Enhancing Energy Consumption Predictions Using ANFIS method

Abstract

This study investigates the application of the Adaptive Neuro-Fuzzy Inference System (ANFIS) for predicting energy consumption, leveraging its unique combination of neural networks and fuzzy inference systems. The research focuses on the integration of historical energy consumption data with influencing factors such as time-related variables, weather conditions, and occupancy levels. By harnessing the adaptive learning capabilities of neural networks alongside the reasoning power of fuzzy logic, ANFIS effectively models complex, nonlinear relationships inherent in energy usage patterns. The performance of ANFIS is compared to traditional forecasting methods, highlighting its enhanced accuracy and robustness in handling uncertainty and imprecision in real-world data. The findings suggest that ANFIS can significantly improve energy management strategies, offering valuable insights for optimizing resource allocation and reducing consumption.