illustrating a method for optimizing the allocation of energy capacity in a multi-market coupled industrial park, provided as an embodiment of the present invention; Figure 2 This is a functional module diagram of a multi-market coupled park energy capacity optimization configuration system provided in an embodiment of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of this invention. The embodiments described in this application are merely some embodiments of this invention, and not all embodiments. Based on the spirit of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of this invention.

[0021] Embodiment 1 of the present invention provides a method for optimizing the allocation of energy capacity in a multi-market coupled industrial park, referring to... Figure 1 As shown, the method includes: S1: Collect electricity market transaction prices, heat market supply and demand parameters, and carbon market emission quota information for energy in the park and compile them into a market data set for energy in the park; More preferably, the electricity market transaction prices, heat market supply and demand parameters, and carbon market emission quota information of the park's energy resources are aggregated into a market data set for the park's energy resources, including: Based on the electricity market transaction prices of the park's energy resources, a price data sequence for the park's energy resources is generated; Based on the energy supply and demand parameters of the park's energy market, a set of energy supply and demand parameters for the park is generated; Based on the carbon market emission quota information of the park's energy, generate the quota data record of the park's energy; By eliminating outliers and redundant information from the price data sequence, the supply and demand parameter set, and the quota data record, the market data set of the park's energy is obtained.

[0022] In practice, S1 connects to the power trading platform through the park's energy management system, collecting real-time electricity market transaction prices for different trading periods each day, such as electricity purchase prices and corresponding purchase quantities. At the same time, it retrieves historical transaction price data from the past 12 months, arranging the real-time and historical price data in ascending order of timestamp. Each data point is labeled with the corresponding transaction date, transaction period, and price value, ensuring that the data is continuous and complete in the time dimension, forming a time-evolving sequence of park energy price data.

[0023] We obtain supply-side parameters such as daily total heat supply, supply pressure, and supply temperature from the heat supply companies in the park. We collect demand-side parameters such as daily total heat demand, peak heat consumption at different times, heat consumption stability, heat purchase price, and corresponding purchase volume data from the metering equipment of each heat-consuming unit in the park. We calculate the difference between daily heat supply and demand to obtain supply-demand balance parameters. We then classify and organize the supply-side parameters, demand-side parameters, and supply-demand balance parameters according to the structure of "date-supply parameter group-demand parameter group-balance parameter" to ensure that each group of parameters corresponds to the same time period, thus forming a set of energy supply and demand parameters for the park.

[0024] Log in to the official platform of the regional carbon trading authority, download the park's annual carbon emission quota document, and extract basic information such as the total quota, quota issuance date, compliance assessment cycle, quota adjustment rules, transaction fees during carbon quota trading, quota adjustment fees, daily maintenance records of park energy equipment, list of regular maintenance costs, and equipment wear and replacement cost data; use the carbon emission monitoring devices of the park's energy equipment to count the monthly carbon emissions of each device in real time, accumulate the cumulative used quota, and calculate the remaining quota by subtracting the cumulative used quota from the total quota; register the total quota, used quota, remaining quota, issuance date, and compliance cycle item by item in the format of "record date - basic quota information - quota usage information - compliance information" to form the park's energy quota data record.

[0025] For the price data series, the average price of the same period in the past 30 days is calculated as the normal range benchmark. Values ​​exceeding the benchmark by ±30% are judged as outliers. Outliers are replaced with the historical average price of the same period, and duplicate price data are deleted. For the set of supply and demand parameters, remove the enterprise internal management code fields that are not related to energy configuration, merge the supply and demand data collected repeatedly on the same date, and retain a complete set of parameters; For quota data records, delete duplicate quota issuance notification records and correct date data with inconsistent formats; The processed price data series, supply and demand parameter sets, and quota data records are linked and integrated according to the time dimension to ensure that the three types of data at the same time point match each other, forming a market data set for energy in the park.

[0026] The above steps, through precise collection and organization across multiple dimensions, generate complete price data sequences, supply and demand parameter sets, and quota data records. After rigorous processing of outliers and redundant information, the final market data set possesses high accuracy, completeness, and consistency, providing reliable basic data support for subsequent generation of coupling factors and construction of multi-market coupling models, and ensuring the scientific nature of the park's energy capacity optimization allocation.

[0027] S2: Based on historical market fluctuation data and park energy load characteristics, adaptively generate the coupling factor of the park's energy, and dynamically construct the multi-market coupling model of the park's energy based on the coupling factor; More preferably, a market coupling intensity distribution map of park energy is constructed based on historical market fluctuation data and park energy load characteristics, thereby adaptively generating coupling factors for park energy, and dynamically constructing a multi-dimensional market coupling model for park energy in conjunction with market data sets, including: S2.1: Decompose historical market fluctuation data into long-term trend components, periodic fluctuation components, and short-term random components according to the time scale to obtain the structured market data of the park's energy. S2.2: Identify the basic load, adjustable load, and critical load of the park's energy based on the energy consumption patterns of the park's energy load characteristics, and obtain the load characteristic pattern set of the park's energy; S2.3: Perform spatiotemporal correlation matching between different market variables in the structured market data and different loads in the load characteristic pattern set to obtain the dynamic impact weight set of the park's energy; S2.4: Reconstruct the dynamic influence weight set into a coupling strength evaluation matrix; S2.5: Quantify the interaction strength among the electricity market, heat market, and carbon market in the coupling strength assessment matrix to obtain the coupling factor of the park's energy, including: (1) Extract the electricity market index vector, heat market index vector and carbon market index vector from the coupling strength assessment matrix to obtain the multi-market index vector set of the park's energy; (2) Project the multi-market indicator vector set into the vector space model, and determine the correlation strength between different markets in the coupling strength evaluation matrix according to the cosine value of the angle between the vectors, so as to obtain the primary correlation strength data of the park energy. (3) Normalize the primary correlation strength data to obtain the standardized correlation strength value of the park's energy; (4) Using different markets as nodes and the standardized correlation strength value as edges, construct the market coupling strength distribution map of the park's energy; (5) Determine the final coupling strength coefficient based on the connection density of the nodes in the market coupling strength distribution map; (6) Based on the standardized correlation strength value, construct a market coupling strength distribution map, and determine the coupling factor of the park energy by analyzing the connection density between nodes in the map.

[0028] S2.6: Based on the interaction between the electricity market, heat market and carbon market in the market coupling intensity distribution map, construct the initial coupling architecture of the park's energy; S2.7: Input the market data set and the coupling factor into the initial coupling architecture to obtain the multi-market coupling model of the park's energy.

[0029] In practice, raw market parameters (historical market fluctuation data) collected directly from the corresponding trading platforms or monitoring systems, such as electricity prices, heat supply and demand, and carbon quota prices, reflect the comprehensive state of the market at a certain moment. This data includes the final result of the combined effects of all influencing factors, exhibiting dramatic fluctuations and complex causes. S2.1, through time series decomposition techniques (such as seasonal decomposition or filtering methods), can separate three components with different physical and economic meanings from these raw data sequences: a long-term trend component, capturing the slow and persistent evolution driven by infrastructure investment, policy guidance, and technological changes; a periodic fluctuation component, extracting the regular recurring fluctuations caused by seasonal changes, production cycles, and holidays; and a short-term random component, representing unpredictable noise fluctuations caused by sudden events, instantaneous market speculation, and prediction errors. Specifically, S2.1 sets time scale division standards. The long-term trend component is based on an annual unit, statistically analyzing the annual average and year-by-year trend of historical market fluctuation data over the past 5 years. By comparing the overall trend of data at the same time each year, long-term stable change patterns are extracted. The periodic fluctuation component is based on a monthly unit, analyzing the repetitive change characteristics of monthly data over the past 36 months, such as the fluctuation pattern of heat demand in the middle and late parts of each month, separating the periodic repetitive fluctuation part. The short-term random component is based on a daily unit, subtracting the corresponding values ​​of the long-term trend component and the periodic fluctuation component from the daily actual market fluctuation data to obtain the daily sudden change random data. The long-term trend component, periodic fluctuation component, short-term random component, and related market variables are organized according to time series to obtain the structured market data of park energy.

[0030] Market variables provide the model with a structured analytical perspective and logical framework, defining which market dimensions to analyze. These variables are populated with real-time, dynamic data through various relevant indicators, driving the model to perform calculations and derive results. In actual operation, the system continuously collects the latest indicator data to update the specific values ​​of each market variable, enabling the coupled model and optimization scheme built based on these variables to adaptively reflect the latest market dynamics.

[0031] S2.2 Collects real-time energy consumption data of the park for one consecutive month, and analyzes energy consumption patterns according to energy stability and importance. Base load is energy consumption that is continuously and stably consumed for 24 hours with a fluctuation range of no more than 5%, such as the park's public lighting system and standby power consumption of core equipment. It is identified by screening energy consumption data with minimal changes within 24 hours. Adjustable load is energy consumption that can be flexibly adjusted during the consumption period and has no serious impact after interruption, such as the park's air conditioning system and power consumption of non-core production auxiliary equipment. It is identified by analyzing energy consumption data that can be transferred at different times without affecting the overall operation. Critical load is energy consumption that would cause the failure of core functions after interruption and must be continuously guaranteed, such as the park's emergency power supply system and power consumption of core production process equipment. It is identified by marking energy consumption data that will trigger alarms after interruption. The energy consumption characteristics, consumption periods, and importance levels of the three types of loads are sorted to obtain the load characteristic pattern set of the park's energy.

[0032] S2.3 The park is divided into production area, living area and public area according to spatial dimension. Electricity, heat and carbon market variables such as electricity price, heat supply and demand and carbon quota price in structured market data are matched with the base load, adjustable load and critical load of each area. Market variable fluctuation data and load change data within the same hour are matched according to time dimension. For example, the change of critical load in production area when electricity price rises in a certain hour period is analyzed. The degree of influence of each market variable on different loads is calculated, such as the proportion of the impact of a 1 unit change in electricity price on critical load. The degree of influence under different time and space dimensions is quantified into specific weight values ​​and organized according to the structure of "market variable-area-load type-weight value" to obtain the dynamic influence weight set of park energy.

[0033] S2.4 Determine the row and column dimensions of the coupling strength assessment matrix. The rows of the matrix correspond to the electricity market variables, heat market variables, and carbon market variables in the structured market data. The columns of the matrix correspond to the base load, adjustable load, and critical load in the load characteristic pattern set. Fill the corresponding weight value of each "market variable-load type" in the dynamic influence weight set into the corresponding position of the matrix. For example, fill the weight value of the electricity price variable and the critical load into the cell of the electricity row and the critical load column. Ensure that all weight values ​​are filled in completely and accurately. The matrix with the weight values ​​is structured and formatted to obtain the coupling strength assessment matrix of park energy.

[0034] S2.5 (1) Extract all row data related to the power market from the coupling strength assessment matrix, including the weight values ​​corresponding to indicators such as power price, power trading volume, and power supply stability, and arrange them in the order of indicators to form a power market indicator vector; extract all row data related to the heat market, including the weight values ​​corresponding to indicators such as heat supply and demand, heat price, and heat transmission efficiency, and arrange them in the order of indicators to form a heat market indicator vector; extract all row data related to the carbon market, including the weight values ​​corresponding to indicators such as carbon quota, carbon emission rights price (carbon quota price), and carbon emission assessment coefficient, and arrange them in the order of indicators to form a carbon market indicator vector; organize the three vectors into an ordered set to obtain the multi-market indicator vector set of park energy.

[0035] (2) Construct a three-dimensional vector space model. The power market index vector, heat market index vector, and carbon market index vector in the multi-market index vector set are respectively used as three vectors in the space. Each index value of each vector corresponds to the coordinate value of one dimension in the space. By measuring the angle between any two vectors, such as the angle between the power market vector and the heat market vector, the smaller the angle, the closer the correlation between the two market indicators. Determine the cosine value of the angle according to the size of the angle. When the angle is 0 degrees, the cosine value is 1, and when the angle is 90 degrees, the cosine value is 0. The cosine value corresponding to each angle is used as the correlation strength between the two markets. Record it according to the structure of "market pair - correlation strength value" to obtain the primary correlation strength data of the park's energy.

[0036] It is determined by calculating the geometric relationship (cosine of the included angle) of the multi-market indicator vector formed by the current data in space, thus realizing adaptive correlation strength quantification based on the characteristics of the data itself.

[0037] (3) Calculate the maximum and minimum values ​​in the primary correlation strength data and the difference between the maximum and minimum values; for each primary correlation strength data value, subtract the minimum value from the value and divide the result by the difference between the maximum and minimum values ​​to adjust all data values ​​to the range of 0 to 1. For example, if a primary correlation strength value is 5, the minimum value is 2 and the maximum value is 10, calculate (5-2) / (10-2)=0.375 to obtain the standardized value of the data; process all primary correlation strength data in this way to obtain the standardized correlation strength value of park energy.

[0038] The maximum and minimum values ​​used for the normalization process described above are derived from the primary association strength dataset calculated in the current batch. The standardized results (values ​​between 0 and 1) will be dynamically adjusted as the input data changes each time, making the association strengths in different periods and scenarios comparable. Its scale adapts to the current data distribution.

[0039] (4) Take the electricity market, heat market and carbon market as three independent nodes respectively, and place the three nodes in a triangular distribution in the planar map. Each node is labeled with the corresponding market name. Determine the attributes of the edges between the nodes according to the standardized correlation strength value. The larger the standardized value, the thicker the edge line. At the same time, label the corresponding standardized correlation strength value on the edge. For example, the standardized value between the electricity market and the heat market is 0.8, so draw a thicker edge and label it 0.8. Connect the three nodes through the corresponding edges to form a complete network structure and obtain the market coupling strength distribution map of the park's energy.

[0040] The attributes (i.e., strength values) of the edges connecting each market node in the dynamically generated graph structure are directly determined by the standardized association strength values ​​obtained in the previous step. Therefore, the structure of the graph (the strength of the edges) is dynamically shaped by the results calculated from real-time data, vividly reflecting the coupling relationships between multiple markets.

[0041] (5) Calculate the total number of node connections in the market coupling strength distribution map. There are 3 possible connection edges between the three market nodes. The actual number of connection edges is the total number of connections. Calculate the sum of the standardized association strength values ​​of all connection edges. Divide the sum by the total number of connections to obtain the average connection density of the nodes. This density value is the final coupling strength coefficient. The process of automatically extracting macroscopic features as coefficients from the generated data structure (graph) by calculating the connectivity density (e.g., the average of the normalized strength values ​​of all edges) based on the strength values ​​of actual edges in the statistical graph. The magnitude of the coefficients depends entirely on the data generated in the preceding steps, achieving adaptive induction from microscopic correlations to macroscopic coefficients.

[0042] (6) Combining the standardized correlation strength value of each connection edge with the average connection density (final coupling strength coefficient), the overall coupling level among the three markets is comprehensively judged. The average connection density (final coupling strength coefficient) and the strength value of each edge are integrated in a fixed proportion to obtain the coupling factor of the park's energy, which specifically includes: The average connection density (final coupling strength coefficient) and edge strength values ​​(normalized association strength values ​​corresponding to each edge in the graph) of the nodes are determined and directly labeled on each edge during graph construction. A list of edge strength values ​​is formed by recording the two market nodes connected to each edge and the edge's strength value. The average connection density and edge strength values ​​are integrated at a fixed ratio. This fixed ratio is preset by the system, specifying the weight of the average connection density and the weight of each edge strength value in the integration. For each edge in the edge strength value record list, the average connection density is multiplied by its weight to obtain the average connection density component. The edge strength value is then multiplied by its weight to obtain the edge strength value component. These two components are added together to obtain the integrated strength value of the edge. The same operation is performed on all edges to obtain the integrated strength value of each edge. The integrated strength values ​​of all edges are organized into an ordered set according to the order of market node pairs. This ordered set is the coupling factor of the park's energy, containing the integrated strength values ​​of all inter-market connection edges.

[0043] The generation process of the aforementioned coupling factors does not rely on any preset fixed rules or empirical parameters. The intermediate and final results of each step are completely and directly determined by the correlations calculated in real time from the input data. The system automatically learns and quantifies the coupling strength between markets from the raw data through a set of algorithms, thereby generating coupling factors adapted to the current data state.

[0044] S2.6 Based on the interaction relationships of the three markets in the market coupling intensity distribution map, the basic structure of the initial coupling architecture is determined. A two-way interaction channel is set between the electricity market and the heat market to reflect the support of electricity supply for heat production and the impact of heat demand on electricity consumption. A one-way interaction channel is set between the electricity market and the carbon market to reflect the impact of carbon emissions from electricity production on carbon quota consumption. A one-way interaction channel is also set between the heat market and the carbon market to reflect the impact of carbon emissions from heat production on carbon quota consumption. Data input interfaces are reserved for each interaction channel in the architecture, forming a framework that includes market nodes, interaction channels, and data interfaces, thus obtaining the initial coupling architecture of the park's energy sector.

[0045] S2.7 Input the electricity market transaction prices, heat market supply and demand parameters, and carbon market emission quota information from the market data set into the interfaces of the corresponding market nodes in the initial coupling architecture to ensure accurate matching of data and nodes; input the coupling factors into each action channel in the architecture as the influence weight of the channel to adjust the strength of the interaction between the markets; through the logical operation inside the architecture, integrate the market data and coupling factors, so that the information of each market node can be transmitted to each other and calculated collaboratively through the action channels to form a complete model that can reflect the coupling relationship of multiple markets, and obtain the multi-market coupling model of park energy.

[0046] The above steps obtain structured data by accurately decomposing historical market fluctuation data according to the time scale, clearly identify three types of loads based on energy consumption patterns to form a characteristic pattern set, obtain dynamic influence weights through spatiotemporal correlation matching, and then construct quantitative market coupling relationships through matrix reconstruction, vector space projection, normalization processing, and graph construction. Finally, a multi-market coupling model is constructed by combining market data and coupling factors. The entire process is specific and logically coherent, ensuring that the model can accurately reflect the interaction between the electricity, heat, and carbon markets, providing a scientific and reliable model foundation for subsequent optimization of energy capacity allocation in the park, and effectively improving the adaptability and rationality of the allocation scheme.

[0047] S3: Construct the energy optimization constraints for the park based on cost minimization, energy efficiency maximization, and carbon emission requirements; More preferably, based on the aforementioned market data set, optimization constraints for the park's energy are constructed with the objectives of minimizing costs, maximizing energy efficiency, and meeting carbon emission requirements, including: S3.1: Identify the energy procurement cost, equipment operation and maintenance cost, and market transaction cost in the market data set to obtain the cost elements of the park's energy, and construct the minimum target cost of the park's energy based on the cost elements; S3.2: Track the conversion and transmission paths of energy in the park system, and determine the maximum energy efficiency target of the park's energy based on the energy efficiency of each link in the conversion and transmission path; S3.3: Collect direct and indirect emission data of the park's energy during the energy conversion process to obtain the carbon emission constraints of the park's energy; S3.4: Perform multi-objective constraint coordination on the minimum target cost, the maximum energy efficiency target, and the carbon emission constraint to obtain the optimized constraint of the park's energy.

[0048] In specific implementation, S3.1 extracts electricity purchase prices, heat purchase prices, and corresponding purchase quantities from the market data set. Electricity purchase costs are calculated by multiplying the purchase price by the purchase quantity, and heat purchase costs are calculated similarly, summarizing these to obtain the energy purchase cost. It also extracts daily maintenance records, periodic inspection cost lists, and equipment wear and tear replacement cost data for the park's energy equipment, summarizing them by equipment type to obtain equipment operation and maintenance costs. Furthermore, it extracts transaction fees and quota adjustment fees from the carbon quota trading process, summarizing them to obtain market transaction costs. These energy purchase costs, equipment operation and maintenance costs, and market transaction costs are integrated into the park's energy cost elements. With the goal of minimizing the total cost elements, a reasonable cost control range is set based on the park's historical cost data. It is determined that, under the premise of meeting basic energy supply needs, the total cost must be lower than the upper limit of this range, thus constructing the minimum target cost for the park's energy.

[0049] S3.2 By conducting an on-site inspection of the equipment connections in the park's energy system, an energy conversion and transmission path diagram is drawn, covering the path of electricity from the external power grid to the park's transformers, through distribution lines to various energy-consuming equipment, and the path of heat from the heat source plant through transmission pipelines and heat exchange stations to the user end. Energy efficiency monitoring instruments are installed at each link in the path, such as energy efficiency analyzers for transformers and heat loss monitors for the heating pipeline network, to collect the energy input and output of each link in real time and calculate the energy efficiency of each link. The total energy efficiency of the park's energy system is obtained by multiplying the efficiencies of each link in turn. A minimum standard for the total energy efficiency to be achieved is set, and it is determined that by optimizing equipment operating parameters and improving transmission paths to reduce losses, the total energy efficiency can be made as close to or exceed this standard as possible, thus determining the park's maximum energy efficiency target.

[0050] S3.3 Install continuous carbon emission monitoring systems at the exhaust outlets of direct emission sources in the industrial park to collect real-time carbon dioxide emissions during combustion, and summarize the direct emission data daily. Extract the monthly purchase volume of externally purchased electricity from the market data set, obtain the annual average carbon emission coefficient published by the local power grid company, and calculate the indirect emission data by multiplying the purchase volume by the carbon emission coefficient. Add the direct and indirect emission data to obtain the total carbon emissions of the park's energy. Referring to the park's annual carbon market emission quota information, set a limit that the total carbon emissions must not exceed the total annual quota, and clarify that the operating time of high-emission equipment must be controlled and the energy structure optimized to reduce carbon emissions during energy allocation, thus obtaining the carbon emission constraints for the park's energy.

[0051] S3.4 first sets carbon emission constraints as hard constraints, clearly stating that total carbon emissions must be strictly lower than the annual quota and cannot be exceeded. For the minimum target cost and maximum energy efficiency targets, weights are assigned based on the park's operational priorities, with cost weighting and energy efficiency weighting each accounting for 50%. Under the premise of meeting the hard carbon emission constraints, the mutual impact of cost reduction and energy efficiency improvement is analyzed. For example, replacing equipment with high-efficiency equipment may increase initial operation and maintenance costs but improve long-term energy efficiency. By adjusting equipment operating parameters and optimizing energy procurement periods, energy efficiency is maximized while keeping costs within the minimum target cost limit. The minimum target cost, maximum energy efficiency target, and carbon emission constraints are integrated according to the principle of "prioritizing hard constraints and balancing flexible targets" to form the optimized constraints for the park's energy.

[0052] The above steps, through precise decomposition and calculation of cost elements, make the minimum target cost practically achievable. The energy efficiency target set based on path tracing and equipment monitoring conforms to the actual operating rules of the park's energy system. The carbon emission constraints set in combination with direct and indirect emission data are in line with the requirements of carbon market policies. The optimized constraints after multi-objective coordination effectively balance economic efficiency, energy efficiency, and environmental protection, providing a scientific and feasible basis for subsequently imposing constraints on the multi-market coupling model and ensuring the accuracy of the park's energy capacity optimization allocation direction.

[0053] S4: Apply the optimization constraints to the multi-market coupling model to obtain the optimal energy allocation scheme for the park; More preferably, applying the optimization constraints to the multi-market coupling model to obtain the optimal energy allocation scheme for the park includes: S4.1: Transform the optimization constraints into the boundary conditions of the multi-market coupling model to obtain the coupling model after constraint injection; S4.2: Simulate energy configuration scenarios under different market conditions in the coupled model after the constraint injection to obtain the initial energy configuration scheme of the park; S4.3: Perform feasibility verification and benefit assessment on the initial configuration scheme to obtain the scheme evaluation results of the initial configuration scheme; S4.4: Based on the evaluation results of the aforementioned schemes, the optimal configuration scheme is selected from the initial configuration schemes to obtain the optimized configuration scheme for the park's energy, including: (1) Map the economic indicators, energy efficiency indicators and carbon emission indicators in the evaluation results of the scheme to the decision matrix to obtain the comprehensive evaluation matrix of the energy scheme of the park; (2) Normalize the comprehensive evaluation matrix of the scheme to obtain the standardized evaluation matrix of the park's energy; (3) The standardized evaluation matrix is ​​weighted and fused based on the preset index weights to generate the comprehensive score of the initial configuration scheme; (4) Sort the initial configuration schemes according to the comprehensive scores to obtain the sorted list of the park energy schemes; (5) Perform feasibility verification on the top-ranked schemes in the scheme ranking list, and output the verified schemes as the optimized energy allocation schemes for the park.

[0054] In practical implementation, S4.1 extracts three core elements from the optimization constraints: minimum target cost, maximum energy efficiency target, and carbon emission constraints, and transforms them according to the parameter logic of the multi-market coupling model: The minimum target cost is transformed into the upper limit of the product of the total energy procurement volume and the transaction price of each market in the model, and it is made clear that the calculation results of the electricity and heat procurement volume and the corresponding price in the model shall not exceed this upper limit; The goal of maximizing energy efficiency is transformed into the minimum threshold for the efficiency of each stage of energy conversion and transmission in the model, requiring that the efficiency values ​​of each stage calculated by the model must not be lower than this threshold. The carbon emission constraint is transformed into an absolute upper limit of the total carbon dioxide emissions in the model, which limits the cumulative result of direct and indirect emissions within the model from exceeding this upper limit.

[0055] These transformed parameters are used as boundary conditions for model operation and input into the multivariate market coupling model to complete constraint injection, resulting in the coupling model after constraint injection of park energy.

[0056] S4.2 sets three typical market condition scenarios: peak electricity market scenario, tight heat market supply and demand scenario, and high carbon quota price scenario, while also setting a benchmark market scenario. In the coupled model after constraint injection, the corresponding market parameters are adjusted sequentially to simulate each scenario: under the peak electricity market scenario, reduce electricity procurement and increase the charging and discharging utilization of energy storage systems; under the tight supply and demand scenario, prioritize the heat supply to critical loads and reduce the allocation of adjustable loads; under the high carbon quota price scenario, increase the installation of clean energy such as photovoltaics and reduce the operating time of gas boilers. The capacity allocation ratio of park energy equipment, the type and quantity of energy procurement, and the selection of trading time periods are recorded for each scenario to form multiple independent configuration schemes, resulting in the initial configuration scheme of park energy.

[0057] S4.3 Conduct feasibility verification for each initial configuration scheme: Verify whether the capacity of the photovoltaic, energy storage, and combined heat and power units in the scheme meets the upper limit of the park's power grid transformer capacity, whether the heat pipeline transmission capacity matches the total heat supply, and whether the carbon quota usage is within the annual quota range. Schemes that do not meet hardware capacity or policy requirements are eliminated. Simultaneously, conduct benefit assessment: Calculate the total actual energy procurement cost, equipment operation and maintenance cost, and market transaction cost of the scheme to determine if it is lower than the minimum target cost; calculate the actual total energy efficiency of energy conversion and transmission to determine if the maximum energy efficiency target has been achieved; and calculate the total carbon dioxide emissions after the scheme is implemented to determine if carbon emission constraints are met. Organize the verification results and assessment data into a structured document to obtain the scheme assessment results for the initial configuration scheme.

[0058] S4.4 (1) Determine the dimensions of the comprehensive evaluation matrix of the schemes: The rows of the matrix correspond to the initial configuration schemes that have passed the feasibility verification for each group, and the title of each row is marked with the scheme number; the columns of the matrix correspond to three types of core evaluation indicators, of which the economic indicators include total operating cost and unit energy cost, the energy efficiency indicators include total system energy efficiency and cogeneration unit conversion efficiency, and the carbon emission indicators include total carbon dioxide emissions and carbon emissions per unit energy consumption. Extract the specific values ​​of the above six indicators for each group of schemes from the scheme evaluation results, and fill the values ​​into the corresponding cells of the matrix one by one according to the correspondence of "scheme number-indicator type", ensuring that the data in each cell is completely matched with the scheme and indicator, so as to obtain the comprehensive evaluation matrix of the park's energy schemes.

[0059] (2) Differentiated normalization is applied to different types of indicators in the comprehensive evaluation matrix of the scheme: For economic indicators, since lower values ​​are better, the calculation method is: (maximum value of indicator - value of indicator in this plan) ÷ (maximum value of indicator - minimum value of indicator). If the maximum value and the minimum value are equal, the normalized value is 1. For energy efficiency indicators (total system energy efficiency, unit conversion efficiency), since higher values ​​are better, the calculation method is: (the value of the indicator in this scheme - the minimum value of the indicator) ÷ (the maximum value of the indicator - the minimum value of the indicator). For carbon emission indicators, since lower values ​​are better, the calculation method is the same as for economic indicators.

[0060] By calculating the index values ​​of all cells in the matrix one by one using this method, and replacing the original values, a standardized evaluation matrix for park energy is obtained.

[0061] (3) Preset indicator weights based on park operation priority: The combined weight of economic indicators is 40%, of which total operating costs account for 25% and unit energy costs account for 15%. The combined weight of energy efficiency indicators is 30%, of which total system energy efficiency accounts for 20% and unit conversion efficiency accounts for 10%. The combined weight of carbon emission indicators is 30%, of which total emissions account for 20% and emissions per unit of energy consumption account for 10%.

[0062] For each initial configuration scheme, the normalized values ​​of each indicator in the corresponding row of the standardized evaluation matrix are multiplied by the preset weights of their respective indicators. The sum of all the product results is then obtained to obtain the comprehensive score of the scheme. For example, the normalized value of total operating cost of a certain scheme is 0.8×25% + unit energy cost 0.7×15% + total system energy efficiency 0.9×20% + unit conversion efficiency 0.8×10% + total emissions 0.9×20% + unit energy consumption emissions 0.8×10% = 0.835, which is the comprehensive score of the scheme. The comprehensive scores of all initial configuration schemes are then generated.

[0063] (4) Arrange all initial configuration schemes in descending order of comprehensive score, with the highest-scoring scheme ranked first, and so on down. If there are schemes with the same score, prioritize the scheme with the higher normalized carbon emission index value. During the arrangement process, label each scheme with its ranking number, scheme number, comprehensive score, and key indicators to form a structured list, ensuring that the information of each item in the list is complete and easy to verify later, thus obtaining the scheme ranking list for park energy.

[0064] (5) Select the top 3 schemes from the scheme ranking list for feasibility review. The review focuses on dynamic operating conditions: simulating seasonal load changes to check whether the equipment capacity in the scheme can still meet the load demand; verifying the impact of extreme weather to determine whether the energy storage system can make up for the power supply gap; and checking the grid dispatch requirements to confirm whether the scheme can adjust the energy procurement and equipment operation mode. Schemes that can meet the optimization constraints under all dynamic conditions during the review process are judged to have passed the verification. The highest-ranked scheme that has passed the verification is output as the final result to obtain the optimal energy allocation scheme for the park.

[0065] The above steps ensure the implementation of constraints by accurately transforming optimization constraints into model boundary conditions. The initial configuration scheme generated by multi-scenario simulation covers different market changes. Feasibility verification and multi-dimensional evaluation ensure the compliance and effectiveness of the scheme. Normalization and weighted fusion make the scheme ranking more objective. Finally, the optimized configuration scheme output by dynamic review has both optimality and stability, providing a scientific and reliable basis for the subsequent allocation of energy equipment capacity in the park, and effectively improving the accuracy and comprehensive benefits of energy allocation.

[0066] S5: Based on the optimized configuration scheme, allocate the capacity of the park's energy equipment to obtain the operating parameters of the park's energy equipment; More preferably, the step of allocating the capacity of the park's energy equipment according to the optimized configuration scheme to obtain the operating parameters of the park's energy equipment includes: S5.1: Identify the capacity configuration requirements of photovoltaic power generation units, energy storage systems, and combined heat and power units in the optimized configuration scheme, and obtain the capacity allocation task set of the park's energy equipment; S5.2: Based on the capacity allocation task set, send a capacity preset instruction to the corresponding energy equipment to obtain the initial operating parameters of the energy equipment in the park; S5.3: Perform a coordination verification on the initial operating parameters of the equipment to ensure the compatibility of the equipment operating parameters at the system level and obtain coordinated operating parameters; S5.4: The coordinated operating parameters are sent to the corresponding energy equipment for execution, and the operating status feedback of the energy equipment in the park is obtained; S5.5: Based on the equipment operation status feedback, perform consistency verification between the actual operating parameters and the target parameters to obtain the operating parameters of the park's energy equipment.

[0067] In practical implementation, S5.1 extracts specific capacity configuration information for photovoltaic power generation units, energy storage systems, and combined heat and power (CHP) units from the optimized configuration scheme. For photovoltaic power generation units, the installed capacity and capacity distribution corresponding to the arrangement of photovoltaic modules must be clearly defined. For energy storage systems, the total energy storage capacity, maximum charging and discharging power, and charging and discharging time limits must be determined. For CHP units, the rated power generation capacity and rated heating capacity must be clearly defined. The capacity requirements of the three types of equipment are organized according to the structure of "equipment type - target capacity - configuration range - time requirement," with each item corresponding to a specific capacity allocation task, forming a capacity allocation task set for the park's energy equipment.

[0068] S5.2 Based on the task requirements of each device in the capacity allocation task set, establish communication connections with the corresponding energy equipment control systems. Photovoltaic power generation units connect to the inverter control system, energy storage systems connect to the battery management system, and combined heat and power (CHP) units connect to the unit control cabinet. For photovoltaic power generation units, send a capacity preset command containing the target installed capacity and initial operating voltage range; for energy storage systems, send a capacity preset command containing the target energy storage capacity and initial charge / discharge current thresholds; for CHP units, send a capacity preset command containing the target power generation and initial heating temperature. Receive response data returned by the control systems of each device, including the initial output current of the photovoltaic inverter, the initial state of charge of the energy storage battery, and the initial speed of the CHP unit. Classify and organize this data according to equipment type to obtain the initial operating parameters of the energy equipment in the park.

[0069] S5.3 establishes system-level coordination verification rules. First, it verifies power balance by calculating the sum of the initial output power of the photovoltaic (PV) power generation unit, the initial charging / discharging power of the energy storage system, and the initial power generation of the cogeneration unit. It determines whether this matches the current electricity load of the park. If the PV output power is too high, causing the total power to exceed the load, the initial charging power of the energy storage system is adjusted to absorb the excess energy. Second, it verifies parameter compatibility by checking whether the initial output voltage of the PV power generation unit and the initial power generation voltage of the cogeneration unit are consistent with the rated voltage of the park's power grid. If there is a deviation, the voltage regulation module of the PV inverter or the excitation system of the cogeneration unit is adjusted. Finally, it verifies timing coordination to ensure that the charging / discharging timing of the energy storage system matches the peak PV output and peak electricity load, avoiding time-period mismatches. The adjusted parameters are then compiled to obtain the coordinated operating parameters.

[0070] S5.4 uses industrial Ethernet or wireless communication modules to precisely distribute coordinated operating parameters to the corresponding energy equipment control systems according to device IDs. Photovoltaic power generation units receive adjusted output power and voltage parameters, energy storage systems receive adjusted charge / discharge power and the initial state of charge control range of the energy storage batteries, and combined heat and power (CHP) units receive adjusted power generation and heating temperature parameters. After each device executes its operating operations according to the parameters, it collects real-time operating data through its built-in sensors, including actual output, voltage, current, and temperature information every 5 minutes. This data is then packaged and fed back to the park's energy management center, forming a feedback mechanism for the operating status of the park's energy equipment.

[0071] S5.5 extracts the actual operating parameters of each device from the equipment operation status feedback. The photovoltaic power generation unit extracts the actual installed capacity and actual output power, the energy storage system extracts the actual energy storage capacity and actual charging and discharging power, and the combined heat and power unit extracts the actual power generation capacity and actual heating capacity.

[0072] These actual operating parameters are compared one by one with the target parameters in the optimized configuration scheme (specific capacity configuration information extracted from the optimized configuration scheme), and the deviation value is calculated. If the deviation value is within the preset allowable range, the actual parameters are determined to be consistent with the target parameters; if the deviation exceeds the range, the process returns to the coordination verification stage to readjust the parameters until the deviation meets the requirements. The parameters that finally meet the consistency requirements are determined as the operating parameters of the park's energy equipment.

[0073] The above steps ensure clear task allocation by accurately identifying equipment capacity configuration requirements, obtain initial parameters by issuing pre-set instructions based on tasks, ensure equipment operation compatibility through system-level collaborative verification, and ensure that actual operating parameters meet target requirements through status feedback and consistency verification after parameter issuance. The final operating parameters enable photovoltaic power generation units, energy storage systems and cogeneration units to operate efficiently and collaboratively, fully utilize equipment efficiency, and ensure the stable, economical and environmentally friendly operation of the park's energy system.

[0074] More preferably, S6: The performance of the park energy equipment after parameter configuration is monitored, and the multi-market coupling model is updated according to the real-time update of the market data set. When the updated multi-market coupling model allocates equipment parameters and optimizes the capacity of the park energy equipment to the target state, the target capacity configuration scheme of the park energy equipment is obtained.

[0075] In practice, power and voltage sensors are installed at the output of the photovoltaic power generation unit after parameter configuration. State-of-charge (SOC) and current sensors are installed in the battery circuit of the energy storage system. Power transmitters and temperature sensors are installed on the power generation bus and heating main network of the combined heat and power (CHP) unit, respectively. All sensors collect operating parameters in real time at a frequency of 1 minute per measurement. These parameters include actual photovoltaic output, energy storage charging and discharging current, SOC values ​​installed in the battery circuit, and actual CHP power generation and heating temperature. The collected data is transmitted to the park's energy management center via industrial Ethernet. The management center analyzes the data in real time to determine whether each parameter is within a preset normal range. If a parameter exceeds the range, an audible and visual alarm is triggered, and the abnormal time and value are recorded, forming continuous and traceable performance monitoring data for the park's energy equipment.

[0076] By connecting the park's energy management system to the real-time data interface of the electricity trading platform, real-time electricity market transaction prices are obtained every 5 minutes. The system also connects to the supply and demand monitoring platform of the heat supply company to collect real-time data on gas supply volume and pressure in the heat pipeline network, as well as heat demand data for various areas within the park. Furthermore, it connects to the information release system of the carbon trading authority to obtain real-time carbon quota transaction prices, remaining quotas in the park, and compliance progress data. This real-time data is then integrated into the original market dataset, replacing the corresponding historical data within the dataset. Simultaneously, a moving average method is used to remove outliers, ensuring data accuracy and timeliness, resulting in an updated park energy market dataset.

[0077] The updated market data set is input into the original multi-market coupling model. First, the weight coefficients of each market variable in the model are adjusted. For example, when the real-time electricity price rises, the influence weight of the electricity market variable in the model is increased. Second, the energy efficiency constraint parameters in the model are corrected according to the changes in the actual efficiency of the equipment in the equipment performance monitoring data. For example, if the actual efficiency of the cogeneration unit decreases by 5%, the energy efficiency constraint threshold of the unit in the model is lowered by 5%. Finally, the latest equipment performance monitoring data is substituted into the model for simulation verification. The expected energy configuration results output by the model are compared with the actual operating status of the equipment. If the deviation exceeds 5%, the model parameters are readjusted until the deviation meets the requirements, thus obtaining the updated multi-market coupling model for the park's energy sector.

[0078] The updated multi-market coupling model, based on real-time market data and optimization constraints, recalculates the capacity configuration parameters of each device: when carbon allowance prices rise, it increases the installed capacity allocation of photovoltaic power generation units and reduces the power generation capacity of combined heat and power (CHP) units to reduce carbon emissions; when heat demand increases, it increases the heating capacity of CHP units and adjusts the discharge period of energy storage systems to ensure electricity supply for heat production. After calculation, it outputs the target installed capacity of photovoltaic power generation units, the target energy storage capacity of energy storage systems, and the target power generation and heating capacity of CHP units, obtaining the updated model-allocated parameters for park energy equipment.

[0079] Set target state standards for equipment capacity: the expected operating cost corresponding to the equipment capacity configuration is lower than the minimum target cost, the expected system energy efficiency is higher than the maximum energy efficiency target, and the expected total carbon emissions are lower than the carbon emission constraints. Substitute the equipment parameters assigned by the model into the calculation logic to calculate the expected operating cost, expected system energy efficiency, and expected carbon emissions, and compare each expected indicator with the target state standards. If all indicators meet the standards, it is determined that the equipment capacity has been optimized to the target state; if any indicator is not met, return to the market data update stage, re-acquire the latest data, and repeat the model update and parameter allocation steps.

[0080] When the expected indicators corresponding to the equipment parameters allocated by the model fully meet the target state standards, the parameters are organized according to equipment type: the final installed capacity, installation area, and output adjustment range of the photovoltaic power generation unit are clarified; the final energy storage capacity, charging and discharging period, and current limit of the energy storage system are clarified; and the final power generation capacity, heating capacity, and start-up and shutdown time of the combined heat and power unit are clarified. At the same time, the applicable market conditions and implementation precautions are marked, forming a complete document containing equipment capacity, operating parameters, applicable scenarios, and implementation details, thus obtaining the target capacity configuration scheme for the park's energy equipment.

[0081] The above steps ensure that the equipment's operating status is controllable through real-time performance monitoring, and that the capacity configuration is always adapted to market changes through dynamic updates based on market data and iterative adjustments based on model iterations. After repeated verification until the target state is reached, the final target capacity configuration scheme has both dynamic adaptability and optimality. It can ensure the balance of economy, energy efficiency and environmental protection of the park's energy system under different market conditions, and effectively improve the long-term stability and comprehensive utilization benefits of the park's energy capacity configuration.

[0082] Understandably, S5 allocates capacity and sets parameters for park energy equipment (such as photovoltaic, energy storage, and combined heat and power units) according to the optimized configuration scheme. This process includes sending preset instructions, performing system coordination verification, and finally ensuring that the actual operating parameters of the equipment match the target parameters through consistency verification. Therefore, S5 ultimately outputs and sends a set of operational parameters that have undergone coordination and consistency verification and are ready for immediate execution to the equipment. At this point, the equipment is already in operation according to these verified configuration parameters (i.e., operating parameters). S6 begins with "performance monitoring of park energy equipment after parameter configuration." Here, "after parameter configuration" means that S5 has been completed and the equipment is operating according to the operating parameters output by S5. That is, S6, based on the equipment operation already achieved in S5, conducts a new round of capacity configuration optimization aimed at the long-term optimal state through continuous monitoring and dynamic model updates, thereby obtaining the final target capacity configuration scheme. The two represent a progressive relationship between initial configuration operation and continuous monitoring and optimization to the final goal.

[0083] The execution entity of the aforementioned method for optimizing energy capacity allocation in a multi-market coupled industrial park includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application embodiment: a server, a terminal, etc. In other words, the aforementioned method for optimizing energy capacity allocation in a multi-market coupled industrial park can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0084] Embodiment 2 of the present invention provides a multi-market coupled park energy capacity optimization allocation system, the functional modules of which are as follows: Figure 2 As shown, the multi-market coupled park energy capacity optimization and allocation system can be installed in an electronic device. Depending on the functions implemented, the multi-market coupled park energy capacity optimization and allocation system may include a data aggregation module, a dynamic model construction module, a constraint setting module, an optimization generation module, a capacity allocation module, and a monitoring and optimization module. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, stored in the memory of the electronic device.

[0085] In this embodiment, the functions of each module / unit are as follows: The data aggregation module is used to aggregate the electricity market transaction prices, heat market supply and demand parameters, and carbon market emission quota information of the park's energy into a market data set for the park's energy. The model dynamic construction module is used to adaptively generate the coupling factor of the park's energy based on historical market fluctuation data and park energy load characteristics, and dynamically construct the multi-market coupling model of the park's energy based on the coupling factor. The constraint setting module is used to construct the optimal constraints for the park's energy based on cost minimization, energy efficiency maximization, and carbon emission requirements. The optimization generation module is used to apply the optimization constraints to the multi-market coupling model to obtain the optimal energy allocation scheme of the park. The capacity allocation module is used to allocate the capacity of the park's energy equipment according to the optimized configuration scheme, and obtain the operating parameters of the park's energy equipment. The monitoring and optimization module is used to monitor the performance of the park's energy equipment after parameter configuration, update the multi-market coupling model according to the real-time update of the market data set, and obtain the target capacity configuration scheme of the park's energy equipment when the updated multi-market coupling model allocates equipment parameters and optimizes the capacity of the park's energy equipment to the target state.

[0086] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0087] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0088] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0089] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0090] Embodiment 3 of the present invention provides a terminal, including a processor and a storage medium; the storage medium is used to store instructions; the processor is used to perform operations according to the instructions to execute the steps of the method.

[0091] Embodiment 4 of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method.

[0092] Compared with the prior art, the beneficial effects of the present invention include at least the following: This invention accurately collects and aggregates market data on electricity market transaction prices, heat market supply and demand parameters, and carbon market emission quotas across multiple dimensions within a park. This eliminates outliers and redundant information, resulting in a highly accurate, complete, and consistent market data set. This provides reliable foundational data for subsequent coupling factor generation and the construction of a multi-market coupling model, ensuring the scientific rigor of the park's energy capacity optimization. Furthermore, based on the structured decomposition results of historical market fluctuation data and pattern recognition results of the park's energy load characteristics, coupling factors are adaptively generated, and a multi-market coupling model is constructed. This model accurately captures the interactions between multiple markets, ensuring it fully aligns with actual market operation scenarios. This provides precise data support and a scientific model foundation for the park's energy capacity optimization, effectively improving the adaptability and rationality of the configuration scheme.

[0093] This invention constructs multi-objective optimization constraints based on cost minimization, energy efficiency maximization, and carbon emission requirements. After imposing constraints on a multi-market coupling model, it simulates multiple scenarios and selects the optimal configuration scheme. The energy equipment capacity of the park is allocated according to the scheme, and the synergy of operating parameters is verified. At the same time, the equipment performance is monitored in real time, and the model is updated according to market data until the equipment capacity is optimized to the target state. This ensures that the configuration scheme takes into account economy, energy efficiency, and environmental protection, and can dynamically adapt to market and load changes, effectively improving the accuracy, stability, and overall benefits of park energy capacity configuration.

[0094] This disclosure can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this disclosure.

[0095] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0096] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0097] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A method for optimizing the allocation of energy capacity in a multi-market coupled industrial park, characterized in that, include: Collect electricity market transaction prices, heat market supply and demand parameters, and carbon market emission quota information for the park's energy sector and compile them into a market data set for the park's energy sector; Based on historical market fluctuation data and park energy load characteristics, a distribution map of the market coupling intensity of park energy is constructed, thereby generating the coupling factor of park energy. Combined with the market data set, a multi-market coupling model of park energy is dynamically constructed. Based on the market data set, optimization constraints are constructed with the goals of cost minimization, energy efficiency maximization, and carbon emission requirements. Optimization constraints are applied to the coupled model to obtain an optimized energy configuration scheme for the park. The capacity of the park's energy equipment is allocated and verified according to the optimized configuration scheme to obtain the operating parameters of the park's energy equipment for configuring the park's energy equipment parameters. The performance of the park's energy equipment after parameter configuration is monitored, and the coupled model is updated according to the real-time update of the market data set to optimize the capacity of the park's energy equipment to the target state, thus obtaining the target capacity configuration scheme.

2. The method for optimizing the allocation of energy capacity in a multi-market coupled industrial park according to claim 1, characterized in that: The data collection includes electricity market transaction prices, heat market supply and demand parameters, and carbon market emission quota information for the park's energy sector, compiled into a market data set for the park's energy sector, comprising: Collect information on electricity market transaction prices, heat market supply and demand parameters, and carbon market emission quotas for energy in the industrial park; Based on the electricity market transaction prices, a price data sequence for park energy is generated; based on the heat market supply and demand parameters, a set of supply and demand parameters for park energy is generated; based on the carbon market emission quota information, quota data records for park energy are generated. By eliminating outliers and redundant information from the price data sequence, the supply and demand parameter set, and the quota data record, a market data set for energy in the park is obtained.

3. The method for optimizing the allocation of energy capacity in a multi-market coupled industrial park according to claim 1, characterized in that: The process involves constructing a market coupling intensity distribution map of park energy based on historical market fluctuation data and park energy load characteristics, thereby generating coupling factors for park energy, and dynamically constructing a multi-dimensional market coupling model for park energy in conjunction with market data sets, including: Based on the time scale, historical market fluctuation data is decomposed into long-term trend components, cyclical fluctuation components, and short-term random components to obtain structured market data for energy in the park. Based on the energy consumption patterns of the park's energy load characteristics, the park's basic load, adjustable load, and critical load are identified, resulting in a set of load characteristic patterns for the park's energy. Spatiotemporal correlation matching is performed between different market variables in the structured market data and different loads in the load characteristic pattern set. The degree of influence of each market variable on different loads is calculated and quantified into a weight value to obtain the dynamic influence weight set of park energy. Using different market variables and different loads as the rows and columns of a matrix, and with the corresponding weight values ​​as the values ​​of the unit cells of the corresponding matrix, the dynamic influence weight set is reconstructed into a coupling strength evaluation matrix; The correlation strength among the electricity market, heat market and carbon market in the coupling strength assessment matrix is ​​quantified to construct a distribution map of market coupling strength of park energy, and the coupling factor of park energy is adaptively obtained. Based on the interaction between the electricity market, heat market, and carbon market in the aforementioned market coupling intensity distribution map, an initial coupling architecture for park energy is constructed. By inputting the market data set and the coupling factor into the initial coupling architecture, a multi-market coupling model for the park's energy is obtained.

4. The method for optimizing the allocation of energy capacity in a multi-market coupled industrial park according to claim 3, characterized in that: The process of quantifying the correlation strength among the electricity market, heat market, and carbon market in the coupling strength assessment matrix to construct a market coupling strength distribution map of the park's energy sector, and adaptively obtaining the coupling factor of the park's energy sector, includes: Extract the electricity market index vector, heat market index vector, and carbon market index vector from the coupling strength assessment matrix to obtain a multi-market index vector set for energy in the park. The multi-market indicator vector set is projected onto the vector space model, and the correlation strength between different markets in the coupling strength evaluation matrix is ​​adaptively determined based on the cosine value of the angle between the vectors to obtain the primary correlation strength data of park energy. The primary correlation strength data is normalized to obtain the standardized correlation strength value of the park's energy. Using different markets as nodes and the standardized correlation strength value as edges, a market coupling strength distribution map of park energy is constructed; The final coupling strength coefficient is determined based on the connection density of the nodes in the market coupling strength distribution map. Based on the standardized correlation strength value and the final coupling strength coefficient, the coupling factor of the park's energy is determined.

5. The method for optimizing the allocation of energy capacity in a multi-market coupled industrial park according to claim 1, characterized in that: The optimization constraints, based on market data sets and aimed at minimizing costs, maximizing energy efficiency, and meeting carbon emission requirements, include: Based on the market data set, energy procurement costs, equipment operation and maintenance costs, and market transaction costs are obtained to determine the cost elements of energy in the park, and the minimum target cost of energy in the park is constructed based on the cost elements. Track the conversion and transmission paths of energy in the park system, and determine the maximum energy efficiency target of the park's energy based on the energy efficiency of each link in the conversion and transmission path; Obtain direct and indirect emission data of energy in the park during the energy conversion process to obtain carbon emission constraints for energy in the park; By coordinating the minimum target cost, the maximum energy efficiency target, and the carbon emission constraint, the optimal constraints for energy in the park are obtained.

6. The method for optimizing the allocation of energy capacity in a multi-market coupled industrial park according to claim 1, characterized in that: The process of applying optimization constraints to the coupled model to obtain an optimized energy allocation scheme for the park includes: The optimization constraints are transformed into the boundary conditions of the multi-market coupling model, resulting in the coupling model after constraint injection. The energy allocation scenarios under different market conditions are simulated in the coupled model after the constraint injection to obtain the initial energy allocation scheme of the park; The feasibility of the initial configuration scheme is verified and its benefits are evaluated to obtain the scheme evaluation results. Based on the evaluation results of the proposed schemes, the optimal configuration scheme is selected from the initial configuration schemes to obtain the optimized configuration scheme for park energy.

7. The method for optimizing the allocation of energy capacity in a multi-market coupled industrial park according to claim 6, characterized in that: The step of selecting the optimal configuration scheme from the initial configuration schemes based on the evaluation results of the aforementioned schemes, to obtain the optimized configuration scheme for park energy, includes: The economic indicators, energy efficiency indicators, and carbon emission indicators from the proposed scheme evaluation results are mapped into a matrix to obtain the comprehensive evaluation matrix of the park's energy schemes. The comprehensive evaluation matrix of the proposed scheme is normalized to obtain a standardized evaluation matrix for park energy. The normalized values ​​in the standardized evaluation matrix are weighted and fused based on preset indicator weights to generate a comprehensive score for the initial configuration scheme. The initial configuration schemes are sorted according to the comprehensive scores to obtain a sorted list of energy schemes for the park. The feasibility of the top-ranked schemes in the scheme ranking list is verified, and the schemes that pass the verification are output as the optimized energy allocation schemes for the park.

8. The method for optimizing the allocation of energy capacity in a multi-market coupled industrial park according to claim 1, characterized in that: The process of allocating and verifying the capacity of park energy equipment according to the optimized configuration scheme to obtain the operating parameters of park energy equipment for configuring park energy equipment parameters includes: Identify the capacity configuration requirements of photovoltaic power generation units, energy storage systems, and combined heat and power units in the optimized configuration scheme to obtain the capacity allocation task set for energy equipment in the park. Based on the capacity allocation task set, a capacity preset instruction is sent to the corresponding energy equipment to obtain the initial operating parameters of the energy equipment in the park. The initial operating parameters of the device are checked for compatibility to ensure the compatibility of the device operating parameters at the system level, and the coordinated operating parameters are obtained. The coordinated operating parameters are sent to the corresponding energy equipment for execution, and feedback on the operating status of the energy equipment in the park is obtained. Based on the feedback of the equipment's operating status, the actual operating parameters and target parameters are checked and adjusted for consistency. The parameters that finally meet the consistency check requirements are determined as the operating parameters of the park's energy equipment to configure the park's energy equipment parameters.

9. A multi-market coupled park energy capacity optimization allocation system, operating the method described in any one of claims 1-8, characterized in that, The system includes: The data aggregation module collects electricity market transaction prices, heat market supply and demand parameters, and carbon market emission quota information for the park's energy sector and aggregates them into a market data set for the park's energy sector. The dynamic model building module dynamically constructs a multi-market coupling model for the park's energy sector. The constraint setting module constructs optimization constraints for the park's energy sector. The optimization generation module applies the optimization constraints to the multi-market coupling model to obtain an optimized configuration scheme for the park's energy sector. The capacity allocation module allocates and verifies the capacity of the park's energy equipment to obtain operating parameters for configuring the park's energy equipment parameters. The monitoring and optimization module monitors the performance of the park's energy equipment after parameter configuration to obtain a target capacity configuration scheme for the park's energy equipment.

10. A terminal, comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to perform the steps of the method according to any one of claims 1-8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method according to any one of claims 1-8.

Images