Implementing a CNN in FPGA Programmable Logic for NILM Application

Non-Intrusive Load Monitoring (NILM) techniques are gaining popularity in the field of energy savings. Generally implemented through the use of smart meters, the main challenge with these devices is that they operate at very low sampling rates. To address this issue, FPGA-based systems have been proposed to capture instantaneous currents and voltages at higher sampling frequencies in the kHz range. However, the limitation of these architectures lies in the fact that the acquired windows are often transmitted upstream to the cloud for the application of load classification algorithms based on machine learning, relying on high-bandwidth communications available onsite. This work proposes an alternative approach by implementing the classification algorithms in the same acquisition and processing system, by using custom convolutional neural networks on mid-range FPGA devices. Brevitas and FINN frameworks are used for the quantization-aware training, as well as for the generation of a peripheral that may be integrated into any FPGA-based SoC (System-on-Chip) architecture. The proposed approach allows the whole processing involved in NILM techniques to be integrated into a single embedded system. Preliminary experimental results demonstrate the effectiveness of the proposed approach.