Abstract
With the development of modern power systems (smart grid), energy consumption prediction becomes an essential aspect of resource planning and operations. In the last few decades, industrial and commercial buildings have thoroughly been investigated for consumption patterns. However, due to the unavailability of data, the residential buildings could not get much attention. During the last few years, many solutions have been devised for predicting electric consumption; however, it remains a challenging task due to the dynamic nature of residential consumption patterns. Therefore, a more robust solution is required to improve the model performance and achieve a better prediction accuracy. This paper presents an ensemble approach based on learning to a statistical model to predict the short-term energy consumption of a multifamily residential building. Our proposed approach utilizes Long Short-Term Memory (LSTM) and Kalman Filter (KF) to build an ensemble prediction model to predict short term energy demands of multifamily residential buildings. The proposed approach uses real energy data acquired from the multifamily residential building, South Korea. Different statistical measures are used, such as mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and R2 score, to evaluate the performance of the proposed approach and compare it with existing models. The experimental results reveal that the proposed approach predicts accurately and outperforms the existing models. Furthermore, a comparative analysis is performed to evaluate and compare the proposed model with conventional machine learning models. The experimental results show the effectiveness and significance of the proposed approach compared to existing energy prediction models. The proposed approach will support energy management to effectively plan and manage the energy supply and demands of multifamily residential buildings.
Highlights
In recent times, a considerable amount of energy consumption is attributed to residential buildings. owing to a high consumption share of the building sector worldwide has turned into an undefined energy sink
The proposed model architecture consists of the following steps: acquisition of residential energy consumption data, preprocessing of energy consumption data, time-series analysis, data normalization, data splitting into training and testing subsets, training and testing of ensemble model based on Long Short-Term Memory (LSTM) and Kalman Filter, and performance evaluation
LSTM acts as a heuristic learner which learn patterns from hourly electric consumption to predict short-term energy consumption demands of the residential buildings, whereas Kalman Filter (KF) acts as a stochastic algorithm that is used to process the training filtering problem and works by estimating states by the reduction of average distance between data and its curve, it only stores the result computed from the previous step
Summary
A considerable amount of energy consumption is attributed to residential buildings. owing to a high consumption share of the building sector worldwide has turned into an undefined energy sink. Machine learning (ML) algorithms are widely used by the researchers to build intelligent inference models based on discovered characteristics using DM techniques to forecast time series data. Provide different time-series analysis of energy consumption data of multifamily residential buildings, South Korea, to highlight hidden insights and characteristics for stakeholders to devise effective policies. Integration of deep learning and statistical models to forecast short-term energy consumption using time-series data collected from multifamily residential buildings, South Korea. The rest of the paper is summarized as follows: Section 2 presents the related works; Section 3 presents methodology of the proposed ensemble prediction model based on LSTM and KF using time-series electricity consumption data of multi-family buildings.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
