Smart energy consumption analysis method

Abstract

The invention discloses a smart energy consumption analysis method, and relates to the technical field of energy consumption analysis, and the method comprises the steps: obtaining the real-time energy consumption data of a plurality of energy devices; based on the spatial and temporal distribution characteristics of the energy consumption data, predicting the energy consumption of the equipment by using a time sequence prediction algorithm; an energy consumption prediction result is adjusted in combination with external variables, and a personalized energy efficiency analysis report is provided; based on an energy efficiency analysis result, proposing an optimization suggestion; real-time energy consumption monitoring is carried out, and abnormal energy consumption conditions are fed back and alarmed. According to the method provided by the invention, a comprehensive, intelligent and efficient energy efficiency analysis and optimization framework is provided for the smart energy system by integrating a plurality of innovative technologies, and the energy utilization efficiency can be effectively improved, the energy consumption can be reduced, the energy waste can be reduced, and the energy efficiency of the smart energy system can be improved by real-time data acquisition and intelligent analysis of a plurality of energy devices. Meanwhile, personalized energy efficiency reports and optimization suggestions are provided for users, and more intelligent energy management is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption analysis, and in particular to a method for analyzing energy consumption of smart energy. Background Art

[0002] With the continuous increase in global energy demand and the increasing tension of energy resources, the application of smart energy systems has gradually become an important development trend in modern cities and industrial fields. Smart energy can achieve real-time monitoring, analysis, prediction and optimization of energy consumption through the integration of technologies such as big data, cloud computing, the Internet of Things, and artificial intelligence, so as to improve energy utilization efficiency, reduce energy waste, and reduce costs. At the same time, the operation of the energy system also faces problems such as numerous energy equipment, huge energy consumption data, and complex dynamic changes. Therefore, higher requirements are placed on the ability to obtain, process and analyze real-time energy consumption data.

[0003] Most current energy management systems rely on fixed scheduling strategies and experience-based equipment management, lacking intelligent energy efficiency prediction and personalized optimization mechanisms. With the rapid development of sensor technology and smart devices, how to accurately and efficiently collect real-time energy consumption data of multiple energy devices, and adjust equipment operation strategies through efficient analysis and prediction models to achieve intelligent scheduling, load balancing and energy conservation has become an urgent problem to be solved in the field of smart energy. Therefore, energy consumption prediction based on spatiotemporal distribution characteristics, adjustment of external variables, intelligent equipment scheduling, and integration of real-time monitoring and alarm systems can help enterprises and cities achieve refined energy management, improve energy utilization, reduce unnecessary energy waste, reduce operating costs, and promote sustainable development. Summary of the invention

[0004] In order to solve the above technical problems, a method for analyzing energy consumption of smart energy is provided. This technical solution solves the above problems.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A method for analyzing energy consumption of smart energy, comprising:

[0007] Obtain real-time energy consumption data of multiple energy devices, pre-process the real-time energy consumption data, transmit the processed real-time energy consumption data to the cloud platform, and store it in the energy efficiency analysis database;

[0008] Based on the spatiotemporal distribution characteristics of energy consumption data, the energy consumption of equipment is predicted using a time series prediction algorithm;

[0009] Adjust energy consumption forecast results based on external variables, including weather, personnel activities, and equipment status, to provide personalized energy efficiency analysis reports;

[0010] Based on the results of energy efficiency analysis, make optimization suggestions, including equipment scheduling, load balancing and energy saving measures;

[0011] Carry out real-time energy consumption monitoring, and provide feedback and alarm when abnormal energy consumption occurs.

[0012] Preferably, the acquiring of real-time energy consumption data of a plurality of energy devices, preprocessing the real-time energy consumption data, transmitting the processed real-time energy consumption data to a cloud platform, and storing the processed real-time energy consumption data in an energy efficiency analysis database specifically includes:

[0013] Based on the API interface of energy equipment, real-time energy consumption data is obtained, and the energy consumption data includes heat, electricity and gas flow data. The time interval is set to regularly collect energy consumption data at the set time interval;

[0014] The generated noise is removed by using a filter, and the missing values ​​are filled by using linear function interpolation according to the existing data points. The linear function interpolation filling formula is:

[0015]

[0016] Where t1 is the time 1 of the known data point, t2 is the target time point to be interpolated, t3 is the time 3 of the known data point, x(t1) is the known data value corresponding to time point t1, x(t3) is the known data value corresponding to time point t3, and x(t2) is the value corresponding to the target time point t2 to be estimated;

[0017] The processed data will be transmitted to the cloud platform via the network for further storage.

[0018] Preferably, the specific steps of predicting the energy consumption of the equipment using a time series prediction algorithm based on the spatiotemporal distribution characteristics of the energy consumption data are:

[0019] Analyze the spatiotemporal distribution characteristics of equipment energy consumption data, and analyze the trend of energy consumption over time based on the timestamps of data points, including daily, weekly and monthly periodic changes;

[0020] Based on the location, type and usage status of the equipment, the equipment is grouped, and then the energy consumption data of each group of equipment is aggregated to obtain the energy consumption under different locations, types and states;

[0021] Group devices by location, obtain the total energy consumption and average energy consumption of each location, group devices by type, obtain the energy consumption of each device type, obtain the difference in energy consumption between the on state and the standby state, and use heat maps to reveal spatiotemporal characteristics;

[0022] The energy consumption of the equipment is predicted based on the time series prediction algorithm. The time series model is trained using historical energy consumption data. Based on the trained model, energy consumption in the future time period is predicted.

[0023] Preferably, the predicting of equipment energy consumption based on a time series prediction algorithm specifically includes:

[0024] Among them, the time series prediction algorithm formula is:

[0025]

[0026] In the formula, y t The predicted energy consumption at time t, c is a constant term, is the autoregressive coefficient, θ1∈ t-1 The influence coefficient of the error term in the lag period t-1 on the current value, θ2∈ t-2 is the influence coefficient of the error term in the lag period t-2 on the current value, p is the order of the autoregressive term, q is the order of the sliding average term, ∈ t is the random error term at the current moment, y t-1 is the energy consumption value of the time series at time t-1, y t-2 is the energy consumption value of the time series at time t-2, y t-p is the energy consumption value of the time series at time tp.

[0027] Preferably, the energy consumption forecast result is adjusted by combining external variables, wherein the external variables include weather, personnel activities and equipment status, and providing a personalized energy efficiency analysis report specifically includes:

[0028] Based on the collection of historical energy consumption data, including electricity, natural gas and water energy consumption data;

[0029] Obtain weather data related to energy consumption through the weather service API interface, and collect data related to personnel activities, including the number of personnel, office area usage, and production line workload;

[0030] Obtain data related to the equipment operating status, including equipment switch status, workload, and equipment failure information;

[0031] Align data from different sources by timestamp and generate new features based on data from external variables, including:

[0032] Generate a "temperature difference" feature based on weather data;

[0033] Generate "people density" feature based on people activity data;

[0034] Generate "equipment load" characteristics based on equipment status;

[0035] Generate personalized energy efficiency analysis reports based on different user needs and scenarios, including:

[0036] Energy efficiency trends: Shows the trend of energy consumption over time;

[0037] Impact analysis: Analyze the specific impact of external variables on energy consumption, including increased air conditioning load when the temperature rises and increased use of lighting systems and equipment when the number of people increases;

[0038] Energy-saving suggestions: Based on the prediction results and the impact of external variables, energy-saving suggestions are provided, including optimizing equipment usage time, adjusting air conditioning temperature settings, and improving personnel activity patterns;

[0039] Incorporate external variables into the forecast model for adjustment;

[0040] The personalized energy efficiency analysis report is presented in a visual way, and the energy consumption prediction model is reviewed and updated regularly. When external variables change, the model is adjusted.

[0041] Preferably, the incorporation of external variables into the prediction model for adjustment specifically includes:

[0042] Incorporate external variables into the prediction model for adjustment. Based on the multiple regression formula, add external variables as additional independent variables into the regression model. The multiple regression formula is:

[0043] y t =β0+β1X1(t)+β2X2(t)+…+β k X k (t)+∈ t

[0044] In the formula, y t is the energy consumption at time t, X1X2X k is an external variable, X k is the kth external variable, β0β1β k is the regression coefficient, ∈ t is the error term.

[0045] Preferably, the personalized energy efficiency analysis report is presented in a visual manner, and the energy consumption prediction model is reviewed and updated periodically. When the external variables change, the model is adjusted, specifically including:

[0046] Deploy a real-time monitoring system to continuously collect external variable data and establish an automatic alarm mechanism. When the external variable changes beyond the preset threshold, anomaly detection is triggered and the system automatically adjusts.

[0047] Based on the Pearson correlation coefficient method, the impact of external variables on energy consumption changes is evaluated. If a strong correlation is found between external variables, the model is adjusted in a timely manner. The Pearson correlation coefficient calculation formula is:

[0048]

[0049] In the formula, x i and i is the i-th sample value of variables x and y, is the mean of variable x, is the mean value of variable y, r is the Pearson correlation coefficient value;

[0050] Based on the Pearson correlation coefficient value, the correlation between variables was determined;

[0051] When the correlation between variables is strongly correlated, the energy consumption prediction model is retrained and the existing model is updated by continuously introducing new data.

[0052] Preferably, judging the correlation between variables based on the Pearson correlation coefficient value specifically includes:

[0053] Strong correlation: The absolute value of the Pearson correlation coefficient r is close to 1, indicating that there is a strong linear relationship between the external variables and energy consumption, and these external variables have a significant impact on energy consumption;

[0054] Moderate correlation: The absolute value of the Pearson correlation coefficient is between 0.3 and 0.7, indicating that there is a moderate linear relationship between the external variable and energy consumption;

[0055] Weak correlation: If the absolute value of the correlation coefficient is less than 0.3, it means that the relationship between the external variable and energy consumption is weak.

[0056] Preferably, based on the results of energy efficiency analysis, optimization suggestions are put forward, including equipment scheduling, load balancing and energy saving measures, including:

[0057] According to the energy efficiency analysis report of real-time energy efficiency data, an intelligent scheduling system based on data analysis and machine learning is introduced to automatically optimize the equipment operation plan and dynamically adjust the equipment load and operation time according to the real-time energy efficiency data;

[0058] Based on energy efficiency analysis, evaluate the energy efficiency performance of each device under different loads, identify load fluctuations during equipment operation, and distribute loads based on the energy efficiency characteristics of different devices.

[0059] Preferably, the load distribution includes: utilizing the difference between peak and valley electricity prices and the demand response mechanism to dispatch the equipment load to a suitable period of time during the period of lower electricity prices, utilizing the energy storage system to store energy during the period of low electricity prices, balancing the load and reducing energy demand during peak periods.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] The method proposed in the present invention integrates multiple innovative technologies to provide a comprehensive, intelligent and efficient energy efficiency analysis and optimization framework for the smart energy system. Through real-time data collection and intelligent analysis of multiple energy devices, it can effectively improve energy utilization efficiency, reduce energy consumption, and reduce energy waste. At the same time, it also provides users with personalized energy efficiency reports and optimization suggestions, helping enterprises and cities to achieve more intelligent and refined energy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a step flow framework diagram of the present invention. DETAILED DESCRIPTION

[0063] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0064] Reference Figure 1 As shown, a method for analyzing energy consumption of smart energy includes:

[0065] Step 1:

[0066] Based on the API interface of energy equipment, real-time energy consumption data is obtained, and the energy consumption data includes heat, electricity and gas flow data. The time interval is set to regularly collect energy consumption data at the set time interval;

[0067] The generated noise is removed by using a filter, and the missing values ​​are filled by using linear function interpolation according to the existing data points. The linear function interpolation filling formula is:

[0068]

[0069] Where t1 is the time 1 of the known data point, t2 is the target time point to be interpolated, t3 is the time 3 of the known data point, x(t1) is the known data value corresponding to time point t1, x(t3) is the known data value corresponding to time point t3, and x(t2) is the value corresponding to the target time point t2 to be estimated;

[0070] The processed data will be transmitted to the cloud platform via the network for further storage.

[0071] Step 2:

[0072] Analyze the spatiotemporal distribution characteristics of equipment energy consumption data, and analyze the trend of energy consumption over time based on the timestamps of data points, including daily, weekly and monthly periodic changes;

[0073] Based on the location, type and usage status of the equipment, the equipment is grouped, and then the energy consumption data of each group of equipment is aggregated to obtain the energy consumption under different locations, types and states;

[0074] Group devices by location, obtain the total energy consumption and average energy consumption of each location, group devices by type, obtain the energy consumption of each device type, obtain the difference in energy consumption between the on state and the standby state, and use heat maps to reveal spatiotemporal characteristics;

[0075] Predict equipment energy consumption based on time series prediction algorithms, use historical energy consumption data to train time series models, and predict energy consumption in future time periods based on the trained models;

[0076] Among them, the time series prediction algorithm formula is:

[0077]

[0078] In the formula, y t The predicted energy consumption at time t, c is a constant term, is the autoregressive coefficient, θ1∈ t-1 The influence coefficient of the error term in the lag period t-1 on the current value, θ2∈ t-2 is the influence coefficient of the error term in the lag period t-2 on the current value, p is the order of the autoregressive term, q is the order of the sliding average term, ∈ t is the random error term at the current moment, y t-1 is the energy consumption value of the time series at time t-1, y t-2 is the energy consumption value of the time series at time t-2, y t-p is the energy consumption value of the time series at time tp.

[0079] Step 3:

[0080] Based on the collection of historical energy consumption data, including electricity, natural gas and water energy consumption data;

[0081] Obtain weather data related to energy consumption through the weather service API interface, and collect data related to personnel activities, including the number of personnel, office area usage, and production line workload;

[0082] Obtain data related to the equipment operating status, including equipment switch status, workload, and equipment failure information;

[0083] Align data from different sources by timestamp and generate new features based on data from external variables, including:

[0084] Generate a "temperature difference" feature based on weather data;

[0085] Generate "people density" feature based on people activity data;

[0086] Generate "equipment load" characteristics based on equipment status;

[0087] Generate personalized energy efficiency analysis reports based on different user needs and scenarios, including:

[0088] Energy efficiency trends: Shows the trend of energy consumption over time;

[0089] Impact analysis: Analyze the specific impact of external variables on energy consumption, including increased air conditioning load when the temperature rises and increased use of lighting systems and equipment when the number of people increases;

[0090] Energy-saving suggestions: Based on the prediction results and the impact of external variables, energy-saving suggestions are provided, including optimizing equipment usage time, adjusting air conditioning temperature settings, and improving personnel activity patterns;

[0091] Incorporating external variables into the prediction model for adjustment. Preferably, incorporating external variables into the prediction model for adjustment specifically includes:

[0092] Incorporate external variables into the prediction model for adjustment. Based on the multiple regression formula, add external variables as additional independent variables into the regression model. The multiple regression formula is:

[0093] y t =β0+β1X1(t)+β2X2(t)+…+β k X k (t)+∈ t

[0094] In the formula, y t is the energy consumption at time t, X1X2X k is an external variable, X k is the kth external variable, β0β1β k is the regression coefficient, ∈ t is the error term;

[0095] Deploy a real-time monitoring system to continuously collect external variable data and establish an automatic alarm mechanism. When the external variable changes beyond the preset threshold, anomaly detection is triggered and the system automatically adjusts.

[0096] Based on the Pearson correlation coefficient method, the impact of external variables on energy consumption changes is evaluated. If a strong correlation is found between external variables, the model is adjusted in a timely manner. The Pearson correlation coefficient calculation formula is:

[0097]

[0098] In the formula, x i andi is the i-th sample value of variables x and y, is the mean of variable x, is the mean value of variable y, r is the Pearson correlation coefficient value;

[0099] Based on the Pearson correlation coefficient value, the correlation between variables was determined;

[0100] Strong correlation: The absolute value of the Pearson correlation coefficient r is close to 1, indicating that there is a strong linear relationship between the external variables and energy consumption, and these external variables have a significant impact on energy consumption;

[0101] Moderate correlation: The absolute value of the Pearson correlation coefficient is between 0.3 and 0.7, indicating that there is a moderate linear relationship between the external variable and energy consumption;

[0102] Weak correlation: If the absolute value of the correlation coefficient is less than 0.3, it means that the relationship between the external variable and energy consumption is weak.

[0103] Step 4:

[0104] According to the energy efficiency analysis report of real-time energy efficiency data, an intelligent scheduling system based on data analysis and machine learning is introduced to automatically optimize the equipment operation plan and dynamically adjust the equipment load and operation time according to the real-time energy efficiency data;

[0105] Based on energy efficiency analysis, evaluate the energy efficiency performance of each device under different loads, identify the load fluctuations of equipment operation, and according to the energy efficiency characteristics of different equipment, utilize the peak and valley electricity price differences and demand response mechanism to dispatch the equipment load to the appropriate time period during the period of low electricity price. Use the energy storage system to store energy during the period of low electricity price, balance the load and reduce energy demand during peak periods.

[0106] Step 5:

[0107] Carry out real-time energy consumption monitoring, and provide feedback and alarm when abnormal energy consumption occurs.

[0108] The use process of the present invention is:

[0109] Obtain real-time energy consumption data of multiple energy devices, pre-process the real-time energy consumption data, transmit the processed real-time energy consumption data to the cloud platform, and store it in the energy efficiency analysis database;

[0110] Based on the spatiotemporal distribution characteristics of energy consumption data, the energy consumption of equipment is predicted using a time series prediction algorithm;

[0111] Adjust energy consumption forecast results based on external variables, including weather, personnel activities, and equipment status, to provide personalized energy efficiency analysis reports;

[0112] Based on the results of energy efficiency analysis, make optimization suggestions, including equipment scheduling, load balancing and energy saving measures;

[0113] Carry out real-time energy consumption monitoring, and provide feedback and alarm when abnormal energy consumption occurs.

[0114] In summary, the advantages of the present invention are:

[0115] By obtaining real-time energy consumption data of multiple energy devices based on the API interface, using filtering technology to remove noise and using linear interpolation to fill in missing values, the accuracy and completeness of energy consumption data are ensured. After the data is transmitted to the cloud platform for further storage and processing, it provides a stable and high-quality data foundation for subsequent energy efficiency analysis and prediction;

[0116] By using the time series prediction algorithm and analyzing the spatiotemporal distribution characteristics of equipment energy consumption data, it is possible to accurately predict energy consumption changes in future time periods. This energy consumption prediction method based on spatiotemporal characteristics takes into account the periodic changes in energy consumption and combines factors such as equipment type, usage status, and location for multi-dimensional aggregation. It can better capture the changing patterns of equipment energy consumption, thereby achieving more accurate energy consumption prediction.

[0117] Through the training of historical energy consumption data and time series models, dynamic prediction of future energy consumption is achieved, effectively responding to changes in energy demand and sudden load fluctuations;

[0118] The impact of external variables such as weather, personnel activities and equipment status on energy consumption cannot be ignored. By integrating meteorological data, personnel activity data and equipment status information, the energy consumption forecast results can be dynamically adjusted to provide personalized energy efficiency analysis reports. This adjustment mechanism can reflect the impact of external environmental changes on energy consumption in real time, providing more accurate and flexible optimization strategies for energy management.

[0119] In the energy consumption prediction model, the multivariate regression analysis method is used to introduce external variables as additional independent variables, which further improves the accuracy of the prediction. The relationship between external variables and energy consumption is evaluated through the Pearson correlation coefficient, which can better identify the mutual influence between variables, adjust the prediction model in time, and improve the intelligence level of energy efficiency analysis;

[0120] Based on the results of energy efficiency analysis, combined with real-time energy efficiency data and equipment operating status, an intelligent scheduling system is used for automated equipment scheduling and load balancing. By utilizing strategies such as peak and valley electricity price differences, demand response mechanisms, and energy storage system scheduling, equipment operation can be scheduled during periods of lower electricity prices, and the load can be balanced through the energy storage system to reduce energy demand during peak periods.

[0121] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for analyzing smart energy consumption, characterized in that: include: Obtain real-time energy consumption data of multiple energy devices, pre-process the real-time energy consumption data, transmit the processed real-time energy consumption data to the cloud platform, and store it in the energy efficiency analysis database; Based on the spatiotemporal distribution characteristics of energy consumption data, the energy consumption of equipment is predicted using a time series prediction algorithm; Adjust energy consumption forecast results based on external variables, including weather, personnel activities, and equipment status, to provide personalized energy efficiency analysis reports; Based on the results of energy efficiency analysis, make optimization suggestions, including equipment scheduling, load balancing and energy saving measures; Carry out real-time energy consumption monitoring, and provide feedback and alarm when abnormal energy consumption occurs.

2. A method for analyzing smart energy consumption according to claim 1, characterized in that: The acquiring of real-time energy consumption data of multiple energy devices, preprocessing of the real-time energy consumption data, transmitting the processed real-time energy consumption data to the cloud platform, and storing the processed real-time energy consumption data in the energy efficiency analysis database specifically includes: Based on the API interface of energy equipment, real-time energy consumption data is obtained, and the energy consumption data includes heat, electricity and gas flow data. The time interval is set to regularly collect energy consumption data at the set time interval; The generated noise is removed by using a filter, and the missing values ​​are filled by using linear function interpolation according to the existing data points. The linear function interpolation filling formula is: Where t1 is the time 1 of the known data point, t2 is the target time point to be interpolated, t3 is the time 3 of the known data point, x(t1) is the known data value corresponding to time point t1, x(t3) is the known data value corresponding to time point t3, and x(t2) is the value corresponding to the target time point t2 to be estimated; The processed data will be transmitted to the cloud platform via the network for further storage.

3. A method for analyzing smart energy consumption according to claim 2, characterized in that: The specific steps of using the time series prediction algorithm to predict the energy consumption of the equipment based on the spatiotemporal distribution characteristics of the energy consumption data are as follows: Analyze the spatiotemporal distribution characteristics of equipment energy consumption data and analyze the trend of energy consumption over time based on the timestamps of data points; Based on the location, type and usage status of the equipment, the equipment is grouped, and then the energy consumption data of each group of equipment is aggregated to obtain the energy consumption under different locations, types and states; Group devices by location, obtain the total energy consumption and average energy consumption of each location, group devices by type, obtain the energy consumption of each device type, obtain the difference in energy consumption between the on state and the standby state, and use heat maps to reveal spatiotemporal characteristics; The energy consumption of the equipment is predicted based on the time series prediction algorithm. The time series model is trained using historical energy consumption data. Based on the trained model, energy consumption in the future time period is predicted.

4. The method for analyzing smart energy consumption according to claim 3, characterized in that: The time series prediction algorithm is used to predict the energy consumption of the equipment. include: Among them, the time series prediction algorithm formula is: In the formula, y t The predicted energy consumption at time t, c is a constant term, is the autoregressive coefficient, θ1∈ t-1 The influence coefficient of the error term in the lag period t-1 on the current value, θ2∈ t-2 is the influence coefficient of the error term in the lag period t-2 on the current value, p is the order of the autoregressive term, q is the order of the sliding average term, ∈ t is the random error term at the current moment, y t-1 is the energy consumption value of the time series at time t-1, y t-2 is the energy consumption value of the time series at time t-2, y t-p is the energy consumption value of the time series at time tp.

5. A method for analyzing smart energy consumption according to claim 4, characterized in that: The energy consumption forecast result is adjusted by combining external variables, wherein the external variables include weather, personnel activities and equipment status, and providing a personalized energy efficiency analysis report specifically includes: Based on the collection of historical energy consumption data, including electricity, natural gas and water energy consumption data; Obtain weather data related to energy consumption through the weather service API interface, and collect data related to personnel activities, including the number of personnel, office area usage, and production line workload; Obtain data related to the equipment operating status, including equipment switch status, workload, and equipment failure information; Align data from different sources by timestamp and generate new features based on data from external variables; Generate personalized energy efficiency analysis reports based on different user needs and scenarios; Incorporate external variables into the forecast model for adjustment; The personalized energy efficiency analysis report is presented in a visual way, and the energy consumption prediction model is reviewed and updated regularly. When external variables change, the model is adjusted.

6. A method for analyzing smart energy consumption according to claim 5, characterized in that: The incorporation of external variables into the forecasting model for adjustment specifically includes: Incorporate external variables into the prediction model for adjustment. Based on the multiple regression formula, add external variables as additional independent variables into the regression model. The multiple regression formula is: y t =β0+β1X1(t)+β2X2(t)+…+β k X k (t)+∈ t In the formula, y t is the energy consumption at time t, X1X2X k is an external variable, X k is the kth external variable, β0β1β k is the regression coefficient, ∈ t is the error term.

7. A method for analyzing smart energy consumption according to claim 6, characterized in that: The personalized energy efficiency analysis report is presented in a visual manner, and the energy consumption prediction model is reviewed and updated periodically. When external variables change, the model is adjusted, specifically including: Deploy a real-time monitoring system to continuously collect external variable data and establish an automatic alarm mechanism. When the external variable changes beyond the preset threshold, anomaly detection is triggered and the system automatically adjusts. Based on the Pearson correlation coefficient method, the impact of external variables on energy consumption changes is evaluated. If a strong correlation is found between external variables, the model is adjusted in a timely manner. The Pearson correlation coefficient calculation formula is: In the formula, x i and i is the i-th sample value of variables x and y, is the mean of variable x, is the mean value of variable y, r is the Pearson correlation coefficient value; Based on the Pearson correlation coefficient value, the correlation between variables was determined; When the correlation between variables is strongly correlated, the energy consumption prediction model is retrained and the existing model is updated by continuously introducing new data.

8. The method for analyzing smart energy consumption according to claim 7, characterized in that: The determination of the correlation between the variables based on the Pearson correlation coefficient value specifically includes: Strong correlation: The absolute value of the Pearson correlation coefficient r is close to 1, indicating that there is a strong linear relationship between the external variables and energy consumption, and these external variables have a significant impact on energy consumption; Moderate correlation: The absolute value of the Pearson correlation coefficient is between 0.3 and 0.7, indicating that there is a moderate linear relationship between the external variable and energy consumption; Weak correlation: If the absolute value of the correlation coefficient is less than 0.3, it means that the relationship between the external variable and energy consumption is weak.

9. A method for analyzing smart energy consumption according to claim 8, characterized in that: Based on the results of energy efficiency analysis, optimization suggestions are put forward, including equipment scheduling, load balancing and energy saving measures. Specifically, they include: According to the energy efficiency analysis report of real-time energy efficiency data, an intelligent scheduling system based on data analysis and machine learning is introduced to automatically optimize the equipment operation plan and dynamically adjust the equipment load and operation time according to the real-time energy efficiency data; Based on energy efficiency analysis, evaluate the energy efficiency performance of each device under different loads, identify load fluctuations during equipment operation, and distribute loads based on the energy efficiency characteristics of different devices.

10. A method for analyzing smart energy consumption according to claim 9, characterized in that: The load distribution includes: utilizing the difference in peak and valley electricity prices and the demand response mechanism to dispatch equipment loads to appropriate time periods during periods of lower electricity prices, utilizing energy storage systems to store energy during periods of low electricity prices, balancing loads and alleviating energy demand during peak periods.

Images