Industrial park resource operation optimization method based on electric carbon space-time distribution characteristics

Abstract

The invention discloses an industrial park resource operation optimization method based on electric carbon space-time distribution characteristics, and relates to the technical field of energy low-carbon optimization, and the method comprises the steps: collecting energy carbon operation data of an industrial park, and carrying out the time synchronization, abnormality elimination and unit standardization processing, and obtaining a multi-source synchronous energy carbon data matrix; performing multi-objective collaborative optimization calculation on the park energy carbon density field distribution diagram to obtain a preliminary operation optimization scheme; carrying out extreme scene verification and nonlinear performance correction on the initial operation optimization scheme to obtain a carbon sensing operation optimization result; performing dynamic execution mapping and energy efficiency response calculation on the carbon sensing operation optimization result to generate an execution state data stream; and performing time sequence comparative analysis and energy-carbon benefit evaluation on the execution state data flow to generate a carbon peak clipping effect evaluation report. And the accuracy, reliability and sustainability of industrial park energy and carbon management are enhanced.

Description

Technical Field

[0001] This invention relates to the field of energy low-carbon optimization technology, and in particular to a method for optimizing the operation of industrial park resources based on the spatiotemporal distribution characteristics of carbon electricity. Background Technology

[0002] With the diversification of energy structures and the accelerated low-carbon transformation of industrial parks, energy operation monitoring and carbon emission collaborative management within these parks have gradually become important research directions in energy informatization. Existing industrial park resource regulation systems largely rely on energy consumption monitoring, carbon emission accounting, and energy efficiency optimization, using energy management systems (EMS) and carbon emission monitoring platforms to collect and manage park energy and carbon data. In this process, researchers generally employ a combination of time-series statistical analysis and energy consumption model fitting to quantitatively describe energy use efficiency and carbon emission characteristics. Some advanced methods have introduced spatiotemporal characteristic-based energy consumption prediction models or zonal characteristic-based carbon emission estimation frameworks to identify high-energy-consuming and high-carbon-emission areas.

[0003] Industrial park operation optimization often requires balancing energy supply, carbon emission control, and economic benefits under multiple objective constraints. Traditional optimization strategies typically employ linear programming, genetic algorithms, or heuristic solutions to generate operational plans based on a single energy consumption index or carbon intensity target. While these methods can reduce carbon emissions or improve energy efficiency to some extent, they suffer from response lag and local optima when dealing with high-dimensional spatiotemporal data and nonlinear coupling relationships. Especially in scenarios where energy-carbon relationships exhibit strong dynamism and spatial heterogeneity, a single model struggles to comprehensively characterize multidimensional energy-carbon interactions, leading to discrepancies between the optimization results and the actual energy-carbon distribution. Furthermore, existing optimization result verification largely relies on offline data backtesting, lacking real-time feedback correction mechanisms, making it difficult to adapt to dynamic adjustment needs under extreme load fluctuations or abnormal carbon emission scenarios. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides an industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of electric carbon to solve the problems of insufficient characterization of energy-carbon coupling relationship and lack of dynamic feedback correction of operation optimization results in the prior art.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: This invention provides a method for optimizing the operation of industrial park resources based on the spatiotemporal distribution characteristics of electric carbon, which includes collecting energy and carbon operation data of industrial park, and performing time synchronization, anomaly removal and unit standardization processing to obtain a multi-source synchronized energy and carbon data matrix. Spatial topological mapping and temporal hierarchical calculation were performed on the carbon data matrix of multi-source synchronous energy to construct a carbon-energy coupling distribution model. The carbon-energy coupling distribution model was then used to generate a carbon-energy density field distribution map of the park through equipotential region division and density gradient analysis. The carbon density field distribution map of the park was used for multi-objective collaborative optimization calculations to obtain a preliminary operation optimization scheme; The initial operational optimization scheme was verified through extreme scenarios and nonlinear performance correction to obtain the carbon sensing operational optimization results; The carbon sensing operation optimization results are dynamically executed and energy efficiency response is calculated to generate an execution status data stream; The execution status data stream is analyzed through time-series comparison and energy-carbon benefit assessment to generate a carbon peak shaving effect assessment report.

[0007] As a preferred embodiment of the industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of electric carbon as described in this invention, the specific steps for collecting energy and carbon operation data of the industrial park and performing time synchronization, anomaly removal, and unit standardization processing to obtain a multi-source synchronized energy and carbon data matrix are as follows. The energy and carbon operation data of the industrial park are integrated by spatial location index and sorted by time granularity to form a preliminary energy and carbon operation dataset. The preliminary energy carbon operation dataset is smoothed by interpolation and time alignment of adjacent time periods to obtain a synchronous energy carbon data sequence. Then, through abnormal fluctuation removal and data correction, a clean energy carbon dataset is obtained. The cleaned energy carbon dataset is normalized and mapped nonlinearly to output a multi-source synchronous energy carbon data matrix.

[0008] As a preferred embodiment of the industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of electrocarbon as described in this invention, the specific steps for constructing a carbon-energy coupled distribution model by performing spatial topological mapping and temporal hierarchical calculation on the multi-source synchronous energy carbon data matrix are as follows. The carbon data matrix of multi-source synchronous energy is mapped by neighboring units and projected by spatial topology to form initial values ​​for spatial coupling. Then, through segmented accumulation and exponential decay processing by historical time windows, time-series hierarchical coupled data is generated. By integrating time-series hierarchical coupled data through spatial-temporal interaction and difference balancing, a carbon energy coupled distribution model is formed.

[0009] As a preferred embodiment of the industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of carbon electricity described in this invention, the specific steps for generating an energy-carbon density field distribution map of the park by dividing the carbon energy coupled distribution model into equipotential regions and performing density gradient analysis are as follows. The carbon energy coupling distribution model is divided into spatial equipotential regions to generate a carbon energy coupling density region, and a carbon energy density gradient field is generated through density gradient analysis. Image mapping processing is performed on the carbon energy density gradient field to generate a carbon energy density field distribution map of the park.

[0010] As a preferred embodiment of the industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of carbon energy density described in this invention, the specific steps for performing image mapping processing on the carbon energy density gradient field to generate an energy-carbon density field distribution map of the park are as follows. The carbon energy density gradient field is subjected to noise filtering and spatial normalization to generate a gradient normalization matrix, and a preliminary pixel value matrix is ​​generated through nonlinear mapping calculation. The initial pixel value matrix is ​​spatially smoothed and made continuous to generate a continuous energy-carbon distribution matrix. Then, through spatial integration and formatting, an energy-carbon density field distribution map of the park is generated.

[0011] As a preferred embodiment of the industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of electrocarbon as described in this invention, the preliminary operation optimization scheme is obtained by performing multi-objective collaborative optimization calculations on the park's energy carbon density field distribution map. The specific steps are as follows: Energy flow, carbon emissions, and load information were extracted from the energy and carbon density field distribution map of the park and a multi-objective collaborative optimization function was constructed through interactive calculation. Constraint projection and space-time mapping are performed on the multi-objective collaborative optimization function to generate a preliminary feasible solution matrix. Through multi-objective interactive integration and local priority accumulation, a preliminary operational optimization scheme is formed.

[0012] As a preferred embodiment of the industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of electrocarbon as described in this invention, the step of obtaining carbon-sensing operation optimization results by verifying the preliminary operation optimization scheme through extreme scenarios and correcting nonlinear performance includes the following specific steps. The initial operation optimization scheme was simulated and constrained to obtain an energy-carbon synergistic optimization set. Multi-dimensional data fusion and dynamic simulation were then carried out to construct a carbon-energy virtual twin. High-precision time-series simulation and performance calculation are performed on a carbon energy virtual twin to generate carbon energy performance prediction results. Through extreme scenario simulation and nonlinear correction, carbon sensing operation optimization results are obtained.

[0013] As a preferred embodiment of the industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of carbon dioxide described in this invention, the specific steps for generating an execution status data stream by dynamically executing the carbon-sensing operation optimization results through dynamic execution mapping and energy efficiency response calculation are as follows. The time-series energy efficiency response is calculated based on the carbon sensing operation optimization results to generate an execution state sequence; The execution state sequence is subjected to nonlinear interactive calculation and local gradient mapping to obtain the execution energy efficiency data stream; The execution energy efficiency data stream is integrated with time series and spatial location to form an execution status data stream.

[0014] As a preferred embodiment of the industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of carbon dioxide described in this invention, the specific steps for integrating the execution energy efficiency data stream through time series and spatial location to form an execution status data stream are as follows. The energy efficiency data stream is standardized according to time series to obtain standardized time series data. Standardized time series data are spatially mapped and fused according to the park layout to generate a preliminary spatial integration matrix. Then, through time interpolation and spatial smoothing, an execution status data stream is generated.

[0015] As a preferred embodiment of the industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of electrical carbon described in this invention, the specific steps for generating a carbon peak reduction effect evaluation report by performing time-series comparative analysis and energy-carbon benefit assessment on the execution status data stream are as follows: Time series features are extracted from the execution status data stream to obtain a time series feature set; The time-series feature set is used to quantify the energy and carbon benefits to generate local carbon peak reduction benefits. Time-series comparative analysis and comprehensive integration are then performed to generate a carbon peak reduction effect evaluation report.

[0016] The beneficial effects of this invention are as follows: By performing spatial topological mapping and temporal hierarchical calculation on the carbon data matrix of multi-source synchronous energy, a carbon-energy coupled distribution model is constructed, which realizes a fine characterization of the energy and carbon operation characteristics of industrial parks in space and time, providing a basic data structure for subsequent density field generation and optimization calculation, thereby improving the pertinence and executability of resource operation optimization; by performing virtual calculation and extreme scenario self-calculation correction on the preliminary operation optimization scheme in the carbon sensing twin, highly reliable prediction and dynamic correction of the optimization scheme are realized, enabling the park resource operation optimization to take into account energy efficiency improvement, carbon emission reduction and actual operating condition adaptability, thereby enhancing the accuracy, reliability and sustainability of energy and carbon management in industrial parks. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1This is a flowchart of a resource operation optimization method for industrial parks based on the spatiotemporal distribution characteristics of carbon dioxide.

[0019] Figure 2 A flowchart for data preprocessing.

[0020] Figure 3 A flowchart for multi-objective collaborative optimization.

[0021] Figure 4 This is a flowchart for evaluating the carbon peak reduction effect. Detailed Implementation

[0022] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0023] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0024] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0025] Reference Figures 1-4 This is one embodiment of the present invention, which provides a method for optimizing the operation of industrial park resources based on the spatiotemporal distribution characteristics of electrocarbon, including the following steps: S1. Collect energy and carbon operation data of the industrial park, and perform time synchronization, anomaly removal and unit standardization to obtain a multi-source synchronized energy and carbon data matrix.

[0026] S1.1 Integrate the energy and carbon operation data of the industrial park by spatial location index and sort them by time granularity to form a preliminary energy and carbon operation dataset.

[0027] Furthermore, the energy and carbon operation data of the industrial park is indexed according to the specific coordinates of each spatial location. Energy and carbon operation data belonging to the same spatial unit are integrated to ensure that the data within each spatial unit is arranged in chronological order and with a unified time granularity, such as sorting by minute, hour, or day. During the integration process, energy and carbon operation data from different energy sources or different monitoring points are merged so that the data at each time point form a continuous record under the spatial location index, thereby obtaining a preliminary energy and carbon operation dataset containing a complete spatial location index and a unified time order.

[0028] S1.2. Perform smooth interpolation and time alignment on the preliminary energy carbon operation dataset to obtain a synchronous energy carbon data sequence. Then, through abnormal fluctuation removal and data correction, obtain a cleaned energy carbon dataset.

[0029] Furthermore, the energy and carbon operation data of adjacent time periods under each spatial location index are smoothed by interpolation according to time sequence. Linear interpolation or spline interpolation methods are used to fill any possible time gaps, so that the energy and carbon operation data of consecutive time points form a smooth transition. The time series after smoothing interpolation is time-aligned according to a uniform time granularity to ensure that the energy and carbon operation data under different spatial location indices correspond precisely at the same time node, generating a continuous and complete synchronous energy and carbon data sequence. Abnormal fluctuations in the synchronous energy and carbon data sequence are removed, and outliers that exceed the reasonable fluctuation range of energy and carbon operation are identified and excluded, such as instantaneous abnormal energy peaks or abnormal decreases in carbon emissions. The removed data is then corrected by averaging or interpolation of adjacent time periods, so that the time series after anomaly removal is continuous and smooth, forming a clean energy and carbon dataset with complete spatial location indices, uniform time granularity, and corrected abnormal fluctuations.

[0030] It should also be noted that the reasonable fluctuation range is determined by calculating the mean and standard deviation of the energy and carbon data. For example, assuming the mean of the energy and carbon data for a certain period is 100 and the standard deviation is 10, then the reasonable fluctuation range can be defined as 90 to 110 (i.e., mean ± 2 times the standard deviation). If the energy and carbon data at a certain moment exceeds this range, such as 150 or 50, it is considered an outlier and needs to be removed or corrected.

[0031] S1.3. The cleaned energy carbon dataset is normalized and nonlinearly mapped to energy carbon to output a multi-source synchronous energy carbon data matrix.

[0032] Furthermore, the cleaned energy carbon dataset is standardized according to the units of each energy and carbon emission indicator. For example, electricity is measured in kilowatt-hours and carbon emissions in carbon dioxide equivalents. By using linear scaling or normalization methods, each indicator is converted into a unified dimension, allowing direct comparison and calculation of energy carbon operation data from different sources and with different dimensions. The standardized cleaned energy carbon dataset is then subjected to nonlinear energy-carbon interaction mapping. Through regression analysis methods, such as multinomial regression, support vector regression (SVR), or neural networks, the nonlinear relationship between electricity and carbon emissions is calculated, forming energy-carbon interaction characteristics at each spatial location index and time node. After completing unit standardization and nonlinear energy-carbon interaction mapping, the processed data is integrated into a matrix form according to spatial location index and time series, outputting a multi-source synchronous energy carbon data matrix.

[0033] It should be noted that the expression for calculating the nonlinear relationship between electricity and carbon emissions is as follows: ; in: This represents the nonlinear relationship between electricity and carbon emissions. Carbon emissions; To standardize electricity consumption; The rate of change of electrical energy; It is a non-linear adjustment parameter; The basic equivalent carbon emission factor is defined under the condition that electricity consumption is at a baseline level and load fluctuations are small. The nonlinear incremental carbon emission impact coefficient that gradually emerges with the increase in electricity consumption levels; This represents the dynamic correction coefficient for the impact of fluctuations in electricity consumption on carbon emissions.

[0034] S2. Perform spatial topology mapping and temporal hierarchical calculation on the carbon data matrix of multi-source synchronous energy to construct a carbon energy coupling distribution model. Then, generate a carbon density field distribution map of the park through equipotential region division and density gradient analysis of the carbon energy coupling distribution model.

[0035] Existing methods typically perform simple spatial or temporal aggregation of multi-source carbon data, obtaining the energy consumption and carbon emission distribution of each region through static partitioning or periodic statistics. However, they do not adequately consider spatial topological relationships and temporal dynamic characteristics, making it difficult to fully reflect carbon-energy coupling relationships. The generated distribution maps are mostly two-dimensional or single-layer statistical maps, which are difficult to reflect the complexity of multi-time period and multi-source carbon interactions within the park, and also lack refined analysis based on density gradients.

[0036] This invention first performs spatial topological mapping on the multi-source synchronous energy carbon data matrix, associating each energy carbon data point in the spatial location of the park, and then captures temporal characteristics through hierarchical calculations using historical time windows to construct a carbon-energy coupling distribution model that can simultaneously reflect the coupling relationship between space and time. Subsequently, the park is finely spatially partitioned by dividing it into equipotential regions, and density gradient analysis is combined to reveal the changing trends of energy carbon density in different regions, generating an energy carbon density field distribution map of the park, thus achieving high-precision characterization of multi-source, multi-time period energy carbon characteristics within the park.

[0037] S2.1. The carbon data matrix of multi-source synchronous energy is mapped by neighboring units and projected by spatial topology to form initial values ​​for spatial coupling. Then, through segmented accumulation and exponential decay processing by historical time windows, time-series hierarchical coupled data is generated.

[0038] Furthermore, the data of each spatial location index in the multi-source synchronous energy-carbon data matrix is ​​associated and mapped with the data of neighboring spatial location indices. By calculating the spatial interactions and dependencies between neighboring spatial location indices, such as calculating the spatiotemporal fluctuations of energy-carbon flow changes or carbon emissions between adjacent locations, initial values ​​for spatial coupling are formed. This ensures that each spatial location index reflects the energy-carbon impact of surrounding spatial location indices in the spatial topology. The initial values ​​for spatial coupling are accumulated in segments according to historical time windows. The energy-carbon interaction features within each time window are accumulated and calculated in chronological order. Combined with the exponential decay method, the weight of energy-carbon impact from more distant historical time periods is gradually reduced, so that recent energy-carbon interaction features occupy a higher proportion in the accumulated results. Through the results of neighboring spatial location index association mapping, spatial topology projection, historical time window segmented accumulation and exponential decay processing, a time-series hierarchical coupled data containing spatial location indices, time-series hierarchies, and energy-carbon coupling features is generated.

[0039] It should be noted that the expression for calculating the spatial interactions and dependencies between neighboring spatial location indices is as follows: ; in: Spatial interactions and dependencies between neighboring spatial location indices; Spatial location index Spatial location index Spatial distance; This is the attenuation scale parameter for spatial effects; For at any time Below Spatial Location Index The corresponding electrical energy index values ​​within the space unit; For at any time Below, with spatial location index The corresponding electrical energy index values ​​within the space unit; At time respectively Below, with spatial location index The corresponding carbon emission index value within the spatial unit; For at any time Below, with spatial location index The corresponding carbon emission index value within the spatial unit; This serves as a benchmark for energy consumption normalization. This serves as a normalized baseline for carbon emissions.

[0040] S2.2. The time-series hierarchical coupled data are fused and the differences are balanced through spatial-temporal interaction to form a carbon energy coupled distribution model.

[0041] Furthermore, the energy-carbon coupling characteristics of each spatial location index in the time-series hierarchical coupled data at different time nodes are fused through spatial-temporal interaction. By calculating the energy-carbon interaction effects between adjacent spatial location indices and between different time nodes, such as analyzing the changing trends of energy flow and the periodic fluctuations of carbon emissions, a comprehensive spatial-temporal interaction characteristic is formed. During the fusion process, the differences in energy-carbon coupling characteristics of each spatial location index are balanced. By calculating the standard deviation and coefficient of variation of the energy-carbon interaction characteristics, the amplitude and dispersion of characteristic fluctuations in the spatial and temporal dimensions are measured. Characteristics that deviate significantly from the average level are adjusted to make the overall energy-carbon distribution tend to be balanced, while retaining local high and low differences. The carbon-energy coupling distribution model is generated from the results of spatial-temporal interaction fusion and difference balancing.

[0042] It should also be noted that the construction process of the carbon energy coupling distribution model is to form initial spatial coupling values ​​by mapping the carbon data matrix of multi-source synchronous energy through neighboring spatial location index association and spatial topological projection, and to generate time-series hierarchical coupling data by using historical time window segmented accumulation and exponential decay processing. Then, the time-series hierarchical coupling data is subjected to spatial-temporal interactive fusion and difference balancing processing to obtain a carbon energy coupling distribution model that reflects the coupling relationship between energy and carbon emissions of each spatial location index at different time nodes.

[0043] The training process of the carbon energy coupling distribution model is to iteratively optimize the energy-carbon coupling characteristics of each spatial location index and time node by using time-series hierarchical coupling data, adjust the coupling value by comparing the features of neighboring spatial location indices and matching the trend of historical time windows, and correct abnormal deviations by combining the difference balancing method. After multiple rounds of iteration, the energy-carbon coupling characteristics of each spatial location index converge to stable values, forming a complete, continuous and smooth carbon energy coupling distribution model.

[0044] The difference balancing method adjusts for fluctuations in the carbon-energy coupling characteristics across spatial location indices by calculating their range. Specifically, it calculates the average value and fluctuation range of the carbon-energy coupling characteristics for each spatial location index. Based on the differences in fluctuations between different spatial location indices, it adjusts the characteristics that deviate significantly from the average value, thus balancing the overall characteristics and preventing excessively large or small characteristics in some spatial location indices from affecting the stability of the overall data. This approach ensures greater consistency in the characteristics of the carbon-energy coupling distribution model while preserving local differences.

[0045] S2.3. The carbon energy coupling distribution model is divided into spatial equipotential regions to generate a carbon energy coupling density region, and a carbon energy density gradient field is generated through density gradient analysis.

[0046] Furthermore, in the carbon-energy coupling distribution model, the carbon-energy coupling characteristics of each spatial location index are classified according to the spatial equipotential value. By comparing the coupling strength of each spatial location index, similar and continuous carbon-energy coupling characteristics in space are combined to form a carbon-energy coupling density region. Based on the carbon-energy coupling density region, density gradient analysis is carried out. By observing the difference in carbon-energy coupling strength between each spatial location index and the surrounding spatial location index, the direction and magnitude of the change in local carbon-energy coupling strength are determined, reflecting the trend and rate of change of the carbon-energy coupling strength. After traversing all spatial location indices, a complete carbon-energy density gradient field is formed.

[0047] S2.4. The carbon energy density gradient field is subjected to noise filtering and spatial normalization to generate a gradient normalization matrix, and a preliminary pixel value matrix is ​​generated through nonlinear mapping calculation.

[0048] Furthermore, in the carbon energy density gradient field, by filtering out local anomalous fluctuations and irrelevant disturbances, noise that may exist in the gradient is removed, making the energy-carbon coupling characteristics of each spatial location index smoother and more continuous. The energy-carbon coupling strength of each spatial location index is spatially standardized according to a unified standard, making the energy-carbon coupling characteristics of different spatial location indices comparable at the same scale, generating a gradient normalization matrix. Based on the gradient normalization matrix, the standardized energy-carbon coupling characteristics are mapped into pixel values ​​through a nonlinear mapping method, so that each spatial location index can reflect the distribution of local energy-carbon coupling strength in the pixel matrix, generating a preliminary pixel value matrix.

[0049] S2.5. The initial pixel value matrix is ​​processed through spatial smoothing and continuity to generate a continuous energy carbon distribution matrix, and through spatial integration and formatting, an energy carbon density field distribution map of the park is generated.

[0050] Furthermore, the initial pixel value matrix undergoes spatial smoothing to make the energy-carbon coupling characteristics of adjacent spatial location indices continuous, smoothing out local abrupt changes. At the same time, the continuity processing maintains the coherence of the overall spatial distribution, forming a continuous energy-carbon distribution matrix. The spatial location indices in the continuous energy-carbon distribution matrix are integrated according to the park layout, so that the energy-carbon coupling characteristics of each region are arranged in a coordinated manner under a unified spatial pattern. The matrix is ​​then formatted so that the spatial location indices can intuitively reflect the energy-carbon distribution of different regions within the park, generating an energy-carbon density field distribution map of the park.

[0051] S3. The carbon density field distribution map of the park is used for multi-objective collaborative optimization calculation to obtain a preliminary operation optimization scheme.

[0052] S3.1 Extract energy flow, carbon emissions, and load information from the energy and carbon density field distribution map of the park, and construct a multi-objective collaborative optimization function through interactive calculation.

[0053] Furthermore, energy flow, carbon emissions, and load information are extracted for each spatial location index. The energy usage, carbon emissions, and load status of each spatial location index in different time periods are clarified. The energy flow, carbon emissions, and load information are correlated and interactively analyzed in space and time. The energy-carbon interaction relationship between different spatial location indices and between different time periods is observed. During the analysis, combinations of spatial location indices with high energy utilization efficiency, low carbon emission intensity, and adjustable load are identified. After completing the energy-carbon interaction analysis, the energy flow, carbon emissions, and load constraints and optimization objectives of each spatial location index are uniformly characterized and correlated to form a multi-objective collaborative optimization function that comprehensively describes energy utilization, carbon emissions, and load balance.

[0054] S3.2. Perform constraint projection and space-time mapping on the multi-objective collaborative optimization function to generate a preliminary feasible solution matrix, and form a preliminary operational optimization scheme through multi-objective interactive integration and local priority accumulation.

[0055] Furthermore, constraint projections are applied to the energy flow, carbon emissions, and load constraints for each spatial location index and time period. By applying the actual operational boundary conditions of the park, the energy flow, carbon emissions, and load data for each spatial location index and time period are limited to a reasonable range, ensuring that each optimization objective meets the actual operational boundaries of the park in both space and time. Simultaneously, the energy and carbon information on the spatial location index and time series are spatially and temporally mapped, so that the energy and carbon status of different location indices and time periods corresponds to a unified optimization search space, generating a preliminary feasible solution matrix. Through multi-objective interactive integration, objectives such as energy utilization, carbon emission control, and load balance are interconnected, identifying the optimal energy and carbon combination scheme in both space and time. Based on the principle of local priority, the energy and carbon regulation strategies for key spatial location indices and key time periods are cumulatively optimized, forming a preliminary operational optimization scheme that takes into account multi-objective constraints and spatial-temporal coordination.

[0056] It should also be noted that the local priority principle prioritizes regions and time periods that contribute significantly to the optimization results by analyzing the impact of each spatial location index and time period on the overall energy and carbon optimization. The local priority principle ranks factors based on their importance, such as energy flow, carbon emissions, and load balance, ensuring that energy and carbon control strategies for key regions and time periods are adjusted preferentially during the optimization process.

[0057] S4. The preliminary operation optimization scheme is verified through extreme scenarios and nonlinear performance correction to obtain the carbon sensing operation optimization results.

[0058] S4.1. The preliminary operation optimization scheme is simulated and constrained to obtain the energy-carbon synergistic optimization set, and multi-dimensional data fusion and dynamic simulation are carried out to construct a carbon-energy virtual twin.

[0059] Furthermore, the energy and carbon status under different operating conditions is verified to ensure that energy flow, carbon emissions, and load meet various operating boundary requirements, generating an energy and carbon co-optimization set. Multi-dimensional data fusion is performed on the energy and carbon co-optimization set, integrating the energy and carbon status of each spatial location index and time period according to spatial and temporal relationships. Through dynamic simulation, the energy and carbon change trends and interaction relationships are processed, making the energy and carbon co-optimization set continuous and complete in spatial and temporal dimensions and reflecting the energy and carbon behavior of different operating scenarios. A carbon energy virtual twin containing spatial location index, time series, and multi-scenario energy and carbon status information is constructed.

[0060] S4.2 Perform high-precision time-series simulation and performance calculation on the carbon energy virtual twin to generate carbon energy performance prediction results, and obtain carbon sensing operation optimization results through extreme scenario simulation and nonlinear correction.

[0061] Furthermore, high-precision time-series simulations are performed on the energy flow, carbon emissions, and load status for each spatial location index and time period. By progressively calculating and predicting the energy and carbon status of each spatial location index according to the time series, and combining the trends of historical operating data and the energy and carbon interaction characteristics of neighboring spatial location indices, the system dynamically simulates changes in energy flow, carbon emissions, and load fluctuations. This ensures that the energy and carbon status at each time point can continuously and accurately reflect the actual operating process. The simulation results are verified in real time to ensure the coherence and accuracy of the time series, resulting in a continuous energy and carbon operating status sequence. Performance indicators such as energy efficiency, carbon emission intensity, and load balance are evaluated in real time during the simulation process, generating energy and carbon performance prediction results. Extreme scenario simulations are applied to the carbon energy virtual twin to simulate different types of abnormal situations, such as peak loads, abnormal carbon emission events, or energy supply fluctuations. Nonlinear corrections are applied to the prediction results to adjust local energy and carbon strategies, ensuring that energy flow, carbon emissions, and load remain controllable and optimized under abnormal conditions. The system outputs carbon-sensing operation optimization results that comprehensively consider normal operation and extreme scenarios.

[0062] S5. The carbon sensing operation optimization results are dynamically executed and energy efficiency response is calculated to generate an execution status data stream.

[0063] S5.1 Calculate the time-series energy efficiency response based on the carbon sensing operation optimization results and generate an execution state sequence.

[0064] Furthermore, the carbon sensing operation optimization results are analyzed sequentially according to each spatial location index and time period to determine the changes in energy flow, carbon emissions, and load. By tracking the response trend of each indicator over time, a continuous sequence of operating states is formed. During the tracking process, the energy efficiency response of each time period is matched with the load distribution to identify energy efficiency change nodes and carbon emission fluctuation nodes. Adjustments are made to local anomalies or imbalances to keep the time-series relationship of energy flow, carbon emissions, and load stable, and a complete execution state sequence is output.

[0065] S5.2 Perform nonlinear interactive calculations and local gradient mapping on the execution state sequence to obtain the execution energy efficiency data stream.

[0066] Furthermore, energy flow, carbon emissions, and load information for each spatial location and time period are extracted sequentially from the execution state sequence. The dynamic correlation between different indicators is mapped through nonlinear interactive calculation. By calculating the energy efficiency differences and load differences between each spatial location and its adjacent locations, local gradient values ​​are determined and mapped onto continuous time periods to reflect the local variation trend of energy efficiency changes with spatial location and time. This clarifies the energy efficiency response and load adjustment trends within continuous time periods. During the mapping process, local anomalies or discontinuities are smoothed and trend corrected to maintain the consistency and continuity of energy flow, carbon emissions, and load in time and space, and outputs the execution energy efficiency data stream.

[0067] S5.3. Standardize the energy efficiency data stream according to the time series to obtain standardized time series data.

[0068] Furthermore, each sampling point is arranged sequentially according to the time series to ensure that the energy flow, carbon emissions, and load information of each time period are aligned with a unified time scale. The energy flow, carbon emissions, and load information within each time period are standardized to make different indicators comparable and consistent at the same time scale, while maintaining the continuity and dynamic trend of each indicator over time, thus generating standardized time series data.

[0069] S5.4. The standardized time series data is spatially mapped and fused according to the park layout to generate a preliminary spatial integration matrix. Then, through time interpolation and spatial smoothing, an execution status data stream is generated.

[0070] Furthermore, based on the park's layout, the energy flow, carbon emissions, and load information for each time period are mapped to the corresponding spatial location and spatially integrated to form a preliminary spatial integration matrix based on the actual distribution of energy and carbon information at each location. The preliminary spatial integration matrix is ​​then interpolated in the time dimension to supplement continuous information between different time points, and smoothing is performed in the spatial dimension to mitigate abrupt changes or local unevenness in spatial distribution, ensuring the continuity and consistency of energy and carbon information in space, and outputting the execution status data stream.

[0071] S6. Generate a carbon peak shaving effect assessment report by performing time-series comparison analysis and energy-carbon benefit assessment on the execution status data stream.

[0072] S6.1 Extract time series features from the execution status data stream to obtain a time series feature set.

[0073] Furthermore, the energy flow, carbon emissions, and load information at each time point are analyzed along the time series. The changing trends, peaks, troughs, fluctuation amplitudes, and periodic characteristics of each time period are extracted by using sliding window or time slicing methods. The short-term and long-term dynamic characteristics are calculated by combining the difference information of continuous time periods. The features extracted from each time period are organized and classified according to a unified dimension to form a complete time series feature representation and output a time series feature set.

[0074] It should also be noted that periodicity refers to the regular recurring patterns in energy flow, carbon emissions, or load data in a continuous time series, such as daily peak electricity consumption, weekend carbon emission declines, or monthly load fluctuations. By analyzing these recurring patterns, the periodic trends in energy and carbon operations can be captured for prediction and optimization.

[0075] Short-term and long-term dynamic characteristics refer to the fluctuations in energy flow, carbon emissions, or load changes at different time scales: short-term dynamic characteristics reflect rapid changing trends over several consecutive time points or hours, such as instantaneous load peaks or sudden increases in carbon emissions; long-term dynamic characteristics reflect overall changing trends over longer periods (such as days, weeks, or months), such as daily load increases or seasonal changes in carbon emissions. By considering both short-term and long-term characteristics simultaneously, the dynamic behavior of energy and carbon status can be comprehensively reflected.

[0076] S6.2. Quantify the time-series feature set through energy and carbon efficiency calculations to generate local carbon peak reduction benefits, and generate a carbon peak reduction effect evaluation report through time-series comparative analysis and comprehensive integration.

[0077] Furthermore, through quantitative calculation of energy-carbon benefits, based on energy consumption and carbon emission indicators for each time period, high-load and low-load periods are identified. The energy consumption during high-load periods is compared with the baseline load to assess potential peak-shaving capacity. The actual carbon emissions are compared with the emission reduction under the theoretical optimal peak-shaving load to determine the actual emission reduction effect for each time period. A time-series comparative analysis of the local carbon peak-shaving benefits for different time periods is conducted, including comparing the changing trends, peak and trough positions of benefits for each time period, identifying the improvement or decline of benefits within consecutive time periods, revealing the characteristics of efficient emission reduction periods and inefficient fluctuation periods, and comprehensively integrating the benefits of each time period to form an overall carbon peak-shaving performance evaluation, outputting a carbon peak-shaving effect assessment report.

[0078] In summary, this invention achieves a detailed spatial and temporal characterization of the energy and carbon operation characteristics of industrial parks by performing spatial topological mapping and temporal hierarchical calculation on a multi-source synchronous energy carbon data matrix, thus constructing a carbon-energy coupled distribution model. This provides a basic data structure for subsequent density field generation and optimization calculations, thereby improving the pertinence and executability of resource operation optimization. Furthermore, by performing virtual calculations and extreme scenario self-calculation corrections on the initial operation optimization scheme in a carbon sensing twin, this invention achieves highly reliable prediction and dynamic correction of the optimization scheme, enabling the optimization of park resource operation to take into account energy efficiency improvement, carbon emission reduction, and adaptability to actual operating conditions, thereby enhancing the accuracy, reliability, and sustainability of energy and carbon management in industrial parks.

[0079] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for optimizing the operation of industrial park resources based on the spatiotemporal distribution characteristics of carbon dioxide, characterized in that: include, Collect energy and carbon operation data from industrial parks, and perform time synchronization, anomaly removal, and unit standardization to obtain a multi-source synchronized energy and carbon data matrix; Spatial topological mapping and temporal hierarchical calculation were performed on the carbon data matrix of multi-source synchronous energy to construct a carbon-energy coupling distribution model. The carbon-energy coupling distribution model was then used to generate a carbon-energy density field distribution map of the park through equipotential region division and density gradient analysis. The carbon density field distribution map of the park was used for multi-objective collaborative optimization calculations to obtain a preliminary operation optimization scheme; The initial operational optimization scheme was verified through extreme scenarios and nonlinear performance correction to obtain the carbon sensing operational optimization results; The carbon sensing operation optimization results are dynamically executed and energy efficiency response is calculated to generate an execution status data stream; The execution status data stream is analyzed through time-series comparison and energy-carbon benefit assessment to generate a carbon peak shaving effect assessment report.

2. The industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of electrocarbon as described in claim 1, characterized in that: The process involves collecting energy and carbon operation data from the industrial park, performing time synchronization, anomaly removal, and unit standardization to obtain a multi-source synchronized energy and carbon data matrix. The specific steps are as follows: The energy and carbon operation data of the industrial park are integrated by spatial location index and sorted by time granularity to form a preliminary energy and carbon operation dataset. The preliminary energy carbon operation dataset is smoothed by interpolation and time alignment of adjacent time periods to obtain a synchronous energy carbon data sequence. Then, through abnormal fluctuation removal and data correction, a clean energy carbon dataset is obtained. The cleaned energy carbon dataset is normalized and mapped nonlinearly to output a multi-source synchronous energy carbon data matrix.

3. The industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of electrocarbon as described in claim 2, characterized in that: The specific steps for constructing a carbon energy coupling distribution model by performing spatial topological mapping and temporal hierarchical calculation on the multi-source synchronous energy carbon data matrix are as follows. The carbon data matrix of multi-source synchrotron energy is mapped by neighboring units and projected by spatial topology to form initial values ​​for spatial coupling. Then, through segmented accumulation and exponential decay processing by historical time windows, time-series hierarchical coupled data is generated. By integrating time-series hierarchical coupled data through spatial-temporal interaction and difference balancing, a carbon energy coupled distribution model is formed.

4. The industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of electrocarbon as described in claim 3, characterized in that: The carbon energy coupling distribution model is used to generate a carbon density field distribution map of the park through equipotential region division and density gradient analysis. The specific steps are as follows: The carbon energy coupling distribution model is divided into spatial equipotential regions to generate a carbon energy coupling density region, and a carbon energy density gradient field is generated through density gradient analysis. Image mapping processing is performed on the carbon energy density gradient field to generate a carbon energy density field distribution map of the park.

5. The industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of electrocarbon as described in claim 4, characterized in that: The specific steps for image mapping processing of the carbon energy density gradient field to generate a carbon energy density field distribution map of the park are as follows. The carbon energy density gradient field is subjected to noise filtering and spatial normalization to generate a gradient normalization matrix, and a preliminary pixel value matrix is ​​generated through nonlinear mapping calculation. The initial pixel value matrix is ​​spatially smoothed and made continuous to generate a continuous energy-carbon distribution matrix. Then, through spatial integration and formatting, an energy-carbon density field distribution map of the park is generated.

6. The industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of electrocarbon as described in claim 5, characterized in that: The preliminary operational optimization scheme is obtained by performing multi-objective collaborative optimization calculations on the carbon density field distribution map of the park. The specific steps are as follows: Energy flow, carbon emissions, and load information were extracted from the energy and carbon density field distribution map of the park and a multi-objective collaborative optimization function was constructed through interactive calculation. Constraint projection and space-time mapping are performed on the multi-objective collaborative optimization function to generate a preliminary feasible solution matrix. Through multi-objective interactive integration and local priority accumulation, a preliminary operational optimization scheme is formed.

7. The industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of electrocarbon as described in claim 6, characterized in that: The preliminary operational optimization scheme is verified through extreme scenarios and nonlinear performance correction to obtain the carbon sensing operational optimization results. The specific steps are as follows: The initial operation optimization scheme was simulated and constrained to obtain an energy-carbon synergistic optimization set. Multi-dimensional data fusion and dynamic simulation were then carried out to construct a carbon-energy virtual twin. High-precision time-series simulation and performance calculation are performed on a carbon energy virtual twin to generate carbon energy performance prediction results. Through extreme scenario simulation and nonlinear correction, carbon sensing operation optimization results are obtained.

8. The industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of electrocarbon as described in claim 7, characterized in that: The process of generating an execution status data stream by dynamically executing the carbon sensing operation optimization results through mapping and energy efficiency response calculation is as follows: The time-series energy efficiency response is calculated based on the carbon sensing operation optimization results to generate an execution state sequence; The execution state sequence is subjected to nonlinear interactive calculation and local gradient mapping to obtain the execution energy efficiency data stream; The execution energy efficiency data stream is integrated with time series and spatial location to form an execution status data stream.

9. The industrial park resource operation optimization method based on the spatiotemporal distribution characteristics of electrocarbon as described in claim 8, characterized in that: The process of integrating the energy efficiency data stream with time series and spatial location to form an execution status data stream involves the following steps. The energy efficiency data stream is standardized according to time series to obtain standardized time series data. Standardized time series data are spatially mapped and fused according to the park layout to generate a preliminary spatial integration matrix. Then, through time interpolation and spatial smoothing, an execution status data stream is generated.

10. The method for optimizing the operation of industrial park resources by generating a spatiotemporal distribution map of the carbon energy density field distribution map of the park based on image mapping processing of the carbon energy density gradient field according to claim 9, characterized in that: The process of generating a carbon peak shaving effect assessment report by performing time-series comparative analysis and energy-carbon benefit assessment on the execution status data stream involves the following specific steps: Time series features are extracted from the execution status data stream to obtain a time series feature set; The time-series feature set is used to quantify the energy and carbon benefits to generate local carbon peak reduction benefits. Time-series comparative analysis and comprehensive integration are then performed to generate a carbon peak reduction effect evaluation report.

Images