Exploring of Recursive Model-based Non-Intrusive Thermal Load Monitoring for Building Cooling Load

Abstract

Non-Intrusive Load Monitoring (NILM), which provides sufficient load information from the energy consumption of the entire building, has become crucial in improving the operation of energy systems. Although it can decompose overall energy consumption into individual electrical sub-loads, it struggles to identify such thermal-driven sub-loads as occupants. This paper explores and proposes a Non-Intrusive Thermal Load Monitoring (NITLM) with recursive models and input data selection to accurately disaggregate the overall thermal load into sub-loads, focusing on occupant thermal load. In experiments, we generated a thermal load dataset derived from a whole building energy simulation and compared the accuracy of the monitoring results with the generated reference data. Our experimental results show that our designed model reduces MAE by up to 77.0% more than the existing NITLM approach.