A Forecasting Approach for IoT-Based Energy and Power Quality Monitoring in Buildings

This paper proposes a novel energy consumption and power quality forecasting technique based on the combination of poly-exponential (PE) and random forest (RF). This technique paves away seamlessly integrating the forecast to the Internet-of-things (IoT)-based monitoring system due to its capability of improving computational efficiency. For the experimental setup, the monitoring system in a building supplied the data for forecasting consisting of daily energy consumption and power quality parameters. The developed algorithm for efficient computational forecasting has already considered the space limitation in online real-time monitoring with a minor effect on the model prediction error (less than 0.3% in our experimental setup). The algorithm can alert the user once an indication of energy waste (more than the determined boundary) or the actual voltage violated the tolerance might occur. An experimental dataset taken from the Bappeda Pontianak building in West Kalimantan, Indonesia, shows that the proposed algorithm required fewer samples than the RF yet could predict the daily energy consumption and voltage inside a building accurately up to 96%. Note to Practitioners—As the energy and power quality monitoring using IoT is applied for buildings nowadays, how to handle the big data and forecast the energy and power for evaluation and strategy in buildings is significant. A standard solution is to apply sophisticated technology with a high computational resource. However, this will increase the cost either in the investment or maintenance. The algorithm in this paper is a new approach for IoT-based monitoring and forecasting of energy consumption and power quality by combining PE and RT models, which is relatively cheap in computational complexity yet does not require much space to store in an online setup. The proposed algorithm first creates the model with the RT algorithm and then tracks the residual generated by this algorithm with the PE model and extended Kalman filter. We then show that this model can predict the daily energy consumption accurately. The algorithm based on this model can be integrated into the monitoring system and advise the user when the current energy consumption has passed the “normal” energy consumption concerning the information from previous days. Experiments on a building located in Pontianak show that this algorithm is applicable and can precisely predict daily energy consumption and power quality with a limited amount of data. In future research, we plan to expand this technique further, such that it is not only for monitoring purposes but also for control.