Machine learning for smart energy monitoring of home appliances using IoT

• Main Authors: Rashid, R. A., Chin, L., Sarijari, M. A., Sudirman, R., Ide, T.
• Format: Conference or Workshop Item
• Language: English
• Published: 2019
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.utm.my/id/eprint/91305/1/RozehaARashid2019_MachineLearningforSmartEnergy.pdf; http://eprints.utm.my/id/eprint/91305/; http://www.dx.doi.org/10.1109/ICUFN.2019.8806026
• Institution: Universiti Teknologi Malaysia

Inefficient energy use has been a major issue globally. In Malaysia, the statistics reveal that residential energy consumption has been on a steady increase due to the growing population as well as a lack of awareness within households regarding proper energy utilization that causes significant amount of energy wastage. The emergence of Internet-of-Things (IoT) is a consequence and convergence of several key technologies such as real-time analytics, machine learning, sensors and embedded systems. The application of intelligence in IoT, known as Cognitive IoT (CIoT), will enable decision making based on historical data, and automatically train, learn and troubleshoot future issues. This project proposes a smart energy monitoring system for home appliances incorporating CIoT which consists of three parts. Firstly, a Raspberry Pi-based smart plug serving as the gateway, that is able to read current data from individual home appliances, load the trained model from training server and test the verified data using the model. Secondly, Google Colab as the training server will be used to store the training data set and building the Tensorflow-based Long Short-term Memory (LSTM) model. This recurrent neural network model will forecast electricity bill and notify users if abnormal energy consumption of individual home appliances is detected. Thirdly, a dashboard using Matplotlib library where users may monitor the real-time energy consumption. The completed LSTM model demonstrates a high accuracy of more than 80%, where a low mean squared error with train score = 0.1798 and test score = 0.1229 is determined. Furthermore, the R2 test shows a high level of goodness of fit with train score = 0.844 and test score = 0.835.