Intelligent deep learning techniques for energy consumption forecasting in smart buildings: a review

Mathumitha, R.; Rathika, P.; Manimala, K.

doi:10.1007/s10462-023-10660-8

Cited by 6 publications

(2 citation statements)

References 92 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mathumitha et al [26] explored various deep learning methods used for predicting buildings' energy usage and found that the DNN model performed better.…”

Section: Related Workmentioning

confidence: 99%

“…Compared to other works, this study concentrates on the predictive modeling of energy consumption in South African residential buildings using RF, DT, XGBoost, and AdaBoost models with real-world data. While the authors in [23][24][25][26] proposed different techniques for predicting the energy consumption of residential buildings, this study investigates whether or not the models we propose outperform their models in terms of prediction accuracy. This will include a detailed analysis of the performance criteria (MSE, MAE, MAPE, and R 2 ) and a discussion on how our findings align with or differ from previous studies.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Predictive Model of Energy Consumption Using Machine Learning: A Case Study of Residential Buildings in South Africa

Moulla,

Attipoe,

Mnkandla

et al. 2024

Sustainability

View full text Add to dashboard Cite

The recurrent load shedding crisis in South Africa has highlighted the need to accurately predict electricity consumption for residential buildings. This has significant ramifications for daily life and economic productivity. To address this challenge, this study leverages machine learning models to predict the hourly energy consumption of residential buildings in South Africa. This study evaluates the performance of various regression techniques, including Random Forest (RF), Decision Tree (DT), Extreme Gradient Boosting (XGBoost), and Adaptive Boosting (AdaBoost) machine learning models, using a national residential dataset that contains measurements collected every hour. The objective is to determine the most effective models for predicting next-hour residential building consumption. These models use historical patterns of energy usage to capture temporal details such as seasonal variations and rolling averages. Feature engineering methods are further employed to enhance their predictive capabilities. The performance of each individual model was evaluated using criteria such as the mean squared error (MSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and coefficient of determination (R2). The results show that both RF and DT achieve the best accuracy for the prediction of residential electricity consumption (because the MSE, MAE, and MAPE for RF and DT are very close to 0). These findings offer actionable insights for households, businesses, and policymakers. By enabling more accurate and granular energy consumption forecasts, this can mitigate the effects of load shedding. This study contributes to the discourse on sustainable energy management by combining advanced machine learning models with real-world energy challenges.

show abstract

“…Mathumitha et al [26] explored various deep learning methods used for predicting buildings' energy usage and found that the DNN model performed better.…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Predictive Model of Energy Consumption Using Machine Learning: A Case Study of Residential Buildings in South Africa

Moulla,

Attipoe,

Mnkandla

et al. 2024

Sustainability

View full text Add to dashboard Cite

show abstract

Reusing the Wasted Energy of Electrochromic Smart Window for Near‐Zero Energy Building

Xie,

Huang,

et al. 2024

Advanced Science

View full text Add to dashboard Cite

Electrochromic smart windows (ESWs) are an effective energy‐saving technology for near‐zero energy buildings. They consume electric energy unidirectionally during a round‐trip coloring‐bleaching process, with the energy involved in the bleaching process being wasted. It is highly desirable to reuse this wasted electric energy directly and/or transfer it into other energy storage equipment, further enhancing the overall efficiency of electric energy usage. Herein, a zinc anode‐based ESW (ESW‐PZ) is reported that not only has fascinating visible–near‐infrared (VIS‐NIR) dual‐band electrochromic performance (a high optical contrast of 63%) but also showcases good energy storage characteristics (a wide voltage window of 2.6 V and a high energy density of 127.5 µWh cm−2). The buildings utilizing ESW‐PZ to modulate indoor environments demonstrated an average annual energy saving of 366 MJ m−2 based on energy simulations, which is about 16% of the total energy consumption. Impressively, a high utilization efficiency of 90% (855 mWh m−2) of the wasted electric energy is realized through an ingenious circuit‐switching strategy, which can be reused to power small household appliances.

show abstract

A Novel Approach for Forecasting and Scheduling Building Load through Real-Time Occupant Count Data

Rafiq,

Mahmood,

Ahmed

et al. 2024

Arab J Sci Eng

View full text Add to dashboard Cite

The smart buildings’ load forecasting is necessary for efficient energy management, and it is easily possible because of the data availability based on widespread use of Internet of Things (IoT) devices and automation systems. The information of buildings’ occupancy is directly associated with energy consumption. Therefore, we present a hybrid model consisting of a Long Short-Term Memory (LSTM) network, Extreme Gradient Boosting (XgBoost), Random Forest (RF) and Linear Regression (LR) for commercial and academic buildings’ load forecasting. The correlation between occupants’ count and total load of the building is calculated using Pearson Correlation Coefficient (PCC). The comparative analysis of the proposed approach with LSTM, XgBoost, RF and Gated Recurrent Unit (GRU) is also performed. Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Square Error (MSE) and Normalized Root Mean Square Error (NRMSE) are used as performance indicators for evaluating performance. Findings indicate that the proposed hybrid approach outperforms other models. The RMSE and MAE of 2.99 and 2.18, respectively, are recorded by the proposed model for commercial building dataset while for academic building the RMSE and MAE are 4.48 and 2.85, respectively. Occupancy and load consumption have a positive correlation as evident from PCC analysis. Therefore, we have scheduled the forecasted load based on occupancy patterns for two different cases. Cost is reduced by 17.42% and 33.40% in case 1 and case 2, respectively. Moreover, the performance of the proposed hybrid approach is compared with different techniques presented in literature for buildings load forecasting.

show abstract

Intelligent deep learning techniques for energy consumption forecasting in smart buildings: a review

Cited by 6 publications

References 92 publications

Predictive Model of Energy Consumption Using Machine Learning: A Case Study of Residential Buildings in South Africa

Predictive Model of Energy Consumption Using Machine Learning: A Case Study of Residential Buildings in South Africa

Reusing the Wasted Energy of Electrochromic Smart Window for Near‐Zero Energy Building

A Novel Approach for Forecasting and Scheduling Building Load through Real-Time Occupant Count Data

Contact Info

Product

Resources

About