An Investigation into Seasonal Variations in Energy Forecasting for Student Residences

TL;DR

This study evaluates various machine learning models for energy forecasting in student residences, highlighting the importance of seasonal dynamics and proposing adaptable models like Hyper Network LSTM and MiniAutoEncXGBoost.

Contribution

It introduces and assesses season-specific and adaptable machine learning models for improved energy forecasting amidst seasonal and irregular consumption patterns.

Findings

No single model outperforms others across all seasons.

Hyper Network LSTM and MiniAutoEncXGBoost show strong adaptability to seasonal changes.

Season-specific model selection improves forecasting accuracy.

Abstract

This research provides an in-depth evaluation of various machine learning models for energy forecasting, focusing on the unique challenges of seasonal variations in student residential settings. The study assesses the performance of baseline models, such as LSTM and GRU, alongside state-of-the-art forecasting methods, including Autoregressive Feedforward Neural Networks, Transformers, and hybrid approaches. Special attention is given to predicting energy consumption amidst challenges like seasonal patterns, vacations, meteorological changes, and irregular human activities that cause sudden fluctuations in usage. The findings reveal that no single model consistently outperforms others across all seasons, emphasizing the need for season-specific model selection or tailored designs. Notably, the proposed Hyper Network based LSTM and MiniAutoEncXGBoost models exhibit strong adaptability to seasonal variations, effectively capturing abrupt changes in energy consumption during summer months. This study advances the energy forecasting field by emphasizing the critical role of seasonal dynamics and model-specific behavior in achieving accurate predictions.