Enhanced N-BEATS for Mid-Term Electricity Demand Forecasting

TL;DR

Evaluated on real-world monthly electricity consumption data from 35 European countries, N-BEATS* demonstrates superior performance compared to its predecessor and other established forecasting methods, including statistical, machine learning, and hybrid models.

Abstract

This paper presents an enhanced N-BEATS model, N-BEATS*, for improved mid-term electricity load forecasting (MTLF). Building on the strengths of the original N-BEATS architecture, which excels in handling complex time series data without requiring preprocessing or domain-specific knowledge, N-BEATS* introduces two key modifications. (1) A novel loss function -- combining pinball loss based on MAPE with normalized MSE, the new loss function allows for a more balanced approach by capturing both L1 and L2 loss terms. (2) A modified block architecture -- the internal structure of the N-BEATS blocks is adjusted by introducing a destandardization component to harmonize the processing of different time series, leading to more efficient and less complex forecasting tasks. Evaluated on real-world monthly electricity consumption data from 35 European countries, N-BEATS* demonstrates superior performance compared to its predecessor and other established forecasting methods, including statistical, machine learning, and hybrid models. N-BEATS* achieves the lowest MAPE and RMSE, while also exhibiting the lowest dispersion in forecast errors.

Figures (7)

• Figure 1: Examples of monthly electricity demand time series.
• Figure 2: Architecture of the N-BEATS* model.
• Figure 3: Example loss functions for $\tau=0.5$ and $\tau=0.2$.
• Figure 4: Data processing by N-BEATS -- example showing test data for Austria.
• Figure 5: MAPE for individual countries.