Comparative Analysis of Neural Network Implementations for NILM Applications

Non-Intrusive Load Monitoring (NILM) comprises a set of techniques that try to disaggregate the energy consumption in a household or building, based on the measurements coming from a single-point smart meter. In this process, a key step is the load identification of the different appliances that may switched on/off during a certain interval under analysis. For that purpose, machine-learning techniques, including deep neural networks, have recently been involved. These classification algorithms may often imply a high computational cost, that might compromise a possible edge-computing implementation on the local smart meters. In this context, this work presents a preliminary comparison between two different real-time implementations of both neural networks, a dense one and a convolutional one, applied to load classification. The implementations are based on a FPGA approach and on a processor. In general terms, preliminary results show that the FPGA solution provides lower latencies than the processor one, at the expense of requiring a higher design effort and a quantization error coming from the fixed-point representation.