A Novel ANFIS Framework for Energy Consumption Forecasting in Vietnam

Abstract

Accurate prediction of energy consumption in the future plays an essential role in national energy security and sustainable economic planning in Vietnam. However, the energy consumption data is subject to non-linearity, high fluctuation and complex seasonal variations. To address this problem, this study proposes a novel framework based on an ANFIS model; the proposed models were established by integrating the Denton method, the Adaptive Neuro-Fuzzy Inference System (ANFIS) and meta-heuristic algorithms, namely Particle Swarm Optimization (PSO), the Grey Wolf Optimizer (GWO), and the Whale Optimization Algorithm (WOA). The simulation results demonstrate that the PSO-ANFIS model achieved the best performance, with a Mean Absolute Percentage Error (MAPE) of 4.65% and an 𝑅2 score of 0.7275. Based on this result, this study suggests that the PSO-ANFIS model is a promising candidate for forecasting the energy consumption demand in Vietnam. Energy consumption demand will reach 3108.38 billion kWh by 2030. These findings provide a reliable scientific foundation for grid management and strategic policy-making.