Using neural networks for non-intrusive monitoring of industrial electrical loads

The success of demand side energy control in industries, mines and commercial buildings depends on factors like the energy sensitivity and awareness of the organisation as well as an accurate and effective measurement and monitoring of its electrical energy consumption. Demand side energy control also forms an important part in the research programs of many research organisations. Reliable data on energy consumption is therefore imperative for effective research in this field, as well as for the successful implementation of demand side management. Traditional load research instrumentation has involved intrusive techniques that require the installation of sensors on each of the individual components of the total load. A non-intrusive appliance load monitor is proposed in this paper to determine the energy consumption of individual appliances turning on or off or operating under continuously varying load conditions. This monitoring system, which is implemented by network pattern identification technology, is based on detailed analysis of the current and voltage of the total load, as measured at the interface of the power source. The approach has been developed to simplify the collection of energy consumption data by utilities, but also has other applications. It is called nonintrusive to contrast it with previous techniques for gathering appliance data, which require placing sensors on individual appliances, and hence an intrusion onto the energy consumer's properly.<>