Forecasting Transmission Line Loss Using a Cluster-Based Refinement Framework and Scheduled Outage Data

Transmission line loss forecasting is an important power system forecasting task, yet, existing methods often overlook qualitative operational data such as scheduled outages, which directly impact network topology and losses. This paper introduces a new framework that integrates scheduled outage reports with a two-stage cluster-based refinement solution to enhance forecasting accuracy. First, we process and utilize outage data in a way that preserves its temporal and contextual relevance, using Natural Language Processing (NLP) technique. This addresses a key gap in prior works that relies solely on quantitative inputs. Next, the proposed framework employs an initial baseline model in the first stage, followed by cluster-refinement using submodels trained on grouped data patterns. The proposed framework is applied to 24 hour ahead forecasts of transmission losses on an IEEE-118 bus test system, and in Alberta, Canada. We compare the results to benchmark methods from existing state-of-the-art transmission loss forecasting models. Our findings indicate that the proposed framework offers an accurate forecasting solution, outperforming the benchmark techniques. Moreover, these results highlight the value of integrating qualitative information into forecasting models for more accurate and reliable predictions.