The increasing cost and demand for energy, coupled with the need to achieve environmental sustainability goals, poses significant challenges that require a multifaceted approach. This research aims to address these challenges by leveraging predictive machine learning techniques and automated feature engineering methods to enhance energy consumption monitoring in various structures, buildings, and environments. This PhD comprises interconnected studies. The first study focuses on predicting electricity consumption, indoor temperature, and humidity in food and drink cold storage rooms using machine learning. Drawing on weather data, it aims to develop explainable machine-learning techniques. It comprehensively investigates the challenges posed by current models in this specialised domain and explores the integration of seasonal elements and human operations into these predictive models. Accurately predicting electricity consumption can significantly contribute to reducing energy usage through improved monitoring and planning. This optimisation can help streamline operational scheduling in such environments, facilitating more sustainable energy management practices and ultimately reducing CO2 emissions. Additionally, monitoring temperature and humidity in these settings is crucial to ensure food safety and preserve the quality of perishable items.

Building upon the first study, the subsequent studies aim to develop an automated feature engineering method integrated with automated machine learning. This approach addresses the challenges associated with the need for domain knowledge in generating new input features, enhancing model performance, and streamlining machine learning model development. For validation of the proposed algorithm, multiple datasets representing various energy consumption settings will be employed, including residential and commercial buildings, renewable energy sources such as wind turbines, and both regional and city-wide energy consumption. Potential positive impacts include the improvement of energy management monitoring systems and the advancement of applied machine learning techniques.