2026-10-06T13:05:30Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33826003 2026-09-29T23:55:55Z category_26479 portal_12 item_type_5 month_year_09_2026

Masood Ur Rehman: Context–Aware Solar PV Forecasting for Critical Energy Infrastructure using Seasonal Mixture of Experts Masood Ur Rehman (18087421) Nirmal Nair (1208952) Kevin I-Kai Wang (1195782) Photovoltaic power systems Solar PV Power Forecasting Mixture of Ex- perts LSTM Seasonal Time Series Context-Aware Prediction <p dir="ltr">Accurate short-term forecasting of solar photovoltaic (PV) power is vital for the reliable operation and resilience of critical energy infrastructure but remains challenging due to seasonal variability and transitional weather patterns. This paper proposes a seasonal Mixture of Experts (MoE) framework that integrates season-specialized Long Short-Term Memory (LSTM) experts with a context-aware gating mechanism to improve forecasting accuracy and adaptability. Each expert captures the temporal characteristics of a specific season, while the gating network dynamically weights their contributions based on the current operating context. Qualitative analysis of expert selection confirms the model’s adaptability to evolving seasonal dynamics, demonstrating the effectiveness of combining seasonal specialization with adaptive expert blending for accurate and generalizable solar PV power forecasting. The proposed framework is evaluated using real-world data and compared against Seasonal Autoregressive Integrated Moving Average (SARIMA), Support Vector Regression (SVR), and a standalone LSTM model. The proposed framework achieves improvements ranging from 21.47% to 50.26% over the baseline models, highlighting its potential to support more resilient operation and planning of critical energy infrastructure.</p> 2026-09-29T23:55:55Z Image Poster 10.17608/k6.auckland.33826003.v2 https://figshare.com/articles/poster/Context_Aware_Solar_PV_Forecasting_for_Critical_Energy_Infrastructure_using_Seasonal_Mixture_of_Experts/33826003 CC BY 4.0