TY - JOUR
T1 - Framework for Load Power Consumption in HANs Using Machine Learning and IoT Assistance
AU - Manimuthu, Arunmozhi
AU - Dharshini, Venugopal
PY - 2021/8
Y1 - 2021/8
N2 - In home area networks (HANs), many appliances share a power distribution network and all are potentially the cause and victims of sudden current, voltage, and power spikes. This article proposes a monitoring framework to protect the devices and the network against damage and to optimize power consumption. The method proposed in this article gives way for the use of the smart sensor for a cluster of loads, where the subroutines of every load are logged with separate data preamble size set. Researchers study and evaluate two machine learning (ML) algorithms, support vector machine and k-means clustering, for identifying anomalies and misbehavior, and find that support vector machines seem to be better suited for this application.
AB - In home area networks (HANs), many appliances share a power distribution network and all are potentially the cause and victims of sudden current, voltage, and power spikes. This article proposes a monitoring framework to protect the devices and the network against damage and to optimize power consumption. The method proposed in this article gives way for the use of the smart sensor for a cluster of loads, where the subroutines of every load are logged with separate data preamble size set. Researchers study and evaluate two machine learning (ML) algorithms, support vector machine and k-means clustering, for identifying anomalies and misbehavior, and find that support vector machines seem to be better suited for this application.
KW - Embedded systems
KW - Energy
KW - Gateway
KW - IoT
KW - Machine Learning
KW - Smart grid
UR - http://www.scopus.com/inward/record.url?scp=85090431231&partnerID=8YFLogxK
UR - https://ieeexplore.ieee.org/document/9183897
U2 - 10.1109/MDAT.2020.3021029
DO - 10.1109/MDAT.2020.3021029
M3 - Article
SN - 2168-2356
VL - 38
SP - 102
EP - 108
JO - IEEE Design and Test
JF - IEEE Design and Test
IS - 4
ER -