Facilitating AI and System Operator Synergy: Active Learning-Enhanced Digital Twin Architecture for Day-Ahead Load Forecasting

TL;DR

This paper tackles trustworthy day-ahead load forecasting in modern power grids by integrating AI with system operators through a digital twin augmented by an active learning loop. The proposed architecture combines real-time data pipelines, an encoder–decoder RNN probabilistic forecaster with Gaussian Negative Log Likelihood loss, and an AL framework that queries high-uncertainty forecasts to update the model, all within a human-in-the-loop HMI. A Greek transmission network case study demonstrates superior point and probabilistic forecast performance compared with traditional methods and shows how AL improves the reliability of prediction intervals. The work advances digitalization and intelligent grid management by enabling scalable, uncertainty-aware forecasting and operator-guided learning, with potential extensions to broader DT services and visualization via LLM-backed tools.

Abstract

In this paper, we introduce a synergistic approach between artificial intelligence and system operators through an innovative digital twin architecture, integrated with an active learning framework, to enhance short-term load forecasting. Central to this architecture is the incorporation of sophisticated data pipelines, facilitating the real-time ingestion, processing and analysis of grid-related data. Utilizing a recurrent neural network architecture, our model generates day-ahead load forecasts together with prediction confidence intervals, strengthening system operator trust in the model's predictive reliability and enhancing their ability to respond to evolving grid conditions effectively. The active learning framework iteratively refines the predictions by incorporating real-time feedback based on forecast uncertainty, utilizing newly available data to continuously enhance forecasting accuracy and confidence. This AI-assisted strategy is exemplified in a case study of the Greek transmission system. It demonstrates the potential to transform short-term load forecasting, thereby increasing the reliability and operational efficiency of modern power grids. This approach marks a significant step forward in the digitalization and intelligent management of power systems.

Figures (5)

• Figure 1: DT Architecture.
• Figure 2: RNN Architecture: Encoder-Decoder Implementation.
• Figure 3: AL Framework.
• Figure 4: Day-ahead forecast with RNN model together with 95% confidence intervals.
• Figure 5: Day-ahead forecast with RNN model together with 95% confidence intervals after the incorporation of AL.