Smart energy strategies: Leveraging LSTM and LLMs for advanced energy management

• Our research aims to support sustainable objectives using effective and efficient energy predictors such as the LSTM model, evaluated comparatively against GRU and XGBoost models. Thus, besides presenting an opportunity to minimize energy waste, the proposed recommendation system for space heating, cooling, and free-cooling consumption is designed to predict and manage energy use dynamically. • One of the most critical aspects of this study is the interpretation of graphical analyses using OpenAI's Generative Pretrained 4.0 (GPT-4.0) model, which presents significant challenges and opportunities. One major challenge is accurately conveying complex patterns in energy consumption data, which can be influenced by various factors such as seasonal changes, occupancy patterns, and weather conditions. The graphical representations of space heating, ceiling cooling, and free cooling systems often reveal intricate interactions that are difficult to interpret without advanced tools. The integration of the GPT-4 model enhances this process by providing detailed, context-specific insights and recommendations based on the visualized data. This approach simplifies understanding of complex graphs and facilitates actionable decision-making by highlighting key trends and anomalies. To the best of our knowledge, this is the first recommendation system that integrates such interpretation capabilities, offering a more nuanced and precise understanding of energy consumption patterns. The significance of this interpretation lies in its ability to support more effective and informed energy management strategies, leading to improved efficiency and reduced operational costs in building environments. • Development of a novel recommendation system using the LSTM model to predict and optimize SH, CC, and FC energy consumption in buildings. • Comparative evaluation of LSTM against GRU and XGBoost models to identify the most effective architecture for forecasting building energy consumption. • Enhancement of energy efficiency and sustainability by leveraging advanced machine learning techniques to dynamically adjust building energy operations based on real-time environmental factors and occupancy patterns. • Introduced a novel recommendation system that integrates OpenAI's GPT-4 for interpreting graphical analyses of energy consumption, providing detailed, context-specific insights to enhance decision-making and operational efficiency. Accurately predicting and optimizing heating and cooling demands in building energy management is crucial for enhancing efficiency and reducing energy consumption. Traditional methods often struggle with building energy usage patterns' nonlinear and variable nature. With the advent of advanced data collection through smart sensors, there is a growing need for intelligent systems to leverage this data to provide actionable insights. This study addresses the gap by developing a recommendation system using three machine and deep learning models, Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and XGBoost to predict and optimize the efficiency levels of space heating, ceiling cooling, and free cooling systems. Our proposed solution harnesses the power of these models, with LSTM performing best overall, to forecast energy consumption across hourly and daily timescales, enabling precise adjustments and efficient energy management. The methodology involves extensive data preprocessing, including hierarchical imputation of missing values and label encoding of categorical variables, followed by the transformation of raw data into efficiency levels. The deep learning model architecture, consisting of sequential layers, captures long-term dependencies in the data, while grid search-based hyperparameter tuning optimizes model performance. Results indicate high predictive accuracy, with R-squared values demonstrating the model's ability to explain up to 97.2% of the variance in hourly space heating, 95.2% in daily ceiling cooling, and 93% in daily free cooling energy consumption. Additionally, we interpret graphs using OpenAI's GPT-4 model to enhance understanding and facilitate actionable insights. This interpretation enhances the clarity of the predictive results, supporting more informed decision-making in energy management. The significance of this work lies in its potential to transform energy management practices in building environments, providing a robust tool for optimizing heating and cooling operations and contributing to overall energy efficiency.