Researchers from the Jožef Stefan Institute, a partner in the SEEDS Project, presented their latest research at MIPRO 2026, the International Convention on Information, Communication and Electronic Technology. The paper explores new approaches to improving short-term electricity consumption forecasting by addressing skewed demand distributions.

Accurate electricity demand forecasting is essential for balancing electricity supply and demand, supporting smart grids, and enabling the integration of renewable energy sources. By improving forecasting accuracy, this research contributes to more reliable and flexible energy management, helping advance Europe’s transition towards smarter and more sustainable energy systems.

The full abstract is available below.

Abstract –
Accurate forecasting of electricity consumption is crucial for smart grids, enabling dynamic matching of supply and demand in both domestic and industrial use. This paper focuses on predicting electricity usage for individual households over a two-day horizon, a scenario that could facilitate flexible consumption adjustments based on grid conditions, showcasing methods that can also be applied in industrial applications.

A significant challenge in this context is the presence of numerous peaks in consumption patterns, which are difficult to predict in terms of timing and magnitude. These peaks resemble outliers and introduce skewness into the target value distribution, ultimately degrading the performance of forecasting models.

To address this issue, we empirically evaluate two approaches: example data weighting and square root transformation of target values. Our goal is to assess the effectiveness and limitations of these methods in mitigating the impact of skewed distributions on forecasting performance.

Title: Addressing Skewed Distributions in Electricity Consumption Forecasting
Authors: Fatima Aziz, Martin Žnidaršič, Aljaž Osojnik and Bernard Ženko
Affiliation: Jožef Stefan Institute, Slovenia
Conference: MIPRO 2026

Link to the full article – https://mipro.hr/MIPRO2026.AIS/ELink.aspx