A carbon emission-based energy management system

Abstract

This invention provides a carbon emission-based energy management system, relating to the field of carbon emission technology. It includes a data acquisition module that collects real-time energy consumption, carbon emission-related data, and historical management data, extracting data such as actual consumption and time distribution. A carbon emission extraction module calculates carbon emission coefficients, carbon emission amounts, and trend data based on the relevant data. A carbon emission change prediction module constructs a seasonal time series model, predicting carbon emission changes based on energy consumption time distribution data and combining this with carbon emission trends. An adjustment strategy module extracts strategies from historical data using association rule mining, and then adjusts them according to carbon emission changes to form an optimized energy management plan. This invention, by calculating carbon emission trend data, helps enterprises and relevant departments accurately grasp carbon emission situations. By organizing energy consumption time distribution data to obtain energy consumption change data, it provides a more reliable basis for carbon emission change prediction, achieving accurate prediction of energy consumption.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of carbon emissions, and particularly relates to an energy management system based on carbon emissions. BACKGROUND

[0002] Under the background of actively responding to climate change and vigorously promoting sustainable development worldwide, carbon emission management has become a key link for industries to realize green transformation. Energy, as the basis for the operation of the economic and social, its consumption is closely linked with carbon emissions. How to efficiently manage energy to reduce carbon emissions has become the focus of attention.

[0003] The traditional energy management method has shortcomings. In the carbon emission calculation link, there is a lack of systematicness and accuracy. The past methods often cannot comprehensively and systematically integrate the actual energy consumption data and carbon emission intensity data, carbon emission factor data, resulting in large errors in the calculated carbon emission coefficient, carbon emission and carbon emission trend data, and it is difficult to accurately reflect the real carbon emission situation. This makes it difficult for enterprises and relevant departments to develop emission reduction targets and strategies, and easily leads to problems such as unreasonable target setting and poor strategy implementation effect, which cannot effectively promote the precise control and reduction of carbon emissions.

[0004] The accuracy of energy consumption prediction is crucial for rational planning of energy use and ensuring stable energy supply. However, existing energy management systems have obvious defects in this regard. Most systems fail to fully consider the time distribution characteristics of energy consumption, lacking scientific and effective prediction models. This makes the energy consumption prediction results deviate greatly, and it is difficult to accurately grasp the energy consumption trend in advance, leading to a lack of foresight in energy planning and making it difficult to achieve optimal resource allocation. This not only causes energy waste, but also increases unnecessary energy procurement costs, affecting the economic benefits and sustainable development ability of enterprises.

[0005] The scientificity and effectiveness of energy management strategies are directly related to energy utilization efficiency and carbon emission control effect. However, existing energy management strategies generally have the problem of insufficient optimization. On the one hand, the development of strategies lacks deep mining and analysis of historical data, making it difficult to extract truly effective strategies from past energy management practices. On the other hand, during the implementation of the strategy, there is a lack of mechanism for dynamic evaluation and adjustment based on real-time carbon emission data. This leads to some strategies failing to adapt to changing energy use scenarios and carbon emission requirements in actual application, and failing to fully play a role in reducing carbon emissions and improving energy utilization efficiency, limiting the effectiveness of enterprises in energy saving and cost control.

[0006] In summary, it is urgent to develop a new energy management system that can accurately calculate carbon emissions, accurately predict energy consumption, and effectively optimize energy management strategies. SUMMARY

[0007] The application provides an energy management system based on carbon emission to solve the defects of inaccurate carbon emission calculation, inaccurate energy consumption prediction and imperfect management strategy in the prior art.

[0008] The application provides an energy management system based on carbon emission, comprising:

[0009] A data acquisition module is configured to acquire energy consumption data and energy consumption time distribution data in real time.

[0010] A carbon emission extraction module is configured to extract carbon emission trend data from the energy consumption data.

[0011] A carbon emission change prediction module is configured to construct a seasonal time series model, input the energy consumption time distribution data, output energy consumption change data, analyze the proportion change of different energy in total energy consumption when the energy structure changes, obtain proportion impact data of the influence of carbon emission, calculate the energy consumption per unit of economic output and the carbon emission per unit of economic output to measure the influence of energy efficiency on carbon emission to obtain efficiency change data, and combine the carbon emission trend data to obtain carbon emission change data.

[0012] An adjustment strategy module is configured to adjust the energy management strategy according to the carbon emission change data to generate an optimized energy management scheme.

[0013] According to the energy management system based on carbon emission provided by the application, the data acquisition module is further configured to:

[0014] The carbon emission factor data and the carbon emission intensity data are acquired in real time, and historical management data and actual consumption data are collected.

[0015] According to the energy management system based on carbon emission provided by the application, the extraction of the carbon emission extraction module comprises:

[0016] The carbon emission coefficient is obtained according to the actual consumption data and the carbon emission intensity data, the carbon emission amount data is obtained according to the carbon emission factor data and the actual consumption data, and the carbon emission trend data is obtained according to the carbon emission coefficient and the energy consumption data.

[0017] According to the energy management system based on carbon emission provided by the application, the step of obtaining the carbon emission coefficient comprises:

[0018] The energy types of the actual consumption data are determined from energy statistical reports and enterprise production records, and the energy types corresponding to the carbon emission intensity data are determined according to a carbon emission database.

[0019] The energy species and the energy types of different units and multiple sources are sorted and matched, so that the actual consumption data of each energy species and energy type corresponds to the corresponding carbon emission intensity data;

[0020] The carbon emission coefficient is obtained by weighting the carbon emission intensity and the actual consumption for each energy species and energy type.

[0021] According to the energy management system based on carbon emission provided by the application, the step of obtaining the carbon emission data comprises:

[0022] According to the division of the life cycle stage of different energy species, a plurality of energy stages are obtained, the carbon emission factor corresponding to different energy stages is found through the carbon emission factor data, and the actual activity data of each energy stage is counted;

[0023] According to the multiplication of the carbon emission factor of each energy stage and the actual activity data, the carbon emission of each energy stage is calculated, and the carbon emission of each energy stage is added to obtain the carbon emission data.

[0024] According to the energy management system based on carbon emission provided by the application, the step of obtaining the carbon emission trend data comprises:

[0025] According to the carbon emission coefficient data, the emission of each energy is calculated in each preset statistical period to obtain the emission of each energy, and the emission of each energy is summarized to obtain the period carbon emission;

[0026] The period carbon emission in each preset statistical period is arranged in time sequence to form carbon emission time series data, and a change trend graph is drawn by using an icon tool according to the carbon emission time series data, with time as the horizontal coordinate and carbon emission as the vertical coordinate;

[0027] The carbon emission time series data is smoothed by using the moving average method, so that the change trend graph shows the long-term trend, and the long-term trend is analyzed to obtain the carbon emission trend data.

[0028] According to the energy management system based on carbon emission provided by the application, the step of obtaining the energy consumption change data comprises:

[0029] The energy consumption time distribution data is sorted to obtain energy time series, and the energy time series is subjected to difference operation by using unit root test method to convert into stationary sequence;

[0030] The seasonal characteristics of the stationary sequence are observed to determine the seasonal period, and the seasonal difference is performed to obtain the seasonal sequence;

[0031] By plotting the autocorrelation function and partial autocorrelation function, and combining different parameter combinations, the parameters of the seasonal time series model are determined to obtain the model parameters. The seasonal series model is then obtained by fitting the seasonal series using the model parameters.

[0032] The seasonal series model is diagnosed to check whether the residuals are white noise. If they are, the seasonal series model is continued to be used; otherwise, the model parameters are readjusted until they are found to be white noise.

[0033] Using the seasonal sequence model, new time point information is input to predict energy consumption and obtain predicted consumption values. The predicted consumption values ​​are then compared with the actual consumption data to calculate the energy consumption change data.

[0034] The steps for acquiring the carbon emission change data according to a carbon emission-based energy management system provided by the present invention include:

[0035] The change in carbon emissions due to changes in energy consumption is calculated by combining the energy consumption change data with the efficiency change data.

[0036] Based on the aforementioned percentage impact data, the degree of impact of energy structure changes on carbon emissions is calculated, and the percentage impact on carbon emission changes is obtained.

[0037] The original energy intensity and the post-energy intensity are obtained by statistically analyzing the data before and after the change in energy intensity caused by the improvement in energy efficiency. The intensity change data are then calculated by using the economic output of the original energy intensity and the post-energy intensity.

[0038] Then, the intensity carbon emission change is calculated based on the intensity change data and the corresponding carbon emission factor.

[0039] The carbon emission change data is obtained by adding the change in carbon emissions due to the proportion, the change in carbon emissions due to energy changes, and the change in carbon emissions due to intensity.

[0040] According to the present invention, an energy management system based on carbon emissions includes the following steps for extracting the energy management strategy from the historical management data using an association rule mining method:

[0041] Energy usage data, equipment operating status, production data, and environmental data related to energy management are collected from the historical management data, transformed, and integrated to establish a unified data table;

[0042] The Apriori algorithm is used to find frequent itemsets from the unified data table through a layer-by-layer search. Then, association rules are generated based on the frequent itemsets, and the parameters of the association rules are determined using minimum support and minimum confidence.

[0043] The association rules that satisfy the minimum support are identified as the mining itemset. Based on the mining itemset, confidence rules that satisfy the minimum confidence are generated. The causal relationships and influence mechanisms of the confidence rules are analyzed to obtain the analysis results. The energy management strategy is extracted from the analysis results.

[0044] According to a carbon emission-based energy management system provided by the present invention, the steps for obtaining the optimized energy management scheme include:

[0045] The key change data is obtained by analyzing the trend, magnitude and time distribution of carbon emission changes in the carbon emission change data, and the factor impact data is obtained by decomposing the key change data into factors.

[0046] The energy management strategy is evaluated based on the key change data and the factor impact data. The energy management strategy is then classified according to its effectiveness in reducing carbon emissions, resulting in effective and inefficient strategies.

[0047] Strengthening and expanding the implementation scope of the effective strategies yields enhanced strategies; while analyzing the reasons for the failure of the inefficient strategies from the aspects of implementation plan, technical solution, and changes in the external environment, and making improvements, yields improved strategies.

[0048] Based on the carbon emission data, corresponding new strategies are specified from the aspects of equipment aging, climate change and process optimization. The enhanced strategies, improved strategies and new strategies are integrated to obtain an optimized energy management solution.

[0049] This invention provides a carbon emission-based energy management system. It derives carbon emission coefficients from actual consumption data combined with carbon emission intensity data, and carbon emission data from carbon emission factor data and actual consumption data. Furthermore, it calculates carbon emission trend data, addressing the lack of systematicity and accuracy in carbon emission calculations. This helps enterprises and relevant departments accurately grasp carbon emission situations and formulate reasonable emission reduction targets and strategies. Furthermore, it constructs a seasonal time series model. Through processing, differencing, determining seasonal cycles, and fitting the model to energy consumption time distribution data, it achieves accurate prediction of energy consumption and obtains energy consumption change data, thus providing a more reliable basis for carbon emission change prediction. This allows for accurate prediction of energy consumption and early understanding of energy consumption trends, providing strong support for energy planning and resource allocation. It also evaluates and classifies energy management strategies, taking strengthening and improvement measures for effective and inefficient strategies respectively, and formulating new strategies based on carbon emission data. Finally, it integrates these to obtain an optimized energy management solution, achieving optimization and improvement of energy management strategies, while also helping enterprises reduce energy costs and improve economic efficiency. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0051] Figure 1 This is a schematic diagram of the structure of an energy management system based on carbon emissions provided in an embodiment of the present invention;

[0052] Figure 2 yes Figure 1 A flowchart illustrating the process of obtaining carbon emission coefficients using the carbon emission extraction module.

[0053] Figure 3 yes Figure 1 A flowchart illustrating how the carbon emission extraction module acquires carbon emission trend data.

[0054] Figure 4 yes Figure 1 A flowchart illustrating how the carbon emission change prediction module acquires carbon emission change data. Detailed Implementation

[0055] 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. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0056] The following is combined Figures 1-4 This invention describes a carbon emission-based energy management system.

[0057] like Figure 1 As shown, an embodiment of the present invention provides a carbon emission-based energy management system comprising:

[0058] The data acquisition module is used to collect energy consumption data and carbon emission-related data in real time, as well as historical management data. It extracts actual consumption data and energy consumption time distribution data from the energy consumption data, and carbon emission-related data includes carbon emission factor data and carbon emission intensity data.

[0059] The carbon emission extraction module is used to obtain carbon emission coefficients based on actual consumption data and carbon emission intensity data, carbon emission amount data based on carbon emission factor data and actual consumption data, and carbon emission trend data based on carbon emission coefficients and energy consumption data.

[0060] The steps to obtain carbon emission coefficients include:

[0061] By analyzing energy statistics reports and enterprise production records, we can determine the types of energy consumed in actual data, and by analyzing carbon emission databases, we can determine the energy types corresponding to carbon emission intensity data.

[0062] For each type and type of energy, a carbon emission coefficient is obtained by weighting carbon emission intensity with actual consumption.

[0063] For each type and type of energy, the carbon emission intensity is divided by the actual consumption to obtain the corresponding emission coefficient. The carbon emission coefficient is obtained by summing up the various emission coefficients.

[0064] The steps to obtain carbon emission data include:

[0065] By dividing the life cycle stages of different energy types, multiple energy stages are obtained. Carbon emission factor data is used to find the corresponding carbon emission factors for different energy stages, and the actual activity data of each energy stage are statistically analyzed.

[0066] The carbon emissions for each energy stage are calculated by multiplying the carbon emission factor for each energy stage by the actual activity data, and the carbon emissions for each energy stage are summed to obtain the total carbon emissions data.

[0067] The steps to obtain carbon emission trend data include:

[0068] Based on carbon emission coefficient data, the emissions of each type of energy are calculated for each preset statistical period, and the emissions of each type of energy are summed to obtain the carbon emissions for that period.

[0069] The carbon emissions within each preset statistical period are arranged in chronological order to form a time series of carbon emissions data. Using a charting tool, a trend chart is drawn based on the carbon emissions time series data, with time as the horizontal axis and carbon emissions as the vertical axis.

[0070] By using the moving average method to smooth the time series data of carbon emissions, the trend graph can be made to show the long-term trend, and then the long-term trend can be analyzed to obtain the carbon emission trend data.

[0071] The carbon emission change prediction module is used to build a seasonal time series model. It takes energy consumption time distribution data as input for prediction and outputs energy consumption change data. The carbon emission trend data is combined with the energy consumption change data to obtain the carbon emission change data.

[0072] The steps to obtain data on changes in energy consumption include:

[0073] The energy consumption time distribution data is processed to obtain an energy time series. Then, the energy time series is differenced using the unit root test method to transform it into a stationary series. The formula is expressed as:

[0074]

[0075] In the formula, It is a stationary sequence. It is an energy time series. yes Order difference operator.

[0076] By observing the seasonal characteristics of stationary sequences, seasonal cycles are determined, and seasonal series are obtained through seasonal differencing. The formula is expressed as:

[0077]

[0078] In the formula, It is a seasonal sequence. It is the seasonal difference of order. Seasonal difference operator.

[0079] By plotting the autocorrelation function and partial autocorrelation function, and combining different parameter combinations, the parameters of the seasonal time series model are determined, and the model parameters are obtained. The seasonal time series model is then obtained by fitting the model parameters to the seasonal series, as expressed by the formula:

[0080]

[0081] In the formula, It is the ordinary autoregressive polynomial of the autoregressive part. It is the seasonal autoregressive polynomial of the autoregressive part. The mean is 0 and the variance is White noise sequence, It is the ordinary autoregressive polynomial of the moving average part. It is the seasonal autoregressive polynomial of the moving average portion.

[0082] Diagnose the seasonal series model by checking whether the residuals are white noise. If so, continue using the seasonal series model; otherwise, readjust the model parameters until they are found to be white noise.

[0083] By using a seasonal series model and inputting new time point information, energy consumption is predicted to obtain predicted consumption values. The predicted consumption values ​​are then compared with actual consumption data to calculate the changes in energy consumption.

[0084] The steps to obtain carbon emission change data include:

[0085] This ensures that carbon emission trend data and energy consumption change data are consistent across time scales, and handles missing and outlier values.

[0086] When the energy structure changes, we analyze the changes in the proportion of different energy sources in total energy consumption, obtain the impact data of the proportion changes on carbon emissions, and measure the impact of energy efficiency on carbon emissions by calculating the energy consumption per unit of economic output and the carbon emissions per unit of economic output, thus obtaining the efficiency change data.

[0087] The change in carbon emissions due to changes in energy consumption is calculated by combining data on changes in energy consumption with data on changes in efficiency. The formula is as follows:

[0088]

[0089] In the formula, It is the change in carbon emissions due to energy changes. It is data on changes in efficiency. It is the carbon emission factor corresponding to the efficiency change data.

[0090] Based on the percentage impact data, the degree of impact of changes in energy structure on carbon emissions is calculated, yielding the percentage impact on carbon emission changes, expressed by the following formula:

[0091]

[0092] In the formula, It refers to the proportion of a certain energy source in the energy structure. It represents the percentage of a certain energy source in the energy structure after its decline. It is the total energy consumption. It is the carbon emission factor corresponding to a certain energy source. It is the percentage that affects the change in carbon emissions.

[0093] By analyzing data before and after the change in energy intensity due to improved energy efficiency, we obtain the original and post-energy intensity. Then, using the economic output of the original and post-energy intensities, we calculate the intensity change data, expressed by the following formula:

[0094]

[0095] In the formula, These are intensity change data. It is the original energy intensity. It is post-energy intensity, It is economic output.

[0096] Then, the change in carbon emissions due to intensity is calculated based on the intensity change data and the corresponding carbon emission factors. The formula is as follows:

[0097]

[0098] In the formula, It is the change in intensity of carbon emissions. It is the carbon emission factor corresponding to the intensity change data.

[0099] The carbon emission change data is obtained by adding the changes in carbon emissions due to the proportion, energy change, and intensity, as well as the changes in carbon emissions due to energy changes. The formula is as follows:

[0100]

[0101] In the formula, It is data on changes in carbon emissions. It is the change in carbon emissions due to energy changes. The percentage affects the change in carbon emissions. It is the change in intensity of carbon emissions.

[0102] The strategy adjustment module is used to extract energy management strategies from historical management data using association rule mining methods, and to adjust the energy management strategies based on carbon emission change data to obtain an optimized energy management solution.

[0103] The steps to obtain an energy management strategy include:

[0104] Energy usage data, equipment operating status, production data, and environmental data related to energy management are collected from historical management data, transformed, and integrated to establish a unified data table.

[0105] The Apriori algorithm is used to find frequent itemsets from a unified data table through a layer-by-layer search. Then, association rules are generated based on the frequent itemsets, and the parameters of the association rules are determined using minimum support and minimum confidence.

[0106] The association rules are identified as itemsets that meet the minimum support requirement. Based on these itemsets, confidence rules that meet the minimum confidence requirement are generated. The causal relationships and influence mechanisms of these confidence rules are analyzed to obtain the analysis results. Energy management strategies are then extracted from the analysis results.

[0107] The steps to obtain an optimized energy management solution include:

[0108] By analyzing the trend, magnitude, and temporal distribution of carbon emission changes in carbon emission change data, key change data are obtained. Factor decomposition of key change data yields factor impact data.

[0109] Energy management strategies are evaluated based on key change data and factor impact data. These strategies are then categorized by their effectiveness in reducing carbon emissions, resulting in effective and inefficient strategies.

[0110] Strengthening strategies are obtained by reinforcing and expanding the implementation scope of effective strategies. For ineffective strategies, the reasons for strategy failure are analyzed from the aspects of implementation plan, technical solution and changes in external environment, and improvements are made to obtain improvement strategies.

[0111] Based on carbon emission data, corresponding new strategies are specified from the aspects of equipment aging, climate change and process optimization. The strengthening strategies, improvement strategies and new strategies are integrated to obtain an optimized energy management solution.

[0112] This embodiment provides a carbon emission-based energy management system. It derives carbon emission coefficients from actual consumption data combined with carbon emission intensity data, and carbon emission data from carbon emission factor data and actual consumption data. Furthermore, it calculates carbon emission trend data, addressing the lack of systematicity and accuracy in carbon emission calculations. This helps enterprises and relevant departments accurately grasp carbon emission situations and formulate reasonable emission reduction targets and strategies. Furthermore, it constructs a seasonal time series model. Through processing, differencing, determining seasonal cycles, and fitting the model to energy consumption time distribution data, it achieves accurate prediction of energy consumption and obtains energy consumption change data. This provides a more reliable basis for predicting carbon emission changes, enabling accurate prediction of energy consumption and allowing for early understanding of energy consumption trends, thus providing strong support for energy planning and resource allocation. It also evaluates and classifies energy management strategies, taking strengthening and improvement measures for effective and inefficient strategies respectively. New strategies are developed based on carbon emission data, ultimately integrating them to obtain an optimized energy management solution. This optimizes and improves energy management strategies, while also helping enterprises reduce energy costs and improve economic efficiency.

[0113] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units 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. Those skilled in the art can understand and implement this without any creative effort.

[0114] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0115] 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 them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A carbon emission based energy management system characterized in that, The method comprises the following steps: a data collection module is configured to collect real-time energy consumption data and energy consumption time distribution data; a carbon emission extraction module is configured to extract carbon emission trend data from the energy consumption data; the extraction of the carbon emission extraction module comprises the following steps: a carbon emission coefficient is obtained according to actual consumption data combined with carbon emission intensity data, carbon emission amount data is obtained according to carbon emission factor data and the actual consumption data, and carbon emission trend data is obtained according to the carbon emission coefficient and the energy consumption data; a carbon emission change prediction module is configured to construct a seasonal time series model, input the energy consumption time distribution data, and output energy consumption change data, when the energy structure changes, analyze the proportion change of different energies in the total energy consumption, obtain proportion impact data by analyzing the influence of the carbon emission, calculate the energy consumption per unit of economic output and the carbon emission per unit of economic output to measure the influence of energy efficiency on carbon emission to obtain efficiency change data, and combine the carbon emission trend data to obtain carbon emission change data; the step of obtaining the carbon emission change data comprises the following steps: an energy change carbon emission change amount is obtained by calculating the carbon emission amount change caused by the energy consumption change according to the energy consumption change data combined with the efficiency change data; a proportion impact carbon emission change amount is obtained by calculating the influence degree of the energy structure change on the carbon emission according to the proportion impact data; original energy intensity and later energy intensity are obtained by calculating the energy intensity change data through the economic output of the original energy intensity and the later energy intensity before and after the energy efficiency improvement; a strength carbon emission change amount is obtained according to the strength change data and the carbon emission factor corresponding to the strength change data; the proportion impact carbon emission change amount, the energy change carbon emission change amount and the strength carbon emission change amount are added to obtain the carbon emission change data; an adjustment strategy module is configured to adjust the energy management strategy according to the carbon emission change data to generate an optimized energy management scheme.

2. The carbon emission based energy management system as claimed in claim 1 wherein, The data collection module is further configured to: collect the carbon emission factor data and the carbon emission intensity data in real time, and collect historical management data and actual consumption data.

3. The carbon emission based energy management system as claimed in claim 1 wherein, The step of obtaining the carbon emission coefficient comprises the following steps: the energy types of the actual consumption data are determined from energy statistical reports and enterprise production records, and the energy types corresponding to the carbon emission intensity data are determined according to a carbon emission database; the energy types and the energy types of different units and multiple sources are sorted and matched, so that the actual consumption data of each energy type and energy type correspond to the corresponding carbon emission intensity data; for each energy type and energy type, the carbon emission coefficient is obtained by weighting the carbon emission intensity and the actual consumption amount.

4. The carbon emission based energy management system as claimed in claim 1 wherein, The step of obtaining the carbon emission amount data comprises the following steps: a plurality of energy stages are obtained by dividing the life cycle stages of different energy types, the carbon emission factors corresponding to different energy stages are found through the carbon emission factor data, and the actual activity data of each energy stage is counted; The carbon emission amount of each energy stage is calculated by multiplying the carbon emission factor of each energy stage and the actual activity data, and the carbon emission amount of each energy stage is added to obtain the carbon emission data.

5. The carbon emission based energy management system as claimed in claim 1 wherein, The step of obtaining the carbon emission trend data comprises: According to the carbon emission coefficient data, the emission amount of each type of energy consumption in each preset statistical period is calculated to obtain the emission amount of each energy, and the emission amount of each energy is summarized to obtain period carbon emission; The period carbon emission in each preset statistical period is arranged in chronological order to form carbon emission time series data, and a change trend graph is drawn by using a graph tool according to the carbon emission time series data, with time as the horizontal coordinate and carbon emission as the vertical coordinate; The carbon emission time series data is smoothed by using a moving average method, so that the change trend graph shows a long-term trend, and the long-term trend is analyzed to obtain the carbon emission trend data.

6. The carbon emission based energy management system as claimed in claim 2 wherein, The step of obtaining the energy consumption change data comprises: The energy consumption time distribution data is arranged to obtain an energy time series, and a unit root test method is used to difference the energy time series to convert it into a stationary sequence; By observing the seasonal characteristics of the stationary sequence, the seasonal period is determined, and the seasonal difference is performed to obtain a seasonal sequence; By drawing autocorrelation function and partial autocorrelation function graphs and combining different parameter combinations, the parameters of the seasonal time series model are determined to obtain model parameters, and the model parameters are used to model fit the seasonal sequence to obtain a seasonal sequence model; The seasonal sequence model is diagnosed to check whether the residual error is white noise, if yes, the seasonal sequence model is continuously used, otherwise, the model parameters are adjusted until the residual error is the white noise; The seasonal sequence model is used to input new time point information to predict the energy consumption to obtain a predicted consumption value, and the predicted consumption value is compared with the actual consumption data to calculate the energy consumption change data.

7. The carbon emission based energy management system as claimed in claim 2 wherein, The step of extracting the energy management strategy from the historical management data using an association rule mining method comprises: Energy use data, equipment operating status, production data and environmental data related to energy management are collected from the historical management data, converted and integrated to establish a unified data table; An Apriori algorithm is used to find frequent item sets from the unified data table by layer-by-layer searching, and then association rules are generated according to the frequent item sets, and the parameters of the association rules are determined using minimum support and minimum confidence; From the association rules, the mining item set satisfying the minimum support is found, based on the mining item set, the confidence rule satisfying the minimum confidence is generated, the causal relationship and influence mechanism of the confidence rule are analyzed to obtain an analysis result, and the energy management strategy is extracted from the analysis result.

8. The carbon emission based energy management system as claimed in claim 1 wherein, The step of obtaining the optimized energy management scheme comprises: The change trend, change amplitude and time distribution of carbon emission in the carbon emission change data are analyzed to obtain key change data, and the key change data is factor-decomposed to obtain factor influence data; According to the key change data and the factor influence data, the energy management strategy is evaluated, classified by the effect of reducing carbon emissions, and effective strategies and inefficient strategies are obtained; The effective strategies are reinforced and expanded to obtain reinforced strategies, and the inefficient strategies are analyzed from the aspects of implementation scheme, technical scheme and external environment change to obtain improved strategies; Based on the carbon emission data, corresponding new strategies are specified from the aspects of equipment aging, climate change and process optimization, and the reinforced strategies, the improved strategies and the new strategies are integrated to obtain an optimized energy management scheme.

Images