In the context of ‘environmental sustainability’, the industrial sector confronts environmental difficulties due to the growing demand for energy. Energy efficiency improvements are required to solve these challenges in the industrial business. It is frequently important to predict energy consumption in order to measure energy efficiency. In 2016, about three-quarters of the world's CO2 emissions were driven by the use of energy . About 30% of emissions are attributed to the industrial sector, with 24.2% related to energy use, making it the most significant source of emissions. As a result of the high use of energy, there is a huge possibility to cut CO2 equivalent emissions while simultaneously providing a financial incentive for businesses to improve their energy efficiency. Industrial enterprises need precise estimates of their energy usage in order to implement preventative and mitigation steps to reduce the environmental impact, avoid regulatory fines, and increase competitiveness. The FAO (Food and Agriculture Organization of the United Nations) predicts that food production would need to rise by 70% by 2050 but energy output will only increase by 33%. As a result, there will almost certainly be a growing gap between energy and food production over the same period of time . The general view is that energy and resource usage reductions in the food industry are critical to the profitability of the business, food security, and reaching the Government's emissions reduction objectives. As a result, increasing energy efficiency has emerged as a critical concern for the food industry [3, 4].
Artificial intelligence (AI) and Machine Learning (ML) have great potential to address the global concern of sustainability. For instance, businesses can use machine learning to find relationships between environmental performance and process characteristics as well as monitoring and incident investigation . The contemporary industrial environment encourages the collection of massive volumes of data, the bulk of which seems to be unexamined by the majority of businesses. The increased use of data-driven models in manufacturing is being fuelled by the growing availability of data as a result of the widespread use of relatively affordable Industrial Internet of Things Technologies (IIoT) and the rising processing capacity of cloud computing . Due to its excellent problem-solving and dimensionality capabilities, data-driven methods such as machine learning are often hailed as a superior analytical approach. In spite of this, there is a lack of study on its use in demand-side energy forecasts. In the context of energy efficiency, the majority of existing machine learning research targets issues in the petrochemical industry. As of now, there are just a few published studies on the use of machine learning methods in other sectors to achieve energy-related goals [6, 7]. To support and drive industry 4.0 technologies adoption and enhance the implementation of sustainable industrial development practices, this research will investigate the use of ML techniques to improve energy-resource efficiency in different industries such as the Oil & Gas industry and Food manufacturing.
1. Walther, J. and M. Weigold, A systematic review on predicting and forecasting the electrical energy consumption in the manufacturing industry. Energies, 2021. 14(4): p. 968. https://doi.org/10.3390/en14040968
2. Bundschuh, J., G. Chen, and S. Mushtaq, Towards a sustainable energy technologies based agriculture. 2014 https://doi.org/10.1201/b16643
3. Tassou, S.A., et al., Energy demand and reduction opportunities in the UK food chain. Proceedings of the Institution of Civil Engineers-Energy, 2014. 167(3): p. 162-170. https://doi.org/10.1680/ener.14.00014
4. Jagtap, S., G. Garcia-Garcia, and S. Rahimifard, Optimisation of the resource efficiency of food manufacturing via the Internet of Things. Computers in Industry, 2021. 127: p. 103397. https://doi.org/10.1016/j.compind.2021.103397
5. Fisher, O.J., et al., Considerations, challenges and opportunities when developing data-driven models for process manufacturing systems. Computers & Chemical Engineering, 2020. 140: p. 106881. https://doi.org/10.1016/j.compchemeng.2020.106881
6. Ribeiro, A.M.N., et al., Short-term firm-level energy-consumption forecasting for energy-intensive manufacturing: a comparison of machine learning and deep learning models. Algorithms, 2020. 13(11): p. 274. https://doi.org/10.3390/a13110274
7. Narciso, D.A. and F. Martins, Application of machine learning tools for energy efficiency in industry: A review. Energy Reports, 2020. 6: p. 1181-1199 https://doi.org/10.1016/j.egyr.2020.04.035