Load Demand Disaggregation based on Simple Load Signature and User's Feedback

A detailed and on-line knowledge of the electrical load demand by the users is a critical issue for an effective and responsive deployment of home/building energy management. An approach based on the application of Non Intrusive Appliance Load Monitoring (NIALM) techniques copes with the goal of disaggregating composite loads; but to get a high level of precision, NIALM algorithms need a complete load signature and complex optimization algorithms to find the right combination of single loads that fits the real electrical measurements. On the other hand, it is practically impossible to get the detailed signature of all appliances inside a house/building and sophisticated optimization algorithm are not suitable for on-line applications. To overcome such problems a straightforward NIALM algorithm is proposed, it is based on both a simple load signature, rated active and reactive power and a heuristic disaggregation algorithm. Of course, it is expected that on real applications, this approach cannot reach very high performances; this is the reason why an active involvement of users is considered. The users' feedback aims to: correct the load signatures, reduce the error of disaggregation algorithm and increase the active participation of users in saving energy politics. The NIALM algorithm has been accurately tested numerically using as input load curves generated randomly but under given constraints. In this way, the causes of inefficiency of the proposed approach are quantitatively analyzed both separately and in different combinations. Finally, the increase of the efficiency of the NIALM algorithm due to the application of different feedback actions is evaluated and discussed. (C) 2015 The Authors. Published by Elsevier Ltd.