Energy efficiency optimization system based on power and carbon emission market coupling

Abstract

The invention relates to the technical field of energy management and environmental protection, in particular to an energy efficiency optimization system based on electric power and carbon emission market coupling, which comprises an electric power demand prediction module, a carbon emission calculation module, a market coupling module, a strategy generation module, an execution feedback module and an interaction interface module. Wherein the power demand prediction module is used for predicting future power demand; the carbon emission calculation module is used for calculating the corresponding carbon emission; the market coupling module is used for generating a supply and demand report of an electric power and carbon emission market; the strategy generation module is used for formulating a specific power dispatching and carbon emission reduction strategy; the execution feedback module is used for adjusting future strategy generation according to market feedback; and the interactive interface module provides an operation interface for a user. According to the invention, by integrating electric power and carbon emission markets, optimizing resource allocation and realizing dynamic strategy adjustment, the energy use efficiency and the environmental protection effect are effectively improved, and the adaptability of the system and the user interactivity are enhanced at the same time.

Description

Technical Field

[0001] The present invention relates to the technical field of energy management and environmental protection, and in particular to an energy efficiency optimization system based on the coupling of electricity and carbon emission markets. Background Art

[0002] As global attention to environmental protection and resource conservation intensifies, electricity markets and carbon emission control have become key areas of policy and technological innovation. Currently, the electricity market focuses on optimizing electricity production and distribution efficiency, while carbon emission management focuses on limiting and reducing greenhouse gas emissions. However, existing systems usually handle these two aspects independently, ignoring the inherent connection between electricity production and carbon emissions. This split processing method fails to fully utilize the possible synergy between the two, resulting in suboptimal resource utilization efficiency and limited environmental protection effects.

[0003] Current technologies have obvious deficiencies in dealing with the coupling of electricity markets and carbon emission markets. For example, electricity supply decisions often fail to take into account carbon emission costs, while carbon emission reduction strategies fail to effectively reflect the real-time demand and supply conditions of the electricity market. This leads to an information gap between the two systems and makes it impossible to achieve the best match between resource and environmental policies.

[0004] Therefore, it is particularly urgent to develop a system that can integrate electricity demand forecasting, carbon emission control and market response. Such a system can not only improve the efficiency of electricity and carbon emission management, but also bring greater economic and social benefits by optimizing resource allocation and reducing environmental impact. Summary of the invention

[0005] Based on the above objectives, the present invention provides an energy efficiency optimization system based on the coupling of electricity and carbon emission markets.

[0006] The energy efficiency optimization system based on the coupling of electricity and carbon emission markets includes an electricity demand forecasting module, a carbon emission calculation module, a market coupling module, a strategy generation module, an execution feedback module and an interactive interface module; wherein:

[0007] Power demand forecasting module: used to collect data on multiple factors including historical power consumption data, weather conditions, and economic activity index, and use improved deep learning networks to predict future power demand;

[0008] Carbon emission calculation module: Calculate the corresponding carbon emissions according to the energy type and quantity in the process of electricity production and consumption;

[0009] Market coupling module: Generates supply and demand reports for the electricity and carbon emission markets based on predicted electricity demand and carbon emission data, and automatically adjusts electricity prices and carbon emission trading prices;

[0010] Strategy generation module: formulates specific power dispatch and carbon emission reduction strategies based on the data provided by the market coupling module;

[0011] Execution feedback module: implements the strategies of the strategy generation module, monitors the execution results, adjusts future strategy generation based on market feedback, and ensures continuous optimization of the system and adaptability to market changes;

[0012] Interactive interface module: provides users with an operation interface, including real-time market data display, strategy execution feedback, and manual strategy adjustment functions.

[0013] Furthermore, the power demand prediction module includes a data collection unit, a data processing unit, a deep learning network unit and an output unit; wherein:

[0014] Data collection unit: used to collect data on various factors that affect electricity demand, including historical electricity consumption data, weather conditions, and economic activity index. The historical electricity consumption data is obtained from the power company's database, including information on past electricity consumption, electricity consumption time periods, and peak electricity consumption; weather condition data, including temperature, humidity, and sunshine duration, is obtained through a data sharing interface with the meteorological department; economic activity index data is obtained through a subscription service to obtain economic indicator reports issued by economic research institutions;

[0015] Data processing unit: Use data preprocessing technology to standardize and normalize data, eliminate noise and outliers in the data, and improve the accuracy and reliability of data analysis; in addition, the data processing unit is also responsible for time series analysis of data, identifying periodic and trend characteristics in the data, and providing representative training data for deep learning networks;

[0016] Deep learning network unit: Use an improved deep learning network to predict future electricity demand. The network structure includes a combination of convolutional neural networks and recurrent neural networks to process time series data and capture long-term dependencies and seasonal changes in the data. The network optimizes network parameters through repeated training and adjustment to improve the accuracy and robustness of the prediction. Cross-validation and hyperparameter tuning strategies are also used in the training process to ensure the model's wide adaptability to future data and prediction accuracy.

[0017] Output unit: Based on the analysis results of the deep learning network unit, the output unit generates a power demand forecast report for the future time period. The report is presented in the form of charts and numbers, clearly showing the predicted power demand trend, peak and valley time points, and providing decision support information for the market coupling module.

[0018] Furthermore, the data processing unit includes:

[0019] Data preprocessing subunit: used to standardize and normalize the collected data. First, the standardization process converts the data into a format with a mean of 0 and a standard deviation of 1 by calculating the mean and standard deviation of each data using the following formula: Among them, x is the original data, μ is the mean value, and σ is the standard deviation. Standardization helps to eliminate the impact of different dimensions and make the data distribution consistent. Next, normalization is performed to scale the data to the [0,1] interval. The specific formula is:

[0020] Among them, min(x) and max(x) are the minimum and maximum values ​​of the data, respectively. Normalization helps to deal with situations where standardization is not applicable, including when the data is not normally distributed. Finally, the outlier detection technology of the box plot method is used to identify and process outliers in the data. Outliers are defined using IQR, and the formula is: IQR = Q3-Q1, where Q1 and Q3 are the first quartile and third quartile of the data, respectively;

[0021] Time series analysis subunit: Use time series analysis techniques to identify the periodicity and trend characteristics of data. First, use the autocorrelation function and partial autocorrelation function to identify the time-dependent structure in the data. The autocorrelation function formula is: Among them, x t represents the observed value at time point t; represents the average of all observations, that is, It is used to normalize data and reduce the impact of data dimensions at different time points; τ is the time lag, which means comparing the current value with the value lagged by τ time units; n is the total number of observation cycles; the formula of the partial autocorrelation function is: Among them, Corr(a,b) represents the correlation between variables a and b; x t Same as above, indicating the observed value at time point t; represents the observed value x at time point t t The linear prediction of x t Previous value; x t+τ represents the observed value at time point t+τ; Represents the observed value x at time point t+τ t+τ The linear prediction of x t+τ The time series analysis technique of seasonal decomposition is then applied to decompose the time series into trend, seasonal, and random components.

[0022] Furthermore, the deep learning network unit includes:

[0023] Network structure design: A combined deep learning network structure is adopted, including the combination of convolutional neural network and recurrent neural network. Convolutional neural network is used to extract spatial features in time series data, while recurrent neural network is used to process sequence data with strong time dependence. The convolutional neural network layer uses multiple convolutional layers to extract local features in the input data. Each convolutional layer processes data through convolution operation. The formula is: y = w*x + b, where x is the output of the input layer or the previous layer, w is the weight of the convolution kernel, b is the bias, * indicates the convolution operation, and y is the output of the convolution layer. The recurrent neural network layer uses a long short-term memory network to capture long-term dependencies in time series. The long short-term memory network is its cell state and three gate structures, including input gate, forget gate, and output gate.

[0024] Network training and optimization: A large amount of historical power demand data is used to train the above network. The training process includes forward propagation and back propagation algorithms. The optimization algorithm is Adam or SGD, which is used to adjust the network weights to minimize the error between the predicted value and the actual value. Specifically, the mean square error MSE is used as the loss function. The specific formula is: Among them, y i is the actual power demand value, is the predicted value, n is the total number of samples;

[0025] Output generation: The trained deep learning network can predict future electricity demand based on the latest input data. The output data includes the predicted electricity demand and its fluctuation range, providing accurate data support for the market coupling module.

[0026] Furthermore, the carbon emission calculation module includes a data collection unit, an energy type identification unit, a carbon emission factor loading unit and a carbon emission calculation unit; wherein:

[0027] Data collection unit: used to collect detailed data on electricity production and consumption, including the use of coal, natural gas, solar energy and wind energy. The data sources include power plant operation records, grid transmission data and terminal consumption data.

[0028] Energy type identification unit: used to classify the collected energy usage data and distinguish different energy types. Specifically, the collected raw data is matched with the preset energy type database using database matching technology;

[0029] Carbon emission factor loading unit: used to store carbon emission factors corresponding to different energy types. The carbon emission factors are based on the latest environmental protection standards and research results. The carbon emission factors represent the carbon emissions generated per unit of energy consumption in kilograms of carbon dioxide equivalent / MJ or kilowatt-hour;

[0030] Carbon emission calculation unit: After obtaining energy consumption data and corresponding carbon emission factors, the following formula is used to calculate the total carbon emissions: Total carbon emissions = ∑(energy consumption i ×Carbon emission factor i ), where i represents different energy types and energy consumption i Refers to the carbon emission factor of each energy type used within a predetermined time period i It is the preset carbon emission amount according to the energy type.

[0031] Furthermore, the market coupling module includes a data integration unit, a supply and demand report generation unit, a price adjustment unit and a real-time monitoring unit; wherein:

[0032] Data integration unit: used to collect and integrate data from the power demand forecasting module and the carbon emission calculation module, using advanced database management methods to ensure data integrity and consistency. The integrated data includes the predicted power demand and calculated carbon emissions;

[0033] Supply and demand report generation unit: Based on the power demand and carbon emission data provided by the data integration unit, a detailed market supply and demand report is generated using statistical analysis and model prediction methods. The report includes power supply and demand forecasts, carbon emission forecasts, and potential market imbalances.

[0034] Price adjustment unit: Automatically adjust electricity prices and carbon emission trading prices according to supply and demand reports. Specifically, it uses a dynamic pricing algorithm to adjust prices according to market supply and demand status to promote market balance. Price adjustment follows the following basic principles: Price adjustment = benchmark price × (1 + α × supply and demand ratio), where α is the adjustment coefficient, the supply and demand ratio represents the ratio of demand to supply, and the benchmark price is the initial price set based on historical data;

[0035] Real-time monitoring unit: monitors market responses and tracks the effects of price adjustments in real time, specifically using market feedback data including trading volume and price changes to evaluate the effectiveness of previous price adjustments and provide data support for the next adjustment.

[0036] Furthermore, the strategy generation module includes a data receiving unit, a strategy planning unit, an environmental impact assessment unit and a strategy optimization unit; wherein:

[0037] Data receiving unit: used to receive data from the market coupling module, including adjusted electricity and carbon emission prices, and market supply and demand reports;

[0038] Strategy Planning Unit: Use optimization algorithms to develop power dispatch and carbon emission reduction strategies: The power dispatch strategy uses linear programming methods to allocate power resources in order to meet market demand while meeting the lowest cost. The specific formula is: Among them, ci represents the electricity cost in different time periods, p i Indicates the electricity production in the corresponding time period; the carbon emission reduction strategy will combine carbon trading and carbon capture methods to optimize carbon emission reduction, specifically by increasing carbon capture facilities and adjusting the energy mix to reduce total carbon emissions;

[0039] Environmental Impact Assessment Unit: Use the Life Cycle Assessment (LCA) method to analyze the potential impact of various strategies on the environment. The LCA method evaluates the environmental impact of the entire process from raw material acquisition, production, use to disposal to ensure that the proposed strategy is not only economically reasonable but also environmentally friendly;

[0040] Strategy optimization unit: Based on the results of environmental impact assessment and market feedback, the adaptive control algorithm of reinforcement learning is used to automatically adjust the strategy parameters to respond to market and environmental changes. The specific formula is:

[0041] New policy = old policy + α·(environmental benefit - cost), where α is the learning rate.

[0042] Furthermore, the execution feedback module includes a strategy execution unit, a result monitoring unit, a feedback analysis unit and a strategy adjustment unit; wherein:

[0043] Strategy execution unit: used to apply the power dispatch and carbon emission reduction strategies formulated by the strategy generation module to market operations. Strategy execution includes adjusting the operation mode of power plants, allocating power resource distribution, and implementing carbon emission control measures.

[0044] Result monitoring unit: used to collect data on strategy execution in real time, including information on power production, consumption, carbon emissions, and market response. The monitoring data is obtained through sensor networks, smart meters, and online monitoring systems.

[0045] Feedback Analysis Unit: Based on the data collected by the Result Monitoring Unit, it evaluates the effectiveness of the strategy. Specifically, it uses data analysis and machine learning techniques, including regression analysis and cluster analysis, to analyze the effectiveness of the implementation strategy and identify problems and improvement points.

[0046] Strategy Adjustment Unit: Adjust and optimize existing strategies based on the evaluation results of the feedback analysis unit. Specifically, the decision support system is used to simulate the potential effects of different strategy adjustment plans and select the optimal plan. The basis for strategy adjustment includes cost-benefit analysis, environmental impact assessment and market demand forecast to ensure continuous optimization of strategies and adapt to market changes.

[0047] Furthermore, the interactive interface module includes a user interface design unit, a real-time data display unit, a policy feedback display unit, a policy adjustment operation unit and a security authentication unit; wherein:

[0048] User Interface Design Unit: used to develop and maintain a user-friendly interface through which users can easily access and operate system functions. The interface design uses modern front-end technologies to build responsive designs, including HTML5, CSS3, and JavaScript, to ensure that it can be displayed and operated on a variety of devices;

[0049] Real-time data display unit: used to display real-time market data on the user interface, including information on electricity demand, supply, electricity and carbon emission prices. The real-time data display unit also includes the ability to update data in real time, specifically using WebSocket technology to push the latest data, and the data is displayed in the form of charts and dashboards;

[0050] Strategy feedback display unit: used to display the current status and historical results of strategy execution in the user interface, including the execution status of the power dispatch plan and the trend of carbon emissions. This information is presented in the form of charts and summaries.

[0051] Strategy adjustment operation unit: used to provide users with the function of manually adjusting strategies, allowing users to fine-tune strategies according to market changes. Users can adjust the parameters of power output and carbon emission control level through the operating controls of the slider and selection box on the interface;

[0052] Security authentication unit: used to implement preset security measures, including user authentication, permission control and data encryption. User authentication specifically adopts the standard authentication protocol OAuth2.0 to ensure that only authorized users can access the system. Permission control is used to ensure that users can only access data and functions within their permission scope.

[0053] Beneficial effects of the present invention:

[0054] The present invention realizes the effective coupling of the electricity market and the carbon emission market by integrating the electricity demand forecast and the carbon emission calculation module. This coupling mechanism enables the electricity supply decision to take into account the cost and environmental impact of carbon emissions, thereby optimizing the electricity production and distribution strategy. At the same time, carbon emission control measures can be more accurately adjusted according to the real-time demand and supply of the electricity market, enhancing the pertinence and effectiveness of environmental protection measures, and achieving dual optimization of environmental protection and resource efficiency.

[0055] The present invention provides a dynamic adjustment mechanism through a strategy generation module and an execution feedback module, allowing electricity and carbon emission strategies to be quickly adjusted according to market changes and policy updates. This flexibility ensures that the system can adapt to future market and environmental changes, improves the timeliness and effectiveness of decision-making, and through continuous monitoring of market and environmental data, the system can optimize its operation in real time, reduce unnecessary waste of resources, and improve the economic benefits of energy use.

[0056] The present invention, through the interface designed by the interactive interface module, enables energy companies, government agencies and related stakeholders to view market dynamics and strategy execution effects in real time and adjust strategies as needed. This not only enhances the user experience, but also improves the system's openness, transparency and participation, promotes multi-party collaboration and information sharing, and enhances the social and economic value and environmental benefits of the entire system. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 A schematic diagram of a market-coupled energy efficiency optimization system according to an embodiment of the present invention;

[0059] Figure 2 Schematic diagram of a power demand prediction module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0060] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0061] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0062] like Figure 1-Figure 2 As shown, the energy efficiency optimization system based on the coupling of electricity and carbon emission markets includes an electricity demand forecasting module, a carbon emission calculation module, a market coupling module, a strategy generation module, an execution feedback module and an interactive interface module; wherein:

[0063] Power demand forecasting module: used to collect data on multiple factors including historical power consumption data, weather conditions, and economic activity index, and use improved deep learning networks to predict future power demand;

[0064] Carbon emission calculation module: Calculate the corresponding carbon emissions according to the energy type and quantity in the process of electricity production and consumption;

[0065] Market coupling module: Generates supply and demand reports for the electricity and carbon emission markets based on predicted electricity demand and carbon emission data, and automatically adjusts electricity prices and carbon emission trading prices to optimize the energy efficiency of the overall market;

[0066] Strategy generation module: Based on the data provided by the market coupling module, formulate specific power dispatch and carbon emission reduction strategies to optimize power efficiency and minimize environmental impact;

[0067] Execution feedback module: implements the strategies of the strategy generation module, monitors the execution results, adjusts future strategy generation based on market feedback, and ensures continuous optimization of the system and adaptability to market changes;

[0068] Interactive interface module: provides users with an operation interface, including real-time market data display, strategy execution feedback, and manual strategy adjustment functions, to enhance the system's interactivity and user experience.

[0069] The power demand forecasting module includes a data collection unit, a data processing unit, a deep learning network unit and an output unit; wherein:

[0070] Data collection unit: used to collect data on various factors that affect electricity demand, including historical electricity consumption data, weather conditions, and economic activity index. The historical electricity consumption data is obtained from the power company's database, including information on past electricity consumption, electricity consumption time periods, and peak electricity consumption; weather condition data, including temperature, humidity, and sunshine duration, is obtained through a data sharing interface with the meteorological department; economic activity index data is obtained through a subscription service to obtain economic indicator reports issued by economic research institutions;

[0071] Data processing unit: Use data preprocessing technology to standardize and normalize data, eliminate noise and outliers in the data, and improve the accuracy and reliability of data analysis; in addition, the data processing unit is also responsible for time series analysis of data, identifying periodic and trend characteristics in the data, and providing representative training data for deep learning networks;

[0072] Deep learning network unit: Use an improved deep learning network to predict future electricity demand. The network structure includes a combination of convolutional neural network (CNN) and recurrent neural network (RNN) to process time series data and capture long-term dependencies and seasonal changes in the data. The network optimizes network parameters through repeated training and adjustment to improve the accuracy and robustness of the prediction. Cross-validation and hyperparameter tuning strategies are also used in the training process to ensure the model's wide adaptability to future data and prediction accuracy.

[0073] Output unit: Based on the analysis results of the deep learning network unit, the output unit generates a power demand forecast report for the future time period. The report is presented in the form of charts and numbers, clearly showing the predicted power demand trend, peak and valley time points, and providing decision support information for the market coupling module.

[0074] The data processing unit includes:

[0075] Data preprocessing subunit: used to standardize and normalize the collected data. First, the standardization process calculates the mean and standard deviation of each data (such as electricity consumption, temperature, etc.) and converts the data into a format with a mean of 0 and a standard deviation of 1 using the following formula: Among them, x is the original data, μ is the mean value, and σ is the standard deviation. Standardization helps to eliminate the impact of different dimensions and make the data distribution consistent. Next, normalization is performed to scale the data to the [0,1] interval. The specific formula is:

[0076] Among them, min(x) and max(x) are the minimum and maximum values ​​of the data, respectively. Normalization helps to deal with situations where standardization is not applicable, including when the data is not normally distributed. Finally, the outlier detection technology of the box plot method (Boxplot) is used to identify and process outliers in the data. Outliers are defined using IQR (interquartile range) with the formula: IQR = Q3-Q1, where Q1 and Q3 are the first quartile and the third quartile of the data, respectively. Points outside Q1-1.5×IQR and Q3+1.5×IQR are usually considered outliers;

[0077] Time series analysis subunit: Use time series analysis techniques to identify the periodicity and trend characteristics of the data. First, use the autocorrelation function (ACF) and partial autocorrelation function (PACF) to identify the time-dependent structure in the data. The autocorrelation function formula is: Among them, x t Represents the observed value at time point t, which can be the value of electricity demand, carbon emissions, etc. at time t; represents the average of all observations, that is, It is used to normalize data and reduce the impact of data dimensions at different time points; τ is the time lag, which means comparing the current value with the value lagged by τ time units; n is the total number of observation cycles, for example, in power demand forecasting, it may be the total number of days or hours of data in the past few years; the numerator is used to calculate the sum of the difference between the value at the current time point and its average value, and the product of the difference between the value at the lagged time point τ and the average value, which reflects the correlation of the time series itself at different time lags; the denominator is used to calculate the sum of the squares of the difference between the value at all time points and its average value, which is used to normalize the autocorrelation function value; the formula of the partial autocorrelation function is: Among them, Corr(a,b) represents the correlation between variables a and b; x t Same as above, indicating the observed value at time point t; represents the observed value x at time point t t The linear prediction of x t Previous value; x t+τ represents the observed value at time point t+τ; Represents the observed value x at time point t+τ t+τ The linear prediction of x t+τ previous value; this formula is used to calculate the direct impact of a given lagged variable in a time series, removing the impact of intermediate lags, and is very useful for modeling lags with specific impacts; then, seasonal decomposition time series analysis techniques such as STL (seasonal and trend decomposition using Loess) are applied to decompose the time series into trend, seasonal, and random components, which helps the deep learning network to better understand and predict the behavior of time series data; through the above detailed data preprocessing and time series analysis, the present invention can significantly improve the efficiency of data use and the accuracy of the prediction model, which not only optimizes the formulation of energy efficiency management strategies, but also improves the adaptability to future changes in electricity demand, and ultimately achieves the maximum efficiency of energy use and the optimization of environmental protection.

[0078] The deep learning network unit includes:

[0079] Network structure design: A combined deep learning network structure is adopted, including the combination of convolutional neural network (CNN) and recurrent neural network (RNN). Convolutional neural network is used to extract spatial features in time series data, while recurrent neural network is used to process sequence data with strong time dependence. The convolutional neural network layer uses multiple convolutional layers to extract local features in the input data. Each convolutional layer processes data through convolution operation. The formula is: y = w*x + b, where x is the output of the input layer or the previous layer, w is the weight of the convolution kernel, b is the bias, * indicates the convolution operation, and y is the output of the convolution layer. The recurrent neural network layer uses the long short-term memory network (LSTM) to capture the long-term dependency in the time series. The long short-term memory network is its cell state and three gate structures, including input gate, forget gate, and output gate. The specific calculation formula is:

[0080] f t =σ(W f ·[h t-1 ,x t ]+b f );

[0081] i t =σ(W i ·[h t-1 ,x t ]+b i );

[0082]

[0083]

[0084] o t =σ(W o ·[h t-1 ,x t ]+b o );

[0085] h t =o t *tanh(C t ), where f t ,i t ,o t are the activation values ​​of the forget gate, input gate, and output gate, respectively. is the candidate cell state, C t is the cell state at the current moment, h t is the output at the current moment, W and b are weight and bias parameters, σ is the sigmoid activation function, and tanh is the hyperbolic tangent activation function;

[0086] Network training and optimization: A large amount of historical power demand data is used to train the above network. The training process includes forward propagation and back propagation algorithms. The optimization algorithm is Adam or SGD, which is used to adjust the network weights to minimize the error between the predicted value and the actual value. Specifically, the mean square error MSE is used as the loss function. The specific formula is: Among them, y i is the actual power demand value, is the predicted value, n is the total number of samples;

[0087] Output generation: The trained deep learning network can predict future electricity demand based on the latest input data. The output data includes the predicted electricity demand and its fluctuation range, providing accurate data support for the market coupling module. The above-mentioned deep learning network unit can efficiently process and predict complex time series data, especially the dynamic changes in electricity demand, through the precisely designed and trained deep neural network. This prediction capability not only improves the management efficiency of power resources, but also helps to optimize the operation of the power market and carbon emission market, and ultimately achieve the goal of energy conservation and emission reduction.

[0088] The carbon emission calculation module includes a data collection unit, an energy type identification unit, a carbon emission factor loading unit and a carbon emission calculation unit; wherein:

[0089] Data collection unit: used to collect detailed data on electricity production and consumption, including the use of coal, natural gas, solar energy and wind energy. The data sources include power plant operation records, grid transmission data and terminal consumption data to ensure that the collected information is accurate and comprehensive;

[0090] Energy type identification unit: used to classify the collected energy usage data and distinguish different energy types. Specifically, the collected raw data is matched with the preset energy type database using database matching technology to ensure that the data of each energy source is correctly classified and recorded;

[0091] Carbon emission factor loading unit: used to store carbon emission factors corresponding to different energy types. The carbon emission factors are based on the latest environmental protection standards and research results. The carbon emission factors represent the carbon emissions generated per unit of energy consumption in kilograms of carbon dioxide equivalent / MJ or kilowatt-hour;

[0092] Carbon emission calculation unit: After obtaining energy consumption data and corresponding carbon emission factors, the following formula is used to calculate the total carbon emissions: Total carbon emissions = ∑(energy consumption i ×Carbon emission factor i ), where i represents different energy types and energy consumption i Refers to the carbon emission factor of each energy type used within a predetermined time period iIt is the preset carbon emission amount according to the energy type;

[0093] Through the precise data collection, intelligent data processing and accurate calculation of the above-mentioned units, the carbon emission calculation module of the present invention can provide detailed carbon emission data, which helps power companies and environmental regulatory agencies to better understand and manage carbon emissions. In addition, the application of this module helps to optimize the way electricity is produced and consumed, promote more environmentally friendly energy use strategies, and promote the realization of environmental protection and sustainable development goals.

[0094] The market coupling module includes a data integration unit, a supply and demand report generation unit, a price adjustment unit, and a real-time monitoring unit; among which:

[0095] Data integration unit: used to collect and integrate data from the power demand forecasting module and the carbon emission calculation module. It uses advanced database management methods to ensure data integrity and consistency. The integrated data includes the predicted power demand and calculated carbon emissions, which are the basis for generating market supply and demand reports.

[0096] Supply and demand report generation unit: Based on the power demand and carbon emission data provided by the data integration unit, a detailed market supply and demand report is generated using statistical analysis and model prediction methods. The report includes power supply and demand forecasts, carbon emission forecasts, and potential market imbalances. The following formula is used for market balance analysis: Market balance = supply - demand, where both supply and demand are predicted values. This analysis helps market operators identify supply and demand contradictions and make timely adjustments;

[0097] Price adjustment unit: Automatically adjust electricity prices and carbon emission trading prices according to supply and demand reports. Specifically, it uses a dynamic pricing algorithm to adjust prices according to market supply and demand status to promote market balance. Price adjustment follows the following basic principles: Price adjustment = benchmark price × (1 + α × supply and demand ratio), where α is the adjustment coefficient, the supply and demand ratio represents the ratio of demand to supply, and the benchmark price is the initial price set based on historical data;

[0098] Real-time monitoring unit: monitors market response and tracks the effect of price adjustment in real time. Specifically, it uses market feedback data including transaction volume and price changes to evaluate the effectiveness of previous price adjustments and provide data support for the next adjustment. Through the precise data integration, real-time supply and demand report generation, dynamic price adjustment and continuous monitoring of the above-mentioned market coupling module, the present invention can effectively promote the balance of the electricity market and the carbon emission market, optimize resource allocation, and reduce energy waste. This market optimization not only improves energy efficiency, but also promotes environmental protection and economic benefits.

[0099] The strategy generation module includes a data receiving unit, a strategy planning unit, an environmental impact assessment unit and a strategy optimization unit; wherein:

[0100] Data receiving unit: used to receive data from the market coupling module, including adjusted electricity and carbon emission prices, market supply and demand reports, which provide real-time and accurate input for strategy formulation, ensuring that the data basis of the strategy is the latest and most accurate;

[0101] Strategy planning unit: Use optimization algorithms to develop power dispatch and carbon emission reduction strategies: The power dispatch strategy uses linear programming to allocate power resources in order to meet market demand while meeting the lowest cost. Using linear programming to optimize power distribution will reduce power pressure during peak hours and increase power utilization during off-peak hours. The specific formula is: Among them, c i represents the electricity cost in different time periods, p i Indicates the electricity production in the corresponding time period; the carbon emission reduction strategy will combine carbon trading and carbon capture methods to optimize carbon emission reduction, specifically by increasing carbon capture facilities and adjusting the energy mix to reduce total carbon emissions;

[0102] Environmental Impact Assessment Unit: Use the Life Cycle Assessment (LCA) method to analyze the potential impact of various strategies on the environment. The LCA method evaluates the environmental impact of the entire process from raw material acquisition, production, use to disposal to ensure that the proposed strategy is not only economically reasonable but also environmentally friendly;

[0103] Strategy optimization unit: Based on the results of environmental impact assessment and market feedback, the adaptive control algorithm of reinforcement learning is used to automatically adjust the strategy parameters to respond to market and environmental changes. The specific formula is:

[0104] New strategy = old strategy + α·(environmental benefit - cost), where α is the learning rate, environmental benefit quantifies the positive impact of the strategy on the environment, and cost takes into account the economic investment of implementing the strategy;

[0105] Through the detailed strategic planning, environmental impact assessment and continuous optimization of the above-mentioned units, the strategy generation module can efficiently formulate and continuously improve power dispatch and carbon emission reduction strategies, which not only ensures the economy and efficiency of energy use, but also greatly reduces environmental impact and helps achieve sustainable development goals. In addition, the adaptive optimization of the strategy ensures that the system can flexibly respond to market and policy changes, enhancing the long-term availability and effectiveness of the system.

[0106] The execution feedback module includes a strategy execution unit, a result monitoring unit, a feedback analysis unit and a strategy adjustment unit; wherein:

[0107] Strategy execution unit: used to apply the power dispatch and carbon emission reduction strategies formulated by the strategy generation module to market operations. Strategy execution includes adjusting the operation mode of power plants, allocating power resource distribution, and implementing carbon emission control measures.

[0108] Result monitoring unit: used to collect data on strategy execution in real time, including information on power production, consumption, carbon emissions, and market response. Monitoring data is obtained through sensor networks, smart meters, and online monitoring systems to ensure the real-time and accuracy of data.

[0109] Feedback Analysis Unit: Based on the data collected by the Result Monitoring Unit, the effectiveness of the strategy is evaluated. Specifically, data analysis and machine learning techniques are used, including regression analysis and cluster analysis, to analyze the effectiveness of the implementation strategy and identify problems and improvement points. For example, by analyzing the relationship between peak electricity consumption and carbon emissions, the effectiveness of the current strategy in reducing carbon emissions during peak periods is evaluated.

[0110] Strategy Adjustment Unit: Adjust and optimize existing strategies based on the evaluation results of the feedback analysis unit. Specifically, the decision support system is used to simulate the potential effects of different strategy adjustment plans and select the best plan. The basis for strategy adjustment includes cost-benefit analysis, environmental impact assessment and market demand forecast to ensure continuous optimization of strategies and adapt to market changes.

[0111] The execution feedback module not only ensures the effective execution of the strategy by systematically implementing, monitoring, analyzing and adjusting the energy efficiency optimization strategy, but also achieves rapid adaptation to market and environmental changes. The feedback loop mechanism of this module enhances the flexibility and responsiveness of the system, promotes the continuous improvement and optimization of energy management, effectively improves energy efficiency and reduces environmental impact, and helps achieve sustainable development goals.

[0112] The interactive interface module includes a user interface design unit, a real-time data display unit, a strategy feedback display unit, a strategy adjustment operation unit and a security authentication unit; wherein:

[0113] User Interface Design Unit: used to develop and maintain a user-friendly interface through which users can easily access and operate system functions. The interface design uses modern front-end technologies to build responsive designs, including HTML5, CSS3, and JavaScript, to ensure that it can be displayed and operated on a variety of devices;

[0114] Real-time data display unit: used to display real-time market data on the user interface, including information on electricity demand, supply, electricity and carbon emission prices. The real-time data display unit also includes the ability to update data in real time, specifically using WebSocket technology to push the latest data. The data is displayed in the form of charts and dashboards, allowing users to intuitively understand the market situation;

[0115] Strategy feedback display unit: used to display the current status and historical results of strategy execution in the user interface, including the execution status of the power dispatch plan and the trend of carbon emissions. This information is presented in the form of charts and summaries so that users can evaluate the effectiveness of the strategy.

[0116] Strategy adjustment operation unit: used to provide users with the function of manually adjusting strategies, allowing users to fine-tune strategies according to market changes. Users can adjust the parameters of power output and carbon emission control level through the slider and selection box operation controls on the interface. This unit is directly connected to the strategy generation module to ensure that the adjustment operation can provide real-time feedback and affect strategy optimization;

[0117] Security authentication unit: used to implement preset security measures, including user authentication, authority control and data encryption. User authentication specifically adopts the standard authentication protocol OAuth2.0 to ensure that only authorized users can access the system. Authority control is used to ensure that users can only access data and functions within their authority.

[0118] The interactive interface module provides a clear, intuitive and responsive user interface, allowing users to easily access real-time market data and strategy execution status and adjust strategies as needed. This module improves the system's operational efficiency and user satisfaction. At the same time, enhanced security measures ensure the system's data security and operational reliability, and enhance users' trust and reliance on the system.

[0119] The present invention is intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An energy efficiency optimization system based on the coupling of electricity and carbon emission markets, characterized in that: It includes power demand forecasting module, carbon emission calculation module, market coupling module, strategy generation module, execution feedback module and interactive interface module; among which: Power demand forecasting module: used to collect data on multiple factors including historical power consumption data, weather conditions, and economic activity index, and use improved deep learning networks to predict future power demand; Carbon emission calculation module: Calculate the corresponding carbon emissions according to the energy type and quantity in the process of electricity production and consumption; Market coupling module: Generates supply and demand reports for the electricity and carbon emission markets based on predicted electricity demand and carbon emission data, and automatically adjusts electricity prices and carbon emission trading prices; Strategy generation module: formulates specific power dispatch and carbon emission reduction strategies based on the data provided by the market coupling module; Execution feedback module: implements the strategies of the strategy generation module, monitors the execution results, adjusts future strategy generation based on market feedback, and ensures continuous optimization of the system and adaptability to market changes; Interactive interface module: provides users with an operation interface, including real-time market data display, strategy execution feedback, and manual strategy adjustment functions.

2. The energy efficiency optimization system based on coupling of electricity and carbon emission markets according to claim 1 is characterized in that: The power demand prediction module includes a data collection unit, a data processing unit, a deep learning network unit and an output unit; wherein: Data collection unit: used to collect data on various factors that affect electricity demand, including historical electricity consumption data, weather conditions, and economic activity index. The historical electricity consumption data is obtained from the power company's database, including information on past electricity consumption, electricity consumption time periods, and peak electricity consumption; weather condition data, including temperature, humidity, and sunshine duration, is obtained through a data sharing interface with the meteorological department; economic activity index data is obtained through a subscription service to obtain economic indicator reports issued by economic research institutions; Data processing unit: Use data preprocessing technology to standardize and normalize data, eliminate noise and outliers in the data, and improve the accuracy and reliability of data analysis; in addition, the data processing unit is also responsible for time series analysis of data, identifying periodic and trend characteristics in the data, and providing representative training data for deep learning networks; Deep learning network unit: Use an improved deep learning network to predict future electricity demand. The network structure includes a combination of convolutional neural networks and recurrent neural networks to process time series data and capture long-term dependencies and seasonal changes in the data. The network optimizes network parameters through repeated training and adjustment to improve the accuracy and robustness of the prediction. Cross-validation and hyperparameter tuning strategies are also used in the training process to ensure the model's wide adaptability to future data and prediction accuracy. Output unit: Based on the analysis results of the deep learning network unit, the output unit generates a power demand forecast report for the future time period. The report is presented in the form of charts and numbers, clearly showing the predicted power demand trend, peak and valley time points, and providing decision support information for the market coupling module.

3. The energy efficiency optimization system based on coupling of electricity and carbon emission markets according to claim 2 is characterized in that: The data processing unit comprises: Data preprocessing subunit: used to standardize and normalize the collected data. First, the standardization process converts the data into a format with a mean of 0 and a standard deviation of 1 by calculating the mean and standard deviation of each data using the following formula: Among them, x is the original data, μ is the mean value, and σ is the standard deviation. Standardization helps to eliminate the impact of different dimensions and make the data distribution consistent. Next, normalization is performed to scale the data to the [0,1] interval. The specific formula is: Among them, min(x) and max(x) are the minimum and maximum values ​​of the data, respectively. Normalization helps to deal with situations where standardization is not applicable, including when the data is not normally distributed. Finally, the outlier detection technology of the box plot method is used to identify and process outliers in the data. Outliers are defined using IQR, and the formula is: IQR = Q3-Q1, where Q1 and Q3 are the first quartile and third quartile of the data, respectively; Time series analysis subunit: Use time series analysis techniques to identify the periodicity and trend characteristics of data. First, use the autocorrelation function and partial autocorrelation function to identify the time-dependent structure in the data. The autocorrelation function formula is: Among them, x t represents the observed value at time point t; represents the average of all observations, that is, It is used to normalize data and reduce the impact of data dimensions at different time points; τ is the time lag, which means comparing the current value with the value lagged by τ time units; n is the total number of observation cycles; the formula of the partial autocorrelation function is: Among them, Corr(a,b) represents the correlation between variables a and b; x t Same as above, indicating the observed value at time point t; represents the observed value x at time point t t The linear prediction of x t Previous value; x t+τ represents the observed value at time point t+τ; Represents the observed value x at time point t+τ t+τ The linear prediction of x t+τ The time series analysis technique of seasonal decomposition is then applied to decompose the time series into trend, seasonal, and random components.

4. The energy efficiency optimization system based on coupling of electricity and carbon emission markets according to claim 3 is characterized in that: The deep learning network unit comprises: Network structure design: A combined deep learning network structure is adopted, including the combination of convolutional neural network and recurrent neural network. Convolutional neural network is used to extract spatial features in time series data, while recurrent neural network is used to process sequence data with strong time dependence. The convolutional neural network layer uses multiple convolutional layers to extract local features in the input data. Each convolutional layer processes data through convolution operation. The formula is: y = w*x + b, where x is the output of the input layer or the previous layer, w is the weight of the convolution kernel, b is the bias, * indicates the convolution operation, and y is the output of the convolution layer. The recurrent neural network layer uses a long short-term memory network to capture long-term dependencies in time series. The long short-term memory network is its cell state and three gate structures, including input gate, forget gate, and output gate. Network training and optimization: A large amount of historical power demand data is used to train the above network. The training process includes forward propagation and back propagation algorithms. The optimization algorithm is Adam or SGD, which is used to adjust the network weights to minimize the error between the predicted value and the actual value. Specifically, the mean square error MSE is used as the loss function. The specific formula is: Among them, y i is the actual power demand value, is the predicted value, n is the total number of samples; Output generation: The trained deep learning network can predict future electricity demand based on the latest input data. The output data includes the predicted electricity demand and its fluctuation range, providing accurate data support for the market coupling module.

5. The energy efficiency optimization system based on coupling of electricity and carbon emission markets according to claim 1 is characterized in that: The carbon emission calculation module includes a data collection unit, an energy type identification unit, a carbon emission factor loading unit and a carbon emission calculation unit; wherein: Data collection unit: used to collect detailed data on electricity production and consumption, including the use of coal, natural gas, solar energy and wind energy. The data sources include power plant operation records, grid transmission data and terminal consumption data. Energy type identification unit: used to classify the collected energy usage data and distinguish different energy types. Specifically, the collected raw data is matched with the preset energy type database using database matching technology; Carbon emission factor loading unit: used to store carbon emission factors corresponding to different energy types. The carbon emission factors are based on the latest environmental protection standards and research results. The carbon emission factors represent the carbon emissions generated per unit of energy consumption in kilograms of carbon dioxide equivalent / MJ or kilowatt-hour; Carbon emission calculation unit: After obtaining energy consumption data and corresponding carbon emission factors, the following formula is used to calculate the total carbon emissions: Total carbon emissions = ∑(energy consumption i ×Carbon emission factor i ), where i represents different energy types and energy consumption i Refers to the carbon emission factor of each energy type used within a predetermined time period i It is the preset carbon emission amount according to the energy type.

6. The energy efficiency optimization system based on coupling of electricity and carbon emission markets according to claim 1, characterized in that: The market coupling module includes a data integration unit, a supply and demand report generation unit, a price adjustment unit and a real-time monitoring unit; wherein: Data integration unit: used to collect and integrate data from the power demand forecasting module and the carbon emission calculation module, using advanced database management methods to ensure data integrity and consistency. The integrated data includes the predicted power demand and calculated carbon emissions; Supply and demand report generation unit: Based on the power demand and carbon emission data provided by the data integration unit, a detailed market supply and demand report is generated using statistical analysis and model prediction methods. The report includes power supply and demand forecasts, carbon emission forecasts, and potential market imbalances. Price adjustment unit: Automatically adjust electricity prices and carbon emission trading prices according to supply and demand reports. Specifically, it uses a dynamic pricing algorithm to adjust prices according to market supply and demand status to promote market balance. Price adjustment follows the following basic principles: Price adjustment = benchmark price × (1 + α × supply and demand ratio), where α is the adjustment coefficient, the supply and demand ratio represents the ratio of demand to supply, and the benchmark price is the initial price set based on historical data; Real-time monitoring unit: monitors market responses and tracks the effects of price adjustments in real time, specifically using market feedback data including trading volume and price changes to evaluate the effectiveness of previous price adjustments and provide data support for the next adjustment.

7. The energy efficiency optimization system based on coupling of electricity and carbon emission markets according to claim 1 is characterized in that: The strategy generation module includes a data receiving unit, a strategy planning unit, an environmental impact assessment unit and a strategy optimization unit; wherein: Data receiving unit: used to receive data from the market coupling module, including adjusted electricity and carbon emission prices, and market supply and demand reports; Strategy Planning Unit: Use optimization algorithms to develop power dispatch and carbon emission reduction strategies: The power dispatch strategy uses linear programming methods to allocate power resources in order to meet market demand while meeting the lowest cost. The specific formula is: Among them, c i represents the electricity cost in different time periods, p i Indicates the electricity production in the corresponding time period; the carbon emission reduction strategy will combine carbon trading and carbon capture methods to optimize carbon emission reduction, specifically by increasing carbon capture facilities and adjusting the energy mix to reduce total carbon emissions; Environmental Impact Assessment Unit: Use the Life Cycle Assessment (LCA) method to analyze the potential impact of various strategies on the environment. The LCA method evaluates the environmental impact of the entire process from raw material acquisition, production, use to disposal to ensure that the proposed strategy is not only economically reasonable but also environmentally friendly; Strategy optimization unit: Based on the results of environmental impact assessment and market feedback, the adaptive control algorithm of reinforcement learning is used to automatically adjust the strategy parameters to respond to market and environmental changes. The specific formula is: New policy = old policy + α·(environmental benefit - cost), where α is the learning rate.

8. The energy efficiency optimization system based on coupling of electricity and carbon emission markets according to claim 1, characterized in that: The execution feedback module includes a strategy execution unit, a result monitoring unit, a feedback analysis unit and a strategy adjustment unit; wherein: Strategy execution unit: used to apply the power dispatch and carbon emission reduction strategies formulated by the strategy generation module to market operations. Strategy execution includes adjusting the operation mode of power plants, allocating power resource distribution, and implementing carbon emission control measures. Result monitoring unit: used to collect data on strategy execution in real time, including information on power production, consumption, carbon emissions, and market response. The monitoring data is obtained through sensor networks, smart meters, and online monitoring systems. Feedback Analysis Unit: Based on the data collected by the Result Monitoring Unit, it evaluates the effectiveness of the strategy. Specifically, it uses data analysis and machine learning techniques, including regression analysis and cluster analysis, to analyze the effectiveness of the implementation strategy and identify problems and improvement points. Strategy Adjustment Unit: Adjust and optimize existing strategies based on the evaluation results of the feedback analysis unit. Specifically, the decision support system is used to simulate the potential effects of different strategy adjustment plans and select the optimal plan. The basis for strategy adjustment includes cost-benefit analysis, environmental impact assessment and market demand forecast to ensure continuous optimization of strategies and adapt to market changes.

9. The energy efficiency optimization system based on coupling of electricity and carbon emission markets according to claim 1, characterized in that: The interactive interface module includes a user interface design unit, a real-time data display unit, a policy feedback display unit, a policy adjustment operation unit and a security authentication unit; wherein: User Interface Design Unit: used to develop and maintain a user-friendly interface through which users can easily access and operate system functions. The interface design uses modern front-end technologies to build responsive designs, including HTML5, CSS3, and JavaScript, to ensure that it can be displayed and operated on a variety of devices; Real-time data display unit: used to display real-time market data on the user interface, including information on electricity demand, supply, electricity and carbon emission prices. The real-time data display unit also includes the ability to update data in real time, specifically using WebSocket technology to push the latest data, and the data is displayed in the form of charts and dashboards; Strategy feedback display unit: used to display the current status and historical results of strategy execution in the user interface, including the execution status of the power dispatch plan and the trend of carbon emissions. This information is presented in the form of charts and summaries. Strategy adjustment operation unit: used to provide users with the function of manually adjusting strategies, allowing users to fine-tune strategies according to market changes. Users can adjust the parameters of power output and carbon emission control level through the operating controls of the slider and selection box on the interface; Security authentication unit: used to implement preset security measures, including user authentication, permission control and data encryption. User authentication specifically adopts the standard authentication protocol OAuth2.0 to ensure that only authorized users can access the system. Permission control is used to ensure that users can only access data and functions within their permission scope.

Images