Non intrusive load monitoring for demand side management

Abstract

In the context of a pilot project, the Lugaggia Innovation Community (LIC), we address the problem of non-intrusive load monitoring for the purpose of demand side management on low voltage grids in presence of distributed power generation (photovoltaic). From the power readings of smart meters, we estimate the photovoltaic production and detect the activation of major loads (heatpumps and domestic water heaters). Experiments, conducted with real data and in silico, show that exploiting meter readings only, we can estimate PV production with MAPE ranging from 4.6% (best case) to 41.9% (worst case). Even with non negligible photovoltaic production estimation errors, the proposed method is capable of detecting the activation of heatpumps and domestic water heaters.

Towards Trustworthy Energy Disaggregation: A Review of Challenges, Methods, and Perspectives for Non-Intrusive Load Monitoring

“…Additionally, NILM is also used for demand-side response scenarios. Demand response provides the possibility of shifting demand away from the peak and, thus, decreasing the corresponding cost of energy [ 9 , 10 ]. In this context, energy disaggregation permits power supplier companies to identify a device with a high consumption rate at a peak hour in a household and send a message to the corresponding users, asking them to postpone their usage to smooth out the current peak in the demand.…”

“…The initial interest of the scientific community to formulate and describe mathematically the NILM problem using machine learning tools—which is the main topic of interest in the review papers that are currently available—has now shifted into a more practical approach towards NILM. Currently, we are in the mature NILM period where there is an attempt for NILM to be applied in real-life application scenarios [ 3 , 4 , 5 , 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 ]. Thus, the complexity of the algorithms, transferability, reliability, practicality, and, in general, trustworthiness are the main issues of interest.…”

Lockdown impacts on residential electricity demand in India: A data-driven and non-intrusive load monitoring study using Gaussian mixture models

“… Klemenjak et al (2020) further stated that as a policy tool NILM can be used to perform diagnostics of household appliances and industrial components that can reduce operational costs. Similarly, Salani et al (2020) in context of Swiss Government funded Lugaggia Innovation Community (LIC) project showed that NILM can be used effectively in distributed energy planning. NILM was also discussed as a critical public health tool through its integration in Ambient Assisted Living (AAL).…”

Review on Deep Neural Networks Applied to Low-Frequency NILM

“…As the term non-intrusive suggests, NILM is motivated by applications where metering of single appliances is necessary, but not feasible with conventional measurement devices, e.g., because of cost considerations or obtrusiveness. Potential NILM applications include, for example, user feedback for energy saving purposes, overseeing activities of daily living for the health assessment of elderly people, or demand management (see, e.g., [3][4][5][6]).…”