A review of data-driven building energy consumption prediction studies

Amasyali, Kadir; El-Gohary, Nora

doi:10.1016/j.rser.2017.04.095

Cited by 1,288 publications

(596 citation statements)

References 77 publications

Supporting

Mentioning

441

Contrasting

Unclassified

Order By: Relevance

“…Inverse models are based on some mathematical relationship between inputs and outputs which can be derived by using various statistical or machine learning algorithms. A comprehensive review of data-driven approaches for prediction of energy consumption in buildings can be found in [19]. Since inception, sensing technologies-based models for energy management have attracted significant research attention.…”

Section: Related Workmentioning

confidence: 99%

A Prediction Mechanism of Energy Consumption in Residential Buildings Using Hidden Markov Model

2018

View full text Add to dashboard Cite

Internet of Things (IoT) is considered as one of the future disruptive technologies, which has the potential to bring positive change in human lifestyle and uplift living standards. Many IoT-based applications have been designed in various fields, e.g., security, health, education, manufacturing, transportation, etc. IoT has transformed conventional homes into Smart homes. By attaching small IoT devices to various appliances, we cannot only monitor but also control indoor environment as per user demand. Intelligent IoT devices can also be used for optimal energy utilization by operating the associated equipment only when it is needed. In this paper, we have proposed a Hidden Markov Model based algorithm to predict energy consumption in Korean residential buildings using data collected through smart meters. We have used energy consumption data collected from four multi-storied buildings located in Seoul, South Korea for model validation and results analysis. Proposed model prediction results are compared with three well-known prediction algorithms i.e., Support Vector Machine (SVM), Artificial Neural Network (ANN) and Classification and Regression Trees (CART). Comparative analysis shows that our proposed model achieves 2.96% better than ANN results in terms of root mean square error metric, 6.09% better than SVM and 9.03% better than CART results. To further establish and validate prediction results of our proposed model, we have performed temporal granularity analysis. For this purpose, we have evaluated our proposed model for hourly, daily and weekly data aggregation. Prediction accuracy in terms of root mean square error metric for hourly, daily and weekly data is 2.62, 1.54 and 0.46, respectively. This shows that our model prediction accuracy improves for coarse grain data. Higher prediction accuracy gives us confidence to further explore its application in building control systems for achieving better energy efficiency.

show abstract

Section: Related Workmentioning

confidence: 99%

A Prediction Mechanism of Energy Consumption in Residential Buildings Using Hidden Markov Model

2018

View full text Add to dashboard Cite

show abstract

“…However, most of the energy used in the world comes from fossil fuels whose reserves have been decreasing. However, energy consumption increases and with it all associated economic, social and environmental impacts [1][2][3].…”

Section: Introductionmentioning

confidence: 99%

Model Predictive Control Home Energy Management and Optimization Strategy with Demand Response

et al. 2018

View full text Add to dashboard Cite

Abstract:The growing demand for electricity is a challenge for the electricity sector as it not only involves the search for new sources of energy, but also the increase of generation capacity of the existing electrical infrastructure and the need to upgrade the existing grid. Therefore, new ways to reduce the consumption of energy are necessary to be implemented. When comparing an average house with an energy efficient house, it is possible to reduce annual energy bills up to 40%. Homeowners and tenants should consider developing an energy conservation plan in their homes. This is both an ecological and economically rational action. With this goal in mind, the need for the energy optimization arises. However, this has to be made by ensuring a fair level of comfort in the household, which in turn spawns a few control challenges. In this paper, the ON/OFF, proportional-integral-derivative (PID) and Model Predictive Control (MPC) control methods of an air conditioning (AC) of a room are compared. The model of the house of this study has a PV domestic generation. The recorded climacteric data for this case study are for Évora, a pilot Portuguese city in an ongoing demand response (DR) project. Six Time-of-Use (ToU) electricity rates are studied and compared during a whole week of summer, typically with very high temperatures for this period of the year. The overall weekly expense of each studied tariff option is compared for every control method and in the end the optimal solution is reached.

show abstract

“…Energy data are used in a wide range of applications. Among the most successful applications is the consumption profile forecast in buildings [1], which can have a number of advantages, including failure predictions and the optimization of energy management systems [2]. The energy characteristics of buildings are often included in energy certifications, and a proper data analysis on large datasets can provide useful insights for energy planning at an urban scale [3].…”

Section: Introductionmentioning

confidence: 99%

Performance Indicators of Electricity Generation at Country Level—The Case of Italy

2018

View full text Add to dashboard Cite

Abstract:Power Grids face significant variability in their operation, especially where there are high proportions of non-programmable renewable energy sources constituting the electricity mix. An accurate and up-to-date knowledge of operational data is essential to guaranteeing the optimal management of the network, and this aspect will be even more crucial for the full deployment of Smart Grids. This work presents a data analysis of the electricity production at the country level, by considering some performance indicators based on primary energy consumption, the share of renewable energy sources, and CO 2 emissions. The results show a significant variability of the indicators, highlighting the need of an accurate knowledge of operational parameters as a support for future Smart Grid management algorithms based on multi-objective optimization of power generation. The renewable share of electricity production has a positive impact, both on the primary energy factor and on the CO 2 emission factor. However, a strong increase of the renewable share requires that the supply/demand mismatching issues be dealt with through appropriate measures.

show abstract

A review of data-driven building energy consumption prediction studies

Cited by 1,288 publications

References 77 publications

A Prediction Mechanism of Energy Consumption in Residential Buildings Using Hidden Markov Model

A Prediction Mechanism of Energy Consumption in Residential Buildings Using Hidden Markov Model

Model Predictive Control Home Energy Management and Optimization Strategy with Demand Response

Performance Indicators of Electricity Generation at Country Level—The Case of Italy

Contact Info

Product

Resources

About