Forecasting peak energy demand for smart buildings

Abstract

Predicting energy consumption in buildings plays an important part in the process of digital transformation of the built environment, and for understanding the potential for energy savings. This also contributes to reducing the impact of climate change, where buildings need to increase their adaptability and resilience while reducing energy consumption and maintain user comfort. The use of Internet of Things devices for monitoring and control of energy consumption in buildings can take into account user preferences, event monitoring and building optimization. Detecting peak energy demand from historical building data can enable users to manage their energy use more efficiently, while also enabling real-time response strategies (including control and actuation) to known or future scenarios. Several statistical, time series, and machine learning techniques are proposed in this work to predict electricity consumption for five different building types, by using peak demand forecasting to achieve energy efficiency. We have used several indigenous and exogenous variables with a view to test different energy forecasting scenarios. The suggested techniques are evaluated for creating predictive models, including linear Regression, dynamic regression, ARIMA time series, exponential smoothing time series, artificial neural network, and deep neural network. We conduct the analysis on an energy consumption dataset of five buildings from 2014 until 2019. Our results show that for a day ahead prediction, the ARIMA model outperforms the other approaches with an accuracy of 98.91% when executed over a 168 h (1 week) of uninterrupted data for five government buildings.

An end-to-end approach for scalable real time Anomaly detection in smart buildings

“…Furthermore, several models for energy consumption prediction are examined at [22], and several Machine Learning models were deployed and tested in a real-world Smart Building testbed, with modest results due to the small size of the dataset that was used. Of course, there exists a much larger number of studies related to energy forecasting than the ones that were already presented [23][24][25][26][27].…”

Simulation and Modelling of Electricity Usage Control and Monitoring System using ThingSpeak

“…They become more aware of energy usage and efficiency because of economic and environmental reasons (23). Detecting peak energy demand also allow users to manage their energy use more proficiently and plan the future scenarios (24). The use of IoT devices for monitoring and control of energy consumption can also consider a lot of other parameters such as event monitoring, building optimization and user favorites.…”

“…The implementation of their proposed system transformed the house into a smart house which eventually generates cost savings and promotes sustainable living. In addition, the collected electricity consumption data also can be used to forecast the future consumption as done in (24,30). ( 30) proposed a forcasting model and algorithm of electricity usage for household.…”

“…Their proposed model can be used to control operating parameters based on power consumption plans and considered the functionality of smart electricity meters. (24) predicted energy consumption plays an important role in the process of digital transformation and for understading the potential for energy savings. Their proposed method use different techniques in forcasting the energy consumption such as linear regression, dynamic regression, artificial and deep neural network.…”

Development progress of power prediction robot and platform: Its world level very long term prototyping example

“…The sixth literature cluster is the long to very-short-term forecasting time horizon of peak power demand prediction topic that includes studies like Ismail (2009), Goia et.al (2010), Asad (2012) [112][113][114][115][116][117][118][119][120][121], however, it is not necessary and possible to cite all of them in this paper. It is important to note that (GP2S), and some parts of (GP2D), (GP2E), and (GP2O) cover the scope of all or some parts of those studies in the literature.…”