Electricity consumption analysis method for solitary population based on electricity consumption abnormity monitoring and analysis model
Through real-time data processing and personalized modeling based on the power consumption abnormality monitoring and analysis model, the problem that traditional power consumption monitoring methods are difficult to identify unusual power consumption patterns for people living alone is solved, and timely monitoring and early warning of power consumption abnormalities is achieved, which improves the Electricity safety and benefits.
Patent Information
- Application Number
- CN202411057312.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-02
- Publication Date
- 2024-12-17
AI Technical Summary
Traditional electricity monitoring methods rely on regular manual inspections, making it difficult to timely identify unusual electricity usage patterns of people living alone, lack intelligent analysis functions, and cannot provide personalized electricity usage suggestions or early warnings.
Based on the power consumption abnormality monitoring and analysis model, electricity consumption data is obtained in real time, key features are extracted after cleaning and preprocessing, electricity consumption abnormality monitoring model is constructed, thresholds are set and response mechanisms are established, and personalized power consumption optimization suggestions are provided.
Timely monitoring and early warning of electricity abnormalities for people living alone has been achieved, the safety and efficiency of electricity use has been improved, personalized electricity use suggestions have been provided, and the cost of electricity has been reduced.
Smart Images
Figure CN119150180A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of abnormal power consumption monitoring, and in particular to a method for analyzing power consumption of people living alone based on an abnormal power consumption monitoring and analysis model. Background Art
[0002] With the development of society and the increasing trend of population aging, the number of people living alone is gradually increasing. Since they live alone, their living and health conditions require special attention. One important aspect is their electricity consumption. The electricity consumption of people living alone is crucial to their quality of life and safety. However, there are some problems with current electricity consumption monitoring methods: traditional electricity consumption monitoring methods usually rely on regular manual inspections, which may lead to delayed detection of abnormal electricity consumption, thereby increasing the risk of emergencies; the electricity consumption patterns of people living alone may vary from individual to individual, and traditional methods have difficulty in accurately identifying when unusual electricity consumption patterns occur, such as sudden increases in energy consumption or sustained decreases in energy consumption; current electricity consumption monitoring systems usually lack intelligent analysis functions and cannot provide personalized electricity consumption recommendations or warnings for people living alone. Summary of the invention
[0003] In order to solve the above problems, the present invention provides a method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model.
[0004] To achieve the above object, the technical solution adopted by the present invention is:
[0005] On the one hand, a method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model comprises the following steps:
[0006] Obtain electricity consumption data of people living alone in real time;
[0007] Clean and preprocess the collected electricity consumption data and extract key features from the electricity consumption data;
[0008] Based on the extracted key features, a power consumption anomaly monitoring model is constructed, and the power consumption anomaly monitoring model is trained using historical power consumption data;
[0009] Through the power consumption anomaly monitoring model, anomalies in power consumption data can be monitored in real time;
[0010] Set thresholds for abnormal power usage and establish corresponding response mechanisms;
[0011] Based on long-term accumulated electricity consumption data, the electricity consumption patterns of people living alone are analyzed to provide them with electricity optimization suggestions.
[0012] Furthermore, the electricity consumption data at least includes electricity consumption, electricity consumption period and electricity consumption equipment information.
[0013] Furthermore, the extracted key features include power quantity features, power consumption pattern features, abnormal monitoring features and energy efficiency features.
[0014] Furthermore, the collected electricity consumption data is cleaned and preprocessed to extract key features from the electricity consumption data, including the following steps:
[0015] Removing outliers or noise data from the acquired electricity consumption data;
[0016] Identify and handle any missing electricity usage data points using interpolation or filling methods;
[0017] Extract key features from the processed electricity consumption data, wherein the key features include statistical indicators of electricity consumption, frequency domain features and time series features of electricity consumption curves;
[0018] The extracted key features are standardized.
[0019] Furthermore, the method of constructing a power consumption anomaly monitoring model based on the extracted key features and training the power consumption anomaly monitoring model using historical power consumption data includes the following steps:
[0020] Acquire the collected electricity consumption data and extract key features thereof;
[0021] Build an abnormal power consumption monitoring model based on time series analysis and machine learning algorithms;
[0022] Use historical electricity consumption data to train an abnormal electricity consumption monitoring model;
[0023] Evaluate the performance of the model using evaluation metrics;
[0024] Use the trained power consumption anomaly monitoring model to monitor and analyze real-time power consumption data.
[0025] Furthermore, the construction of an abnormal power consumption monitoring model based on time series analysis and machine learning algorithm includes the following steps:
[0026] Using the electricity consumption data as electricity consumption time series data;
[0027] Use the ARI MA model to model the data, calculate the residuals, and extract features about anomalies from the residual series;
[0028] Build a neural network model based on the extracted features;
[0029] Use the training set to train the neural network model and perform cross-validation;
[0030] Input the test data into the trained neural network model;
[0031] Set the threshold for anomaly detection, and adjust the threshold according to application requirements;
[0032] Use evaluation metrics to assess the performance of the model.
[0033] Furthermore, the neural network model is specifically as follows: taking the residual features extracted by ARI MA as input, using a multilayer perceptron or a convolutional neural network, setting appropriate nodes and activation functions, outputting anomaly probability, using binary cross entropy as a loss function, optimizing through training and cross-validation, setting thresholds for anomaly detection, and evaluating performance indicators.
[0034] Furthermore, the priorities of the set thresholds include, from high to low, a safety threshold, a health threshold, a comfort threshold, an energy saving threshold and a general threshold.
[0035] Furthermore, the response mechanism includes abnormal notification and alarm, emergency contact setting, remote control or power cut and emergency service dispatch.
[0036] On the other hand, a system for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model includes: a data acquisition module, an abnormality monitoring module, a data analysis module and an alarm module;
[0037] The data collection module is used to collect electricity consumption data of people living alone in real time based on smart meters or sensor networks;
[0038] The abnormality monitoring module is used to monitor abnormal conditions in power consumption data in real time through a power consumption abnormality monitoring model;
[0039] The data analysis module is used to analyze the electricity consumption patterns of people living alone and provide them with electricity consumption optimization suggestions;
[0040] The alarm module is used to trigger an alarm when monitoring an abnormality, and respond to the abnormal situation by remote control or cutting off the power supply.
[0041] The beneficial effects of the present invention are:
[0042] By acquiring electricity consumption data in real time and using an abnormal monitoring model, the system can timely monitor abnormal electricity consumption of people living alone and give early warning of possible problems, such as electrical failures, improper electricity use, etc. Cleaning and preprocessing the collected electricity consumption data can improve the quality and accuracy of the data and ensure the reliability of the data used for modeling and analysis.
[0043] By extracting key features and constructing an abnormal power consumption monitoring model, the present invention can perform personalized modeling based on individual power consumption habits and characteristics, thereby improving the accuracy of abnormality detection. By setting abnormal power consumption thresholds and establishing a response mechanism, it is possible to automatically respond to abnormal situations, ensuring that abnormalities are handled in a timely manner, thereby improving power safety.
[0044] The system of the present invention can analyze the electricity consumption patterns of people living alone, understand their electricity consumption habits and needs, and provide them with personalized electricity consumption optimization suggestions to help them use electricity resources reasonably, reduce electricity costs, and improve electricity efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] Figure 1 It is a flow chart of a method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model of the present invention.
[0046] Figure 2 It is a flowchart of step S2 provided in one embodiment of the present invention.
[0047] Figure 3 It is a flowchart of step S3 provided in one embodiment of the present invention. DETAILED DESCRIPTION
[0048] See also Figure 1-3 As shown, the present invention relates to a method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model.
[0049] Example 1
[0050] A method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model comprises the following steps:
[0051] S1: Real-time acquisition of electricity consumption data of people living alone, including electricity consumption, electricity consumption period and electricity consumption equipment information;
[0052] Specifically, smart meters or sensor networks are deployed in the homes of people living alone to record electricity usage in real time and set the frequency of data collection.
[0053] S2: Cleaning and preprocessing the collected electricity consumption data, and extracting key features from the electricity consumption data, wherein the key features include electricity consumption features, electricity consumption mode features, abnormal monitoring features, and energy efficiency features;
[0054] Specifically, the collected electricity consumption data is cleaned and preprocessed to extract key features from the electricity consumption data, including the following steps:
[0055] S21: removing abnormal values or noise data from the acquired power consumption data;
[0056] S22: Identify and process any missing electricity consumption data points, using interpolation or filling methods;
[0057] S23: extracting key features from the processed electricity consumption data, wherein the key features include statistical indicators of electricity consumption, frequency domain features and time series features of the electricity consumption curve;
[0058] S24: Standardize the extracted key features.
[0059] S3: Build an abnormal power consumption monitoring model based on the extracted key features, and use historical power consumption data to train the abnormal power consumption monitoring model;
[0060] Specifically, the method of constructing an abnormal power consumption monitoring model based on the extracted key features and training the abnormal power consumption monitoring model using historical power consumption data includes the following steps:
[0061] S31: Obtain the collected electricity consumption data and extract its key features;
[0062] S32: Building an abnormal power consumption monitoring model based on time series analysis and machine learning algorithms;
[0063] S33: Using historical electricity consumption data to train an abnormal electricity consumption monitoring model;
[0064] S34: Evaluate the performance of the model using evaluation metrics;
[0065] S35: Use the trained power consumption anomaly monitoring model to monitor and analyze real-time power consumption data.
[0066] S4: Monitor abnormal conditions in power consumption data in real time through the power consumption abnormality monitoring model;
[0067] Specifically, the power consumption data collected in real time is feature extracted and predicted or evaluated in real time with the established abnormal monitoring model. The threshold of the abnormal score is set to determine whether to trigger an abnormal alarm. The sliding window technology is used to continuously monitor the power consumption data to capture instantaneous and continuous abnormal situations.
[0068] S5: Set the threshold of abnormal power consumption and establish a corresponding response mechanism;
[0069] Specifically, set a threshold for abnormal power usage, which can be adjusted based on historical data and business needs. Establish a response mechanism, including alarm notifications, SMS or email notifications to people living alone or related maintenance personnel. Determine the urgency of the abnormal situation so that appropriate action can be taken.
[0070] S6: Based on the long-term accumulated electricity consumption data, analyze the electricity consumption patterns of people living alone and provide them with electricity optimization suggestions.
[0071] Specifically, based on the long-term accumulated electricity consumption data, the system can provide single people with analysis reports on electricity consumption patterns and targeted electricity optimization suggestions to help them use electricity resources reasonably and efficiently. Provide a real-time monitoring interface or application so that single people can check the current electricity consumption at any time and get timely feedback when abnormal situations occur. Provide electricity optimization suggestions, such as suggestions for saving electricity costs, optimizing equipment use, and improving electricity efficiency.
[0072] In this embodiment, through data cleaning and preprocessing steps, outliers can be removed, missing data can be processed, and key features can be extracted. This helps to improve the accuracy and reliability of the model. An abnormal power consumption monitoring model is established and trained using historical power consumption data. This model can automatically identify abnormal power consumption, including sudden and continuous abnormalities, and provides an automated monitoring method. Set the threshold for abnormal power consumption and establish a corresponding response mechanism, including alarm notification, SMS or email notification to single people or relevant maintenance personnel. This helps to take timely action and reduce potential risks. Through the long-term accumulated power consumption data, analysis reports on power consumption patterns and power consumption optimization suggestions can be provided for single people. This helps them use power resources more reasonably and efficiently, save electricity costs, and improve power efficiency. Provide a real-time monitoring interface or application so that single people can view the current power consumption at any time and get timely feedback when abnormal situations occur. This improves the user's visualization and control of their own power consumption.
[0073] Example 2
[0074] According to the method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model described in Example 1, wherein the abnormal electricity consumption monitoring model is constructed based on time series analysis and machine learning algorithm, the following steps are included:
[0075] Using the electricity consumption data as electricity consumption time series data;
[0076] Use the ARI MA model to model the data, calculate the residuals, and extract features about anomalies from the residual series;
[0077] Build a neural network model based on the extracted features;
[0078] Use the training set to train the neural network model and perform cross-validation;
[0079] Input the test data into the trained neural network model;
[0080] Set the threshold for anomaly detection, and adjust the threshold according to application requirements;
[0081] Use evaluation metrics to assess the performance of the model;
[0082] The neural network model is specifically:
[0083] Input layer: The residual features extracted by ARIMA are used as input features.
[0084] Hidden layer: Use a multilayer perceptron or convolutional neural network, setting appropriate nodes and activation functions.
[0085] Output layer: Outputs the anomaly probability and uses the Sigma id activation function to limit the output between 0 and 1.
[0086] Loss function: Binary cross entropy is used as the loss function to measure the performance of anomaly detection.
[0087] Optimization algorithm: Use gradient descent or its variants to optimize the neural network model parameters.
[0088] Perform optimization through training and cross-validation, set thresholds for anomaly detection, and evaluate performance metrics.
[0089] In this embodiment, the combination of time series analysis and neural network model can improve the accuracy of anomaly detection, reduce the false alarm rate, and ensure timely detection of real anomalies. The model can learn and adapt to changes in power consumption patterns based on historical data, so it can cope with anomalies in different situations. Through the neural network model, rapid monitoring and analysis of real-time power consumption data can be achieved to help take timely action. The threshold of anomaly detection can be freely adjusted according to application requirements to meet the needs of different users and environments.
[0090] Example 3
[0091] According to the method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model described in Example 2, the priorities of the set thresholds include, from high to low, a safety threshold, a health threshold, a comfort threshold, an energy saving threshold and a general threshold.
[0092] Specifically, safety threshold: This is the highest priority threshold used to detect abnormal power usage that may cause safety issues or dangerous situations. For example, there may be overload, short circuit, etc.
[0093] Health threshold: This level of threshold is used to detect abnormal conditions that may have a negative impact on the life of electrical equipment or power systems. For example, frequent high load conditions may cause premature failure of equipment.
[0094] Comfort threshold: This level of threshold is used to detect abnormal conditions that may affect the user's comfort or quality of life. For example, the room temperature is too high or too low, the lighting is obviously abnormal, etc.
[0095] Energy conservation threshold: This level of threshold is used to detect abnormal power usage that may result in energy waste, such as leaving the heating or air conditioning on when no one is home.
[0096] General Threshold: This level of threshold is used to detect general abnormal power usage that may not immediately affect safety, health, comfort, or energy waste, but may require user attention or action.
[0097] The response mechanism includes abnormal notification and alarm, emergency contact setting, remote control or power cut-off and emergency service dispatch.
[0098] Specifically, abnormal notification and alarm: When the monitoring model detects abnormal power consumption, it will trigger a notification or alarm to notify the relevant responsible person or the person living alone. The notification method can include SMS, email, App reminder, etc.
[0099] Emergency contact settings: Allow users to set emergency contacts. When an abnormal situation occurs, notifications can be automatically sent to the emergency contacts so that appropriate measures can be taken in time.
[0100] Remote control or power cut-off: In some cases, abnormal situations can be dealt with by remote control or power cut-off to ensure safety.
[0101] Emergency service dispatch: When serious abnormal power consumption occurs, the system can provide emergency service dispatch functions, such as sending electricians to deal with it.
[0102] In this embodiment, by setting the safety threshold, the system can detect and promptly notify the user about abnormal power usage that may cause safety problems or dangerous situations, such as overload and short circuit. This helps to prevent potential dangers such as damage to electrical equipment, power problems and fire. The setting of health thresholds helps to detect abnormal conditions that may have a negative impact on the life of electrical equipment or power systems. This helps to reduce the cost of repairing and replacing equipment and extend the life of equipment. The setting of comfort thresholds allows the system to detect abnormal conditions that affect user comfort or quality of life, such as abnormal temperature or lighting problems. This helps to improve the user's living experience. The setting of energy saving thresholds can detect abnormal power usage that may cause energy waste, such as continuously running heating or air conditioning when no one is living. This helps to reduce energy waste, reduce energy costs, and reduce adverse effects on the environment. The setting of general thresholds can be used to detect general abnormal power usage, even if it does not immediately affect safety, health, comfort or energy waste, but users can still be reminded and take appropriate measures to prevent potential problems.
[0103] The system's response mechanism includes abnormal notifications and alarms as well as emergency contact settings, ensuring that when an abnormal situation occurs, the relevant responsible person or people living alone can be notified in time and take necessary actions. The system also provides the function of remote control or power cut-off to deal with serious abnormal situations and ensure safety. This can remotely prevent further problems from occurring. For serious power consumption abnormalities, the system can provide emergency service dispatch functions, such as sending electricians to deal with them, to ensure that the problem is resolved quickly.
[0104] Example 4
[0105] According to the method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model described in Example 3, a system for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model comprises: a data acquisition module, an abnormality monitoring module, a data analysis module and an alarm module;
[0106] The data collection module is used to collect electricity consumption data of people living alone in real time based on smart meters or sensor networks;
[0107] Specifically, smart meters or sensor networks are deployed and installed in the homes or circuits of people living alone, and the data collection frequency is set to collect electricity consumption data.
[0108] The abnormality monitoring module is used to monitor abnormal conditions in power consumption data in real time through a power consumption abnormality monitoring model;
[0109] Specifically, based on the power consumption anomaly monitoring model, a power consumption anomaly detection system is constructed. The power consumption data from the data acquisition module is received in real time. The pre-trained power consumption anomaly monitoring model is used to monitor the power consumption data and detect abnormal conditions. When an abnormality is detected, the timestamp and characteristics of the abnormal event are recorded and an alarm is triggered.
[0110] The data analysis module is used to analyze the electricity consumption patterns of people living alone and provide them with electricity consumption optimization suggestions;
[0111] Specifically, the electricity consumption data accumulated over a long period of time is used to analyze the electricity consumption patterns of people living alone. Using data analysis technology, peak hours and high-energy-consuming devices in electricity consumption patterns are identified. Power consumption optimization suggestions are generated, such as suggestions for saving electricity costs, suggestions for equipment replacement, and energy-saving strategies. A user interface is provided to display the analysis results and suggestions.
[0112] The alarm module is used to trigger an alarm when monitoring an abnormality, and respond to the abnormal situation by remote control or cutting off the power supply.
[0113] Specifically, when an abnormal situation is detected, an alarm mechanism is triggered. The alarm can be implemented in a variety of ways, including sound alarm, SMS notification, email notification, etc. The access circuit can be remotely controlled to disconnect the power supply or cut off the power supply of the abnormal device to deal with emergency abnormal situations. The alarm module can also record abnormal events and generate reports for subsequent analysis.
[0114] In this embodiment, the system can timely discover potential safety problems, such as overload or short circuit, by real-time monitoring of abnormal conditions in power consumption data, thereby improving the living safety of people living alone. Through long-term accumulation and analysis of power consumption data, the system can identify peak hours and high-energy-consuming equipment in the power consumption mode, and provide users with power optimization suggestions, which helps to extend the life of electrical equipment and reduce the risk of equipment damage. Through power consumption mode analysis and optimization suggestions, the system can help users reduce energy consumption, reduce energy waste, reduce electricity costs, and also help reduce adverse effects on the environment. The alarm module of the system can trigger an alarm when an abnormal situation is detected, and notify the user through sound, text messages, emails, etc., so that the user can quickly take necessary actions to prevent the escalation of potential problems. The system provides the function of remotely controlling the circuit to disconnect the power supply or cut off the power supply of abnormal equipment, which can remotely respond to emergency abnormal situations and ensure the safety of users and residences. The data analysis module can provide users with detailed analysis results and power optimization suggestions on power consumption modes, helping users to better manage power consumption, improve comfort, and reduce costs. The system can also record abnormal events and generate reports for subsequent analysis, which helps users understand the evolution and trend of power consumption.
[0115] The above implementation modes are merely descriptions of the preferred implementation modes of the present invention, and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary engineering and technical personnel in the field shall fall within the protection scope determined by the claims of the present invention.
Claims
1. A method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model. It is characterized in that The following steps are involved: Obtain electricity consumption data of people living alone in real time; Clean and preprocess the collected electricity consumption data and extract key features from the electricity consumption data; Based on the extracted key features, a power consumption anomaly monitoring model is constructed, and the power consumption anomaly monitoring model is trained using historical power consumption data; Through the power consumption anomaly monitoring model, anomalies in power consumption data can be monitored in real time; Set thresholds for abnormal power usage and establish corresponding response mechanisms; Based on long-term accumulated electricity consumption data, the electricity consumption patterns of people living alone are analyzed to provide them with electricity optimization suggestions.
2. According to the method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model according to claim 1, It is characterized in that The electricity consumption data at least includes electricity consumption, electricity consumption period and electricity consumption equipment information.
3. According to the method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model according to claim 1, It is characterized in that The extracted key features include power consumption features, power consumption pattern features, abnormal monitoring features and energy efficiency features.
4. According to claim 1, a method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model, It is characterized in that The step of cleaning and preprocessing the collected electricity consumption data and extracting key features from the electricity consumption data includes the following steps: Removing outliers or noise data from the acquired electricity consumption data; Identify and handle any missing electricity usage data points using interpolation or filling methods; Extract key features from the processed electricity consumption data, wherein the key features include statistical indicators of electricity consumption, frequency domain features and time series features of electricity consumption curves; The extracted key features are standardized.
5. According to claim 1, a method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model, It is characterized in that The method of constructing a power consumption anomaly monitoring model based on the extracted key features and training the power consumption anomaly monitoring model using historical power consumption data includes the following steps: Acquire the collected electricity consumption data and extract key features thereof; Build an abnormal power consumption monitoring model based on time series analysis and machine learning algorithms; Use historical electricity consumption data to train an abnormal electricity consumption monitoring model; Evaluate the performance of the model using evaluation metrics; Use the trained power consumption anomaly monitoring model to monitor and analyze real-time power consumption data.
6. The method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model according to claim 5, It is characterized in that The method of constructing an abnormal power consumption monitoring model based on time series analysis and machine learning algorithm includes the following steps: Using the electricity consumption data as electricity consumption time series data; Use the ARIMA model to model the data, calculate the residuals, and extract features about anomalies from the residual series; Build a neural network model based on the extracted features; Use the training set to train the neural network model and perform cross-validation; Input the test data into the trained neural network model; Set the threshold for anomaly detection, and adjust the threshold according to application requirements; Use evaluation metrics to assess the performance of the model.
7. The method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model according to claim 6, It is characterized in that The neural network model specifically includes: taking the residual features extracted by ARIMA as input, using a multilayer perceptron or a convolutional neural network, setting appropriate nodes and activation functions, outputting anomaly probability, using binary cross entropy as a loss function, optimizing through training and cross-validation, setting thresholds for anomaly detection, and evaluating performance indicators.
8. According to claim 1, a method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model, It is characterized in that The priorities of the set thresholds include, from high to low, a safety threshold, a health threshold, a comfort threshold, an energy saving threshold and a general threshold.
9. The method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model according to claim 1, It is characterized in that The response mechanisms include abnormal notification and alarm, emergency contact setting, remote control or power cut-off and emergency service dispatch.
10. A system for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model. It is characterized in that The system is applied to a method for analyzing electricity consumption of people living alone based on an abnormal electricity consumption monitoring and analysis model as described in any one of claims 1 to 9, comprising: a data acquisition module, an abnormality monitoring module, a data analysis module and an alarm module; The data collection module is used to collect electricity consumption data of people living alone in real time based on smart meters or sensor networks; The abnormality monitoring module is used to monitor abnormal conditions in power consumption data in real time through a power consumption abnormality monitoring model; The data analysis module is used to analyze the electricity consumption patterns of people living alone and provide them with electricity consumption optimization suggestions; The alarm module is used to trigger an alarm when monitoring an abnormality, and respond to the abnormal situation by remote control or cutting off the power supply.