Intelligent electricity consumption behavior analysis and management method

Abstract

The invention discloses an intelligent power consumption behavior analysis and management method, relates to the technical field of energy management, and aims to improve energy consumption synergistic effect identification and management among equipment in a smart home through a load correlation analysis technology. The method comprises the following steps: collecting power consumption data of a plurality of electrical equipment in a family in real time through Internet of Things equipment or a sensor; a load incidence relation graph is constructed based on load fluctuation between the devices, the load fluctuation intensity relation between the devices is calculated through cross correlation analysis, mutual information analysis and other modes, and therefore the synergistic effect and potential faults between the devices are recognized. And optimizing the load association relation graph through a graph theory algorithm, carrying out equipment priority ranking, and optimizing an energy scheduling and management strategy. According to the method, the load fluctuation condition of the equipment can be monitored in real time, the abnormal power consumption behavior can be accurately identified, an intelligent load scheduling and energy efficiency management scheme is provided, and the safety, energy efficiency and intelligent level of household intelligent power management are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of energy management technology, and in particular to a method for analyzing and managing smart electricity usage behavior. Background Art

[0002] As the number and variety of electrical devices increase, the electrical load in homes and commercial buildings is becoming increasingly complex. Multiple appliances, such as air conditioners, refrigerators, washing machines, and water heaters, often operate simultaneously, and their energy consumption is influenced not only by their individual operating states but also by the synergistic effects of their interactions. In particular, when high-energy-consuming devices like air conditioners and refrigerators operate together, they can cause significant fluctuations in the power load, placing significant pressure on energy management in homes and buildings.

[0003] Most existing methods for analyzing electricity usage behavior focus on monitoring and analyzing the energy consumption of individual devices. By collecting and processing energy consumption data for each device, device operating patterns can be predicted and managed. However, these traditional methods often overlook the synergistic effects between devices. This is because when multiple devices operate together, their energy consumption fluctuations are interrelated, and this interplay cannot be accurately captured simply by analyzing the load characteristics of a single device. For example, in the summer, when air conditioners and refrigerators are used together, the increased cooling load of the air conditioner may overlap with the frequent activation of the refrigerator, leading to drastic load fluctuations. Traditional methods, which only analyze the behavior of individual devices, cannot identify the potential problems caused by this synergistic fluctuation.

[0004] Furthermore, existing energy consumption monitoring typically uses static, single-device-based or simple statistical models to predict energy consumption fluctuations and anomalies. This presents significant limitations when dealing with complex load fluctuations caused by multiple devices operating simultaneously. Traditional monitoring methods fail to effectively capture the temporal and functional relationships between devices, as well as the characteristics of load fluctuations. Especially when devices are simultaneously activated and frequently switching between operating modes, traditional methods often fail to detect abnormal load fluctuations in a timely manner, resulting in wasted energy, insufficient warning of equipment failures, and even impacting the electrical safety of the entire building or home.

[0005] Therefore, a smart electricity consumption behavior analysis and management method is proposed. Summary of the Invention

[0006] The purpose of the present invention is to solve the problem that when multiple electrical devices are running together, the energy consumption fluctuations between them are interrelated. This mutual influence cannot be accurately grasped by simply analyzing the load characteristics of a single device. Therefore, a smart electricity consumption behavior analysis and management method is proposed.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] A smart electricity usage behavior analysis and management method includes the following steps:

[0009] Collecting device information: Using IoT devices or sensors to collect real-time electricity usage data from multiple electrical devices in the home. The electricity usage data includes the power, operating time, voltage, current, and switch status of the device, which serves as the basic data for each device;

[0010] Modeling inter-device load correlation: Each device is treated as a node, and the load correlation relationships between devices are used as edges to build a device load correlation network. The load fluctuations of devices are reflected through time series data, which includes changes in device power and the start and stop times of devices.

[0011] Calculating the strength of load fluctuations: Based on the power consumption data of the devices, calculating the strength relationship of load fluctuations between devices, the calculation includes:

[0012] Cross-correlation analysis is used to determine whether there is a temporal correlation between the power consumption fluctuations of two devices. The cross-correlation function calculation formula is:

[0013]

[0014] Where x(t) and y(t) represent the power data of device A and device B at time t, respectively. x and y are their means, respectively. τ is the time delay.

[0015] The mutual information or correlation coefficient is used to determine whether the load fluctuations between two devices have nonlinear correlation. The mutual information calculation formula is:

[0016]

[0017] Where p(x,y) is the joint probability distribution of the power data of device A and device B, and p(x) and p(y) are the marginal probability distributions of device A and device B.

[0018] Based on the correlation degree of load fluctuations, the load correlation relationship between devices A and B is determined to determine whether there is a synergistic effect between devices A and B. The comprehensive correlation score formula is:

[0019] S AB =w1·C xy (τ)+w2·I(X;Y)

[0020] Among them, w1 and w2 are weight coefficients used to balance the contribution of cross-correlation and mutual information analysis, C xy (τ) is the cross-correlation, I(X;Y) is the mutual information;

[0021] Generate a load association graph: Based on the strength of load fluctuations between devices, a load association graph is generated. In the graph, each device is a node, and the load association between each pair of devices is an edge. The weight of the edge is assigned according to the strength of the load fluctuation.

[0022] Anomaly detection based on load associations: By monitoring changes in the load association graph, abnormal power usage behavior can be identified, including abnormal correlations between load fluctuations between devices, thereby detecting device failures, energy waste, or abnormal power usage.

[0023] Preferably, the load correlation modeling between devices includes:

[0024] Each electrical device is considered as a node in the graph, and the device's power consumption data is used as the node's attribute information;

[0025] The time series data of the power consumption data of the device includes changes in the power of the device, the on and off status of the device, the device operation time, frequency and the time series relationship between them;

[0026] By calculating the power fluctuation data between devices and conducting cross-correlation analysis of device time series data, load association relationships between devices are constructed. These association relationships are represented as edges in the graph.

[0027] The edge weight between each pair of devices is assigned according to the strength relationship of load fluctuations. The edge weight value reflects the correlation of load fluctuations between devices, and further reflects the mutual influence and correlation strength of load fluctuations between devices.

[0028] Preferably, the load correlation modeling between devices further includes:

[0029] Based on the power data between devices, a spatiotemporal model of device load association is constructed, further considering the geographical distribution and time characteristics of the devices to capture the interactions between devices;

[0030] Use time window sliding technology to segment data to more efficiently analyze the load change trends of equipment in different time periods and improve the accuracy of load correlation modeling.

[0031] Preferably, the calculation of the load fluctuation strength includes: cross-correlation analysis: analyzing the time dependency of the load fluctuations between device A and device B by calculating the temporal correlation of the power fluctuations between devices. The specific steps are as follows:

[0032] Collect power data of device A and device B, where the power data is recorded in a time series format, reflecting the power consumption of the devices within a specific time period;

[0033] Use the cross-correlation function to calculate the power time series of device A and device B to measure the similarity between the two time series at different time delays;

[0034] If the correlation value under a certain time delay is significant, it indicates that there is a significant temporal correlation between the load fluctuations between devices, and further analysis is needed to determine whether there is a synergistic effect.

[0035] Preferably, the calculation of load fluctuation strength further includes:

[0036] Mutual Information Analysis: By calculating mutual information, we can measure the nonlinear relationship between load fluctuations of devices and reveal the potential synergy between devices. The steps are as follows:

[0037] Obtain the power time series data of device A and device B, and ensure that there is sufficient overlap between the time series;

[0038] The power data is discretized and the mutual information is calculated using the joint probability distribution and marginal probability distribution to reveal the nonlinear dependence between device A and device B.

[0039] The synergistic effect between devices is identified by the mutual information value, especially in the case of complex load fluctuations, as the mutual information can capture the nonlinear influence between devices.

[0040] Preferably, the calculation of load fluctuation strength further includes:

[0041] Correlation determination: Combine the results of cross-correlation analysis and mutual information analysis to comprehensively evaluate the strength of the load fluctuation relationship between devices. The specific steps are as follows:

[0042] The results of cross-correlation analysis and mutual information analysis are combined to form a comprehensive load correlation score using weighted calculation;

[0043] Based on the comprehensive score, the strength of the load fluctuation relationship between devices is determined. A high score indicates a strong correlation, and a low score indicates a weak correlation.

[0044] Based on the comprehensive score and the predetermined threshold, it is determined whether there is a significant load fluctuation correlation between the devices, and then the potential collaborative load effect is identified.

[0045] Preferably, generating a load association relationship diagram includes:

[0046] Based on the load fluctuation strength relationship between devices, a weighted graph algorithm is used to generate a device load correlation graph;

[0047] In the graph, each device is a node, and the load association between each pair of devices is an edge in the graph. The weight of the edge is assigned according to the intensity of the load fluctuation.

[0048] In the load association diagram, the dynamic adjustment of edge weights can reflect the changes in load fluctuations between devices in real time, ensuring that the load association relationships of the devices in the diagram can adapt to the dynamically changing power consumption environment.

[0049] Preferably, the generation of the load association relationship diagram further includes:

[0050] Based on the constructed preliminary load association graph, graph theory algorithms are applied to further optimize the graph structure to identify key association nodes between devices and prioritize device groups.

[0051] By analyzing the relationship between load fluctuations between devices, we can determine the importance weights of the devices, group the devices according to these weights, and optimize energy scheduling and device management strategies to improve overall power efficiency.

[0052] In the load correlation diagram, graph analysis tools are used to analyze the changing trends of load correlations between devices, and the device scheduling and management strategies are adjusted according to the load fluctuation patterns of the devices, thereby improving the efficiency of energy management and optimizing fault detection and early warning capabilities.

[0053] Preferably, the abnormality detection based on the load association relationship includes:

[0054] Monitor changes in load correlation diagrams, determine abnormal load fluctuations between devices, and identify abnormal power usage behavior;

[0055] The abnormal behavior includes an abnormal correlation of load fluctuations between device A and device B, indicating device failure, device overload, energy waste, and abnormal power usage.

[0056] Preferably, the anomaly detection further includes:

[0057] Based on the historical data of the load correlation diagram, the threshold of load fluctuation between devices is dynamically adjusted. By comparing the deviation between the current load fluctuation and the historical fluctuation, it is determined whether it is an abnormal fluctuation.

[0058] By training a deep neural network model and combining it with the characteristics of load fluctuations, we can automatically identify abnormal patterns of load fluctuations between devices and improve the accuracy and robustness of anomaly detection.

[0059] The present invention has the following beneficial effects:

[0060] 1. In the present invention, by introducing load correlation modeling and its calculation method, the energy efficiency coordination between devices in intelligent power management is significantly improved. By combining cross-correlation analysis with mutual information analysis, the temporal correlation between devices can be captured, and the potential synergistic effect of nonlinear load fluctuations can be revealed. By constructing a load correlation relationship graph between devices and optimizing the load correlation relationship in combination with graph theory algorithms, dynamic analysis and optimization of multi-device synergy effects are achieved. By real-time monitoring of load fluctuations and correlations between devices, the collaborative load fluctuations between devices can be accurately captured. By introducing the graph convolutional network (GCN) graph theory optimization algorithm, not only the key correlation nodes between devices can be identified, but also the scheduling priority of the device can be dynamically adjusted according to the intensity and frequency of the device load fluctuations. And by timely identifying abnormal collaborative load fluctuations.

[0061] 2. In this invention, by collecting electricity consumption data from household devices in real time, combined with load correlation modeling and anomaly detection between devices, it can comprehensively and real-timely reflect device load fluctuations. It considers the impact of load fluctuations when multiple devices operate in collaboration, and optimizes scheduling based on this correlation. It can monitor load fluctuations between devices in real time and dynamically adjust energy management strategies based on the changing trends of load correlations. In addition, the anomaly detection mechanism, by dynamically adjusting the detection threshold by introducing historical data and combining it with a deep neural network (DNN) model, effectively improves the accuracy and robustness of abnormal fluctuation detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 This is a flow chart of a smart electricity usage behavior analysis and management method proposed by the present invention. DETAILED DESCRIPTION

[0063] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0064] This implementation proposes a smart electricity usage analysis and management method. Through data collection, modeling, analysis, anomaly detection, and intelligent scheduling, it enables load fluctuation analysis, fault diagnosis, and energy optimization for electrical equipment. The following details the modeling and analysis process.

[0065] like Figure 1 As shown, the present invention proposes a smart electricity consumption behavior analysis and management method, including the following steps:

[0066] Collect device information: Use IoT devices or sensors to collect real-time electricity consumption data of multiple electrical devices in the home. The electricity consumption data includes the power, operating time, voltage, current, and switch status of the device, which serves as the basic data of each device;

[0067] Modeling inter-device load correlation: Each device is treated as a node, and the load correlation relationships between devices are used as edges to build a device load correlation network. The load fluctuations of devices are reflected through time series data, which includes changes in device power and the start and stop times of devices.

[0068] Calculate the strength of load fluctuations: Based on the power consumption data of the devices, calculate the strength relationship of load fluctuations between devices. The calculation includes:

[0069] Cross-correlation analysis is used to determine whether there is a temporal correlation between the power consumption fluctuations of two devices. The cross-correlation function calculation formula is:

[0070]

[0071] Where x(t) and y(t) represent the power data of device A and device B at time t, respectively. and are their means respectively, τ is the time delay;

[0072] The mutual information or correlation coefficient is used to determine whether the load fluctuations between two devices have nonlinear correlation. The mutual information calculation formula is:

[0073]

[0074] Where p(x,y) is the joint probability distribution of the power data of device A and device B, and p(x) and p(y) are the marginal probability distributions of device A and device B.

[0075] Based on the correlation degree of load fluctuations, the load correlation relationship between devices A and B is determined to determine whether there is a synergistic effect between devices A and B. The comprehensive correlation score formula is:

[0076] S AB =w1·C xy (τ)+w2·I(X;Y)

[0077] Among them, w1 and w2 are weight coefficients used to balance the contribution of cross-correlation and mutual information analysis, C xy (τ) is the cross-correlation, I(X;Y) is the mutual information;

[0078] Generate a load association graph: Based on the strength of load fluctuations between devices, a load association graph is generated. In the graph, each device is a node, and the load association between each pair of devices is an edge. The weight of the edge is assigned based on the strength of the load fluctuation.

[0079] Anomaly detection based on load correlation: By monitoring changes in the load correlation graph, abnormal power usage behavior can be identified, including abnormal correlations between load fluctuations between devices, thereby detecting device failures, energy waste, or abnormal power usage.

[0080] 1. Data collection and preprocessing:

[0081] In this method, the data input is the real-time electricity consumption data collected from multiple home appliances through IoT devices and sensors. The specific steps are as follows:

[0082] Data collection: Use sensor devices installed in the home (such as smart sockets, power meters, smart meters, etc.) to regularly or in real time monitor basic information such as power, current, voltage, switch status, etc. of multiple electrical devices.

[0083] Power (W): reflects the working intensity of the device; Current (A): reflects the power consumption of the device; Voltage (V): reflects the voltage requirement of the device; Switch status: reflects whether the device is on or off.

[0084] Data cleaning and preprocessing: Data denoising and supplementation: Use data cleaning algorithms to remove noise that occurs during the collection process, fill in missing values, and ensure data integrity.

[0085] Standardization and normalization: In order to ensure that the data of different electrical equipment are in the same dimension, the collected power, current, voltage and other values ​​need to be standardized.

[0086] Time alignment: Since the collection time points of different devices may differ, the data needs to be time-aligned to ensure that data within the same time period can be effectively compared and analyzed.

[0087] 2. Modeling the load correlation between devices: Analyze the load fluctuation relationship between devices. The specific steps are as follows:

[0088] Construction of load association network between devices:

[0089] Each device is regarded as a node in the graph, and the device's power consumption data (such as power, current, etc.) is regarded as the attributes of the node.

[0090] The load fluctuation relationship between devices is represented by the edges in the graph. The strength of the load fluctuation relationship between each pair of devices determines the weight of this edge.

[0091] The load fluctuation of the equipment is reflected through time series data, which includes the power changes of the equipment, the timing information of opening and closing, the frequency of equipment use, etc.

[0092] Correlation analysis: Through cross-correlation analysis and mutual information analysis, the load fluctuation relationship between devices is revealed.

[0093] The spatiotemporal model considers each device as a node, and the load correlation between devices is dynamically weighted based on the following factors:

[0094] Geographic distance: The spatial distance between devices affects the degree of mutual influence of their load fluctuations. Devices with closer distances may have stronger load correlation.

[0095] Time period relationship: The load fluctuation of equipment within the same time period has time period characteristics. By modeling the time period characteristics, the model can capture the periodic law of equipment load fluctuation.

[0096] Through spatiotemporal modeling, we can more accurately describe the spatiotemporal correlation between device loads and identify complex interaction patterns across time and geographical regions.

[0097] Cross-correlation analysis:

[0098] The cross-correlation function is used to calculate the temporal correlation between the power data series of two devices. The cross-correlation reflects the temporal synchronization and lag of power fluctuations between devices.

[0099] For example, assuming that the power data of device A is x(t) and the power data of device B is y(t), the cross-correlation can be calculated using the following formula:

[0100]

[0101] Where x(t) and y(t) represent the power data of device A and device B at time t, respectively. and are their means respectively, τ is the time delay;

[0102] Mutual Information Analysis: This measures the nonlinear dependency between device A and device B. It can discover potential correlations that cannot be revealed by cross-correlations.

[0103] Assuming that the power data of device A and device B are x and y respectively, the mutual information I(x;y) can be calculated using the joint probability distribution and marginal probability distribution:

[0104]

[0105] Where p(x,y) is the joint probability distribution of the power data of device A and device B, and p(x) and p(y) are the marginal probability distributions of device A and device B.

[0106] Determination of load correlation strength:

[0107] Based on the results of cross-correlation analysis and mutual information calculation, the strength relationship of load fluctuations between devices is comprehensively evaluated.

[0108] If the cross-correlation or mutual information value is high, it means that there is a strong correlation between the load fluctuations of the two devices and there may be a synergistic effect.

[0109] Application of Sliding Time Window Technology: To more efficiently analyze device load trends over different time periods, we use sliding time window technology to segment data. This technology dynamically segments data and gradually updates the load trends within each time window, improving the accuracy of load correlation modeling. Data within each time window is analyzed based on specific time intervals to identify load change patterns for each device and their interactions.

[0110] 3. Generation of load association diagram:

[0111] Based on the results of load correlation analysis, a load correlation diagram between devices is generated. The specific steps are as follows:

[0112] Graph construction: The load fluctuation relationship between devices is represented by the edges in the graph. The devices themselves are nodes, and the edge weights represent the strength of the load fluctuation. The edge weights can be calculated using the following formula:

[0113] S AB =w1·C xy (τ)+w2·I(X;Y)

[0114] Among them, S AB is the load correlation strength between device A and device B, w1 and w2 are weight coefficients used to balance the contribution of cross-correlation and mutual information analysis, C xy (τ) is the cross-correlation, I(X;Y) is the mutual information;

[0115] Dynamic graph updates: The load association graph is a dynamic graph. As device power usage data is updated in real time, the graph structure and edge weights change. To monitor the status of electrical devices in real time, the edge weights in the graph need to be dynamically adjusted to reflect changes in load fluctuations.

[0116] Graph structure optimization: Optimize the load association graph constructed using graph theory algorithms. Specific optimization methods include:

[0117] Minimum Spanning Tree (MST) algorithm: used to select key nodes from all device nodes, remove redundant nodes and edges, and ensure the shortest and most direct connections between devices with strong load fluctuations.

[0118] Maximum flow algorithm: Optimizes the power flow path between devices to ensure efficient energy transmission and avoid unnecessary power loss.

[0119] Shortest path algorithm: Determine the shortest path between devices with load fluctuations and optimize load scheduling strategies.

[0120] Graph Convolutional Network (GCN) optimization process:

[0121] In the graph optimization part, the load association graph after combining the spatiotemporal model will be optimized using a graph convolutional network (GCN). GCN learns the neighborhood information of device nodes and optimizes the characteristics of each node, thereby improving the accuracy of the load association model. The specific optimization process is as follows:

[0122]

[0123] in, represents the device node characteristics of the lth layer, N(i) is the neighbor of node i, deg(i) is the degree of node i, W (l) is the weight matrix of layer l, and σ is the activation function. Through optimization, the representation capability of the device load association graph is improved, thereby more accurately reflecting the load fluctuation relationship between devices and enhancing the model's predictive ability.

[0124] Identifying key nodes: By analyzing the graph structure, we can identify key nodes, which are devices with high load fluctuations. Key nodes are typically "central" devices that affect the load of other devices.

[0125] 4. Anomaly detection based on load correlation graph:

[0126] By monitoring the load association graph, abnormal power usage behavior can be identified in a timely manner. The anomaly detection process includes the following steps:

[0127] Monitor changes in load fluctuations: By tracking changes in edge weights in the load association graph in real time, we can identify abnormal changes in load fluctuations between devices. For example, a sudden change in the load fluctuation pattern of a device may indicate a device failure.

[0128] Identification of abnormal behavior:

[0129] When the load fluctuation between two devices no longer conforms to the previous correlation pattern, a threshold is set to determine whether the change is abnormal.

[0130] Abnormal behavior may include device failure (such as large fluctuations in power), device overload (such as power exceeding the maximum load), or abnormal power usage (such as current flowing through the device when it is turned off).

[0131] Output abnormality alarm: When an abnormality is detected, an alarm can be output to inform the user that there is a malfunction in the equipment, abnormal power usage or potential energy waste.

[0132] Use historical data to dynamically adjust the threshold for load fluctuations between devices. Based on the statistical characteristics of historical data (such as mean and standard deviation), dynamic threshold ranges are set. The deviation between current load fluctuation data and historical fluctuation data is compared in real time to determine whether the fluctuation is abnormal. Dynamic threshold adjustment improves the accuracy of anomaly detection and avoids false positives and missed negatives.

[0133] A deep neural network (DNN) model is introduced. This model automatically identifies abnormal load fluctuation patterns between devices by training historical load fluctuation data and combining it with the load fluctuation characteristics between devices.

[0134] 5. Energy management and optimization:

[0135] Based on the load association diagram, energy scheduling and equipment management can be further optimized:

[0136] Equipment scheduling: By analyzing the load correlation between devices, priority is given to scheduling those devices with smaller load fluctuations to avoid energy waste caused by high-load devices working at the same time.

[0137] Optimize device group management: Based on the load correlation strength, devices can be divided into different priority groups, and those with strong load correlation are scheduled first to achieve energy saving and load balancing.

[0138] Intelligent control: Combined with the prediction of load fluctuations and the results of anomaly detection, the operation of equipment is intelligently controlled to optimize energy consumption and extend the service life of equipment.

[0139] In a specific example, a user has installed multiple smart home devices at home, such as an air conditioner, refrigerator, washing machine, TV, and water heater. All devices monitor their power consumption in real time via smart sockets and energy meters. The user's home has a total power capacity of 10kW, and peak daily electricity consumption is expected to occur in the afternoon (12:00-14:00) in summer and in the evening (18:00-20:00) in winter. During these peak hours, the air conditioner, water heater, and electric heating equipment are all running simultaneously, often leading to power shortages and even equipment overloads and failures.

[0140] 1. Data collection and real-time monitoring:

[0141] Real-time data collection is performed through smart sockets and electricity meters. Each device uploads power, current, voltage and other data in real time through sensors. The following is an example of electricity consumption data collection for a user's home appliances:

[0142] Air conditioner: Power consumption is 1200W, current is 5.5A, voltage is 220V, and the collection frequency is once per second.

[0143] Refrigerator: Power consumption is 200W, current is 0.9A, voltage is 220V, and the collection frequency is once every 10 seconds.

[0144] TV: Power consumption is 150W, current is 0.7A, voltage is 220V, and acquisition frequency is once per second.

[0145] Washing machine: Power consumption is 1500W, current is 6.8A, voltage is 220V, and the collection frequency is once every 5 seconds.

[0146] Water heater: Power consumption is 3000W, current is 13.6A, voltage is 220V, and the collection frequency is once every 5 seconds.

[0147] By collecting data from these devices, the energy consumption of each appliance can be tracked in real time to ensure that electricity is reasonably distributed during peak hours.

[0148] 2. Load correlation analysis between devices:

[0149] Based on the power consumption data between devices, analyze the load fluctuation relationship of each device. Assume the following data analysis results:

[0150] Air conditioners and water heaters: During the summer peak hours (12:00 PM to 2:00 PM), the load fluctuations of air conditioners and water heaters show a significant correlation. The air conditioner's peak power is 1200W, while the water heater's peak power during the same period is 3000W. A strong cross-correlation of 0.85 was found between these load fluctuations, indicating a strong correlation.

[0151] Refrigerator and TV: There is no obvious correlation between the load fluctuations of these two devices, and the cross-correlation is 0.2, so the load relationship between them is considered weak.

[0152] Example of equipment load fluctuation relationship:

[0153] Air conditioners and water heaters:

[0154] Cross-correlation: 0.85, indicating that the load fluctuations of air conditioners and water heaters are very strongly correlated. This means that during peak hours, the power consumption of air conditioners and water heaters often fluctuates synchronously, so their load management requires special attention.

[0155] Mutual information: 0.45, indicating a high degree of information sharing between the two. When the load of one device fluctuates, the power usage of the other device may change significantly.

[0156] Air conditioner and refrigerator:

[0157] A cross-correlation of 0.2 indicates that the load fluctuations of air conditioners and refrigerators are weakly correlated. Although they are common household appliances, their load fluctuations are not always synchronized, so some flexibility can be accommodated in scheduling.

[0158] Mutual information: 0.1, indicating that their electricity usage behaviors do not have a strong mutual impact.

[0159] Washing machine and TV:

[0160] The cross-correlation is 0.1, indicating that the load fluctuations of the washing machine and the TV are almost unrelated. Their operating modes are unlikely to affect each other, so their scheduling can be performed independently.

[0161] Mutual information: 0.05, indicating that the information correlation between them is very weak and can be almost ignored.

[0162] Based on the above correlation analysis, it is possible to intelligently determine which devices are high-load devices and which devices need to be staggered to avoid overload.

[0163] 3. Construction and dynamic update of load association diagram:

[0164] A load association graph is constructed using a graph algorithm to update the load relationship between devices in real time. The weight of the edge connecting each device node represents the intensity of the load fluctuation. The graph is updated every 5 seconds. An example is as follows:

[0165] The edge weight of the air conditioner and water heater is 0.85, indicating that the load fluctuations between them are highly correlated.

[0166] The edge weight between the air conditioner and refrigerator is 0.2, indicating that their load fluctuations are almost unrelated.

[0167] Every time new load data is collected, the graph structure is updated and the edge weights between devices are adjusted. For example, when an air conditioner is running at high speed, the edge weights in the load relationship graph are adjusted to optimize power scheduling.

[0168] 4. Intelligent scheduling and load optimization:

[0169] Based on the load association diagram and the power requirements of the equipment, load optimization scheduling is performed. The following is an example of a scheduling strategy:

[0170] Priority scheduling: During the summer peak period of 12:00-14:00, the load fluctuations of air conditioners and water heaters are large. The air conditioners are scheduled to run from 9:00-11:00 in the morning, and the water heaters are scheduled to run from 3:00-5:00 in the afternoon to avoid overlap between the two.

[0171] Load balancing: When household devices are most heavily loaded (e.g., between 6:00 PM and 8:00 PM), the system adjusts the order of device operation based on priority and load fluctuations. For example, when a user turns on the TV, the system prioritizes shutting down a high-power washing machine to avoid simultaneous operation and potentially overloading the system.

[0172] Time period optimization: Based on historical data analysis, we know that users usually use the washing machine between 9:00 and 10:00 in the evening, so the washing machine will be automatically scheduled to run during this period.

[0173] 5. Abnormal detection and fault warning:

[0174] Monitor device load fluctuations in real time and set thresholds based on historical data to detect abnormal power usage. The following are the specific operations for data monitoring and anomaly detection:

[0175] Air conditioner overload detection: If the air conditioner's power suddenly rises to 2000W (exceeding the normal 1200W) and remains at high power for 5 minutes, the system will detect a possible air conditioner failure (such as compressor overload) and send an alarm notification to the user.

[0176] Abnormal water heater startup: The system detected that the water heater was still drawing 0.5A of current even when the user had not turned it on. This state lasted for more than an hour. This abnormal power usage was detected and the user was warned and advised to check the water heater's status.

[0177] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A smart electricity consumption behavior analysis and management method, characterized in that: The following steps are involved: Collecting device information: Collecting power consumption data of multiple electrical devices in the home in real time through IoT devices or sensors. The power consumption data includes the power, operating time, voltage, current, and switch status of the device as the basic data of each device; Modeling of load correlation between devices: Each device is taken as a node, and the load correlation between devices is taken as an edge to build a device load correlation network, in which the load fluctuation of the device is reflected by time series data, which includes the change of device power and the start and stop time between devices; Calculating the strength of load fluctuations: Based on the power consumption data of the devices, calculating the strength relationship of load fluctuations between devices, the calculation includes: Through cross-correlation analysis, it is determined whether there is a temporal correlation between the power consumption fluctuations of the two devices; the cross-correlation function calculation formula is: Among them, x(t) and y(t) represent the power data of device A and device B at time t respectively. and are their means respectively, τ is the time delay; Through the mutual information or correlation coefficient, it is judged whether the load fluctuation between two devices has nonlinear correlation; the mutual information calculation formula is: Where p(x,y) is the joint probability distribution of power data of device A and device B, and p(x) and p(y) are the marginal probability distributions of device A and device B. According to the correlation degree of load fluctuation, the load correlation relationship between device A and device B is determined to determine whether there is a synergistic effect between device A and device B; the comprehensive correlation score formula is: S AB =w1·C xy (τ)+w2·I(X;Y) Among them, w1 and w2 are weight coefficients used to balance the contribution of cross-correlation and mutual information analysis, C xy (τ) is the cross-correlation, I(X;Y) is the mutual information; Generate a load association relationship graph: Generate a load association relationship graph between devices according to the strength relationship of load fluctuations between devices. In the graph, each device is a node, and the load association between each pair of devices is an edge. The weight of the edge is assigned according to the strength of the load fluctuation. Anomaly detection based on load association: By monitoring changes in the load association graph, abnormal power usage behavior can be identified, including abnormal associations of load fluctuations between devices, thereby detecting device failures, energy waste, or abnormal power usage.

2. According to claim 1, a smart electricity consumption behavior analysis and management method is characterized in that: The load correlation modeling between devices includes: Each electrical device is regarded as a node in the graph, and the power consumption data of the device is used as the attribute information of the node; The time series data of the power consumption data of the device includes the change of the power of the device, the on and off status of the device, the operating time and frequency of the device, and the time series relationship between them; By calculating the power fluctuation data between devices and based on the cross-correlation analysis of the device time series data, the load association relationship between the devices is constructed, and the association relationship is represented as an edge in the graph; The edge weight between each pair of devices is assigned according to the strength relationship of load fluctuations. The edge weight value reflects the correlation of load fluctuations between devices, and further reflects the mutual influence and correlation strength of load fluctuations between devices.

3. According to claim 1, a smart electricity consumption behavior analysis and management method is characterized in that: The load correlation modeling between devices also includes: Based on the power data between devices, a spatiotemporal model of device load association is constructed, further considering the geographical distribution and time characteristics of the devices to capture the interactions between devices; The time window sliding technology is used to segment the data so as to more efficiently analyze the load change trend of the equipment in different time periods and improve the accuracy of load correlation modeling.

4. The method for analyzing and managing smart electricity consumption behavior according to claim 1, characterized in that: The calculation of load fluctuation strength includes: cross-correlation analysis: by calculating the timing correlation of power fluctuations between devices, analyzing the time dependence of load fluctuations between device A and device B, the specific steps are as follows: Collect power data of device A and device B, where the power data is recorded in a time series form, reflecting the power consumption of the devices in a specific time period; The power time series of device A and device B are calculated using the cross-correlation function to measure the similarity of the two time series at different time delays; If the correlation value under a certain time delay is significant, it indicates that there is a significant timing correlation between the load fluctuations between devices, and further analysis is performed to determine whether there is a synergistic effect.

5. The method for analyzing and managing smart electricity consumption behavior according to claim 1, characterized in that: The calculation of load fluctuation strength also includes: Mutual information analysis: By calculating the mutual information, the nonlinear relationship between load fluctuations between devices is measured and the potential synergy between devices is revealed. The steps are as follows: Obtain the power time series data of device A and device B, and ensure that there is sufficient overlap between the time series; The power data is discretized, and the mutual information is calculated through joint probability distribution and marginal probability distribution to reveal the nonlinear dependence between device A and device B. The mutual information value is used to identify the synergistic effect between devices, especially in the case of complex load fluctuations, as the mutual information value can capture the nonlinear impact between devices.

6. The method for analyzing and managing smart electricity consumption behavior according to claim 1, characterized in that: The calculation of load fluctuation strength also includes: Correlation determination: Combine the results of cross-correlation analysis and mutual information analysis to comprehensively evaluate the strength of load fluctuations between devices. The specific steps are as follows: The results of the cross-correlation analysis and the mutual information analysis are combined to form a comprehensive load correlation score using weighted calculation; Based on the comprehensive score, the strength of the load fluctuation relationship between devices is determined, where a high score indicates a strong correlation and a low score indicates a weak correlation; Based on the comprehensive score and the predetermined threshold, it is determined whether there is a significant load fluctuation correlation between the devices, thereby identifying potential collaborative load effects.

7. The method for analyzing and managing smart electricity consumption behavior according to claim 1, characterized in that: The generating of the load association relationship diagram comprises: Based on the relationship between the load fluctuation strengths of the devices, a weighted graph algorithm is used to generate a device load association graph; In the graph, each device is a node, the load association between each pair of devices is an edge in the graph, and the weight of the edge is assigned according to the load fluctuation intensity; In the load association diagram, the changes in load fluctuations between devices are reflected in real time through dynamic adjustment of edge weights, ensuring that the load association relationship of the devices in the diagram can adapt to the dynamically changing power consumption environment.

8. The method for analyzing and managing smart electricity consumption behavior according to claim 1, characterized in that: The generation of the load association relationship diagram further includes: Based on the constructed preliminary load association graph, graph theory algorithms are applied to further optimize the graph structure to identify key association nodes between devices and prioritize device groups; By analyzing the strength relationship of load fluctuations between devices, the importance weights of devices are determined, and devices are grouped according to these weights to optimize energy scheduling and device management strategies to improve overall power efficiency; In the load association diagram, graph analysis tools are used to analyze the changing trend of load associations between devices, and the scheduling and management strategies of the devices are adjusted according to the load fluctuation patterns of the devices, thereby improving the efficiency of energy management and optimizing fault detection and early warning capabilities.

9. The method for analyzing and managing smart electricity consumption behavior according to claim 1, characterized in that: The abnormality detection based on the load association relationship includes: Monitor changes in the load association diagram, determine abnormal changes in load fluctuations between devices, and identify abnormal power consumption behavior; The abnormal behavior includes an abnormal correlation of load fluctuations between device A and device B, indicating device failure, device overload, energy waste, and abnormal power usage.

10. The method for analyzing and managing smart electricity consumption behavior according to claim 1, characterized in that: The anomaly detection further comprises: Based on the historical data of the load correlation diagram, the threshold of load fluctuation between devices is dynamically adjusted. By comparing the deviation between the current load fluctuation and the historical fluctuation, it is determined whether it is an abnormal fluctuation. By training a deep neural network model and combining the characteristics of load fluctuations, abnormal patterns of load fluctuations between devices can be automatically identified, thereby improving the accuracy and robustness of anomaly detection.

Images