Distributed Energy Resources Electric Profile Identification in Low Voltage Networks Using Supervised Machine Learning Techniques

• Published in: IEEE access Vol. 11; pp. 19469 - 19486
• Main Authors: Jaramillo, Andres F. Moreno, Lopez-Lorente, Javier, Laverty, David M., Brogan, Paul V., Velasquez, Santiago H. Hoyos, Martinez-Del-Rincon, Jesus, Foley, Aoife M.
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Distributed energy resources (DER); Distributed generation; Distribution networks; Electric vehicles; Electrical networks; Energy resources; Energy sources; Load modeling; Load monitoring; Low voltage; low voltage networks distribution networks (LVN); Machine learning; Monitoring; Multilayer perceptrons; non-intrusive load monitoring (NILM); Photovoltaic cells; random forest; Random forests; Reactive power; Resistance heating; Supervised learning; supervised machine learning; Transformers
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2023.3247977

Increasing integration of distributed energy resources (DER) in the electrical network has led distribution network operators to unprecedented challenges. This issue is compounded by the lack of monitoring infrastructure on the low voltage (LV) side of distribution networks at residential and utility sides. Non-intrusive load monitoring (NILM) methods provide an opportunity to add value to conventional electric measurements and to increase the observability of LV networks for the implementation of active management network techniques and intelligent control of DER. This work proposes a novel implementation of NILM methods for the identification of DER electrical signatures from aggregated measurements taken at the LV side of a distribution transformer. The implementation evaluates three machine learning algorithms such as k Nearest Neighbours (kNN), random forest and a multilayer perceptron under 100 scenarios of DER integration. A year of minutely reported values of electric current, voltage, active power, and reactive power are used to train and test the proposed model. The <inline-formula> <tex-math notation="LaTeX">F_{1} </tex-math></inline-formula> scores achieved of 73% and 93% for Electrical Vehicles (EV) and rooftop photovoltaic (PV) respectively and processing times below <inline-formula> <tex-math notation="LaTeX">314~\mu \text{s} </tex-math></inline-formula> on an Intel Core i7-8700 machine. These results confirm the relevance of the NILM method based on low frequency electric measurements from the real-time identification of DER.