Non-intrusive load monitoring is a method that disaggregates the overall energy consumption of a building to estimate the electric power usage and operating status of each appliance individually.Prior studies have mos...Non-intrusive load monitoring is a method that disaggregates the overall energy consumption of a building to estimate the electric power usage and operating status of each appliance individually.Prior studies have mostly concentrated on the identification of high-power appliances like HVAC systems while overlooking the existence of low-power appliances.Low-power consumer appliances have comparable power consumption patterns,which can complicate the detection task and can be mistaken as noise.This research tackles the problem of classification of low-power appliances and uses turn-on current transients to extract novel features and develop unique appliance signatures.A hybrid feature extraction method based on mono-fractal and multi-fractal analysis is proposed for identifying low-power appliances.Fractal dimension,Hurst exponent,multifractal spectrum and the Hölder exponents of switching current transient signals are extracted to develop various‘turn-on’appliance signatures for classification.Four classifiers,i.e.,deep neural network,support vector machine,decision trees,and K-nearest neighbours have been optimized using Bayesian optimization and trained using the extracted features.The simulated results showed that the proposed method consistently outperforms state-of-the-art feature extraction methods across all optimized classifiers,achieving an accuracy of up to 96%in classifying low-power appliances.展开更多
The most generally used technique of load power monitoring is non-intrusive load monitoring, which requires only one device to be mounted on the bus to monitor the current parameters and the working state of various t...The most generally used technique of load power monitoring is non-intrusive load monitoring, which requires only one device to be mounted on the bus to monitor the current parameters and the working state of various types of appliances within the total load. It is required to investigate a cost-effective non-intrusive load monitoring and identification system that can perform a range of duties such as fault monitoring, energy monitoring, and fault analysis without requiring a significant number of sensing components. Measurement of electrical values of commonly used home appliances during stable operation, followed by feature extraction and electrical feature analysis to identify appliance types, can help residential users understand appliance habits and consciously reduce consumption and losses while enabling fault detection. The STM32F103RCT6 core control chip and the SUI-101 energy metering module are used in this system to monitor and evaluate load characteristics using the Modbus-RTU communication protocol. The active and reactive power of the load is measured and recorded in the learning mode;in the analysis and identification mode, the electrical parameters of the current appliance, such as current, voltage, active power, reactive power, frequency, and power factor, can be displayed in real-time, and the corresponding load can be deduced using binary simulation and the Euclidean distance matching method. The device has a short learning time and good identification accuracy for typical household appliances, according to the system test, and can satisfy the analysis and recognition of electrical appliances in a regular domestic setting. The current device design combines the advantage of cheap cost, low power consumption, and portability, making it a viable alternative for domestic appliance identification and monitoring.展开更多
文摘Non-intrusive load monitoring is a method that disaggregates the overall energy consumption of a building to estimate the electric power usage and operating status of each appliance individually.Prior studies have mostly concentrated on the identification of high-power appliances like HVAC systems while overlooking the existence of low-power appliances.Low-power consumer appliances have comparable power consumption patterns,which can complicate the detection task and can be mistaken as noise.This research tackles the problem of classification of low-power appliances and uses turn-on current transients to extract novel features and develop unique appliance signatures.A hybrid feature extraction method based on mono-fractal and multi-fractal analysis is proposed for identifying low-power appliances.Fractal dimension,Hurst exponent,multifractal spectrum and the Hölder exponents of switching current transient signals are extracted to develop various‘turn-on’appliance signatures for classification.Four classifiers,i.e.,deep neural network,support vector machine,decision trees,and K-nearest neighbours have been optimized using Bayesian optimization and trained using the extracted features.The simulated results showed that the proposed method consistently outperforms state-of-the-art feature extraction methods across all optimized classifiers,achieving an accuracy of up to 96%in classifying low-power appliances.
文摘The most generally used technique of load power monitoring is non-intrusive load monitoring, which requires only one device to be mounted on the bus to monitor the current parameters and the working state of various types of appliances within the total load. It is required to investigate a cost-effective non-intrusive load monitoring and identification system that can perform a range of duties such as fault monitoring, energy monitoring, and fault analysis without requiring a significant number of sensing components. Measurement of electrical values of commonly used home appliances during stable operation, followed by feature extraction and electrical feature analysis to identify appliance types, can help residential users understand appliance habits and consciously reduce consumption and losses while enabling fault detection. The STM32F103RCT6 core control chip and the SUI-101 energy metering module are used in this system to monitor and evaluate load characteristics using the Modbus-RTU communication protocol. The active and reactive power of the load is measured and recorded in the learning mode;in the analysis and identification mode, the electrical parameters of the current appliance, such as current, voltage, active power, reactive power, frequency, and power factor, can be displayed in real-time, and the corresponding load can be deduced using binary simulation and the Euclidean distance matching method. The device has a short learning time and good identification accuracy for typical household appliances, according to the system test, and can satisfy the analysis and recognition of electrical appliances in a regular domestic setting. The current device design combines the advantage of cheap cost, low power consumption, and portability, making it a viable alternative for domestic appliance identification and monitoring.
