抄録
A non-intrusive load monitoring system has been developed to ascertain each electrical appliance in a household by disaggregating the total load demand. This system does not need to intrude into a house when metering power consumption of each appliance. Therefore, the system has significant cost advantages and is less troublesome to the customers. This paper describes a non-intrusive load monitoring system which is especially useful when the household has inverter-driven appliances that frequently change their operational state. Conventional non-intrusive load monitoring system cannot treat these inverter-driven appliances easily because of their complicated operation. In the developed system, the load consumption of household appliances is identified by a Neural Network, which perceives the pattern of harmonics flowing out of the house. An air conditioner, a refrigerator, an incandescent lamp, a fluorescent lamp and a television set were used as household appliances for experiments of inference tests. From the experimental result, it was verified that the NN could identify the load consumption of an inverter-driven air conditioner from the pattern of harmonics of the total load. For this reason, the non-intrusive load monitoring system for the household which has several appliances including inverter-driven appliances is viewed as reliable.
