The use of big data to optimize energy consumption and environmental performance of construction machinery: models and practical solutions
How to cite
Abstract
The study is devoted to a comprehensive analysis of the potential of big data technologies in optimizing energy consumption and environmental performance of construction machinery. The paper presents an integrative model for managing the energy efficiency of construction machinery based on a multiparametric analysis of operational characteristics. The research methodology is based on the application of machine learning algorithms to arrays of telemetry data collected from 128 units of construction equipment in real-world operating conditions for 24 months. It has been empirically established that the implementation of the proposed model makes it possible to achieve a 17.8% reduction in energy consumption while reducing CO₂ emissions by 22.3% without loss of productivity. Correlations between the modes of operation of equipment and key environmental indicators with a coefficient of determination R2=0.83 have been identified. An algorithm has been developed for predicting the resource status of equipment with an accuracy of 91.7%, which ensures preventive maintenance and minimization of environmental risks. The research results have significant practical value for the construction industry and demonstrate the prospects for integrating big data technologies into the energy efficiency and environmental safety management system of construction processes.
Keywords
References
Arambula-Lara R., Perea-Moreno A.J., Salmerón-Manzano E. Machine Learning Techniques Focusing on the Energy Performance of Buildings: A Dimensions and Methods Analysis // Buildings. 2022. № 12(1). Р. 28.
Elhaby M., Khalifa M., Bitar I.E. Machine learning algorithms for predicting energy consumption in educational buildings // International journal of energy research. 2024.рр. 681-2425.
Himeur Y., Elnour M., Fadli F. AI-Big Data analytics for building automation and management systems: a survey, actual challenges and future perspectives // Artificial intelligence review. 2022. pp. 1-59.
Lei F., Hu P. Energy consumption prediction by using machine learning for smart building: Case study in Malaysia // Developments in the built environment. 2020. № 3.рр. 34-100.
Lu Y., Zhang J. Bibliometric analysis and critical review of the research on big data in the construction industry // Engineering, construction and architectural management. 2022. № 29(9). рр. 3574-3592.
Marinakis V. Big Data for energy management and energy-efficient buildings // Energies. 2020. № 13(7). рр. 15-55.
Miliс V. Next-generation data center energy management: a data-driven decision-making framework // Frontiers in energy research. 2024. № 12. рр. 358-1449.
Nikbakht N.S., Hosseini S., Motamed M. Novel approach to energy consumption estimation in smart homes: application of data mining and optimization techniques // Frontiers in energy research. 2024. № 12. рр. 1361803.
Perovic M., Klimenta D. Predicting energy consumption in residential buildings using advanced machine learning algorithms // Energies. 2023. № 16(9). рр. 37-48.
Puksec J., Kirac M. A Review of energy-efficient and sustainable construction scheduling supported with optimization tools // Energies. 2022. № 15(7). рр. 2330.
Sarswatula S.A., Pugh T., Prabhu V. Modeling energy consumption using machine learning // Frontiers in manufacturing technology. 2022. № 2. рр. 208-855.
Seyedzadeh S., Rahimian F.P., Glesk I., Roper M. Machine learning for estimation of building energy consumption and performance: a review // Visualization in еngineering. 2018. № 6(1). рр. 1-20.
Yesilyurt H., Dokuz Y., Dokuz A.S. Data-driven energy consumption prediction of a university office building using machine learning algorithms // Energy. 2024. № 283. рр. 130-184.
Yu Y., Lin J., Kim S.K. A holistic review of building energy efficiency and reduction based on Big Data // Sustainability. 2021. № 13(4). рр. 22-73.
Zhan S., Chong A., O'Neill Z. Interpretable machine learning for building energy management: A state-of-the-art review // Artificial intelligence review. 2023. № 1. 21-100.