Efficient Energy Demand-Supply Forecasting via Deep Learning

In recent years, sustainable development and intelligent applications have grown in parallel, complementing each other. Sustainability enhances the effectiveness of intelligent applications, while these applications contribute to improved sustainability. Energy is a key factor in promoting sustainability, with renewable energy sources often generating surplus energy. Monitoring sustainable applications such as smart cities, smart buildings, and smart environments is crucial to understanding the demand for resources like water, energy, air, and sunlight, ensuring a balanced supply. This paper proposes a deep learning prediction model designed to balance demand and supply by analyzing energy requirements end-to-end. To validate the effectiveness of the model, its performance is compared with other machine learning models commonly used for similar purposes. Daily predictions are essential for maintaining efficiency in sustainable and smart environments, ensuring customer demands are met alongside surplus supply. The study provides a detailed overview of machine learning and deep learning algorithms, along with experimental results. Based on the comparative analysis, the LSTM model demonstrates superior performance compared to the other models.