Sub-Hourly Multi-Horizon Quantile Forecasting of Photovoltaic Power Using Meteorological Data and a HybridCNN–STTransformer
Taganova G. Zakirova A. Abdildayeva A. Nurbekov B. Akhayeva Z. Azykanov T.
February 2026Multidisciplinary Digital Publishing Institute (MDPI)
Algorithms
2026#19Issue 2
The rapid deployment of photovoltaic generation increases uncertainty in power-system operation and strengthens the need for ultra-short-term forecasts with reliable uncertainty estimates. Point-forecasting approaches alone are often insufficient for dispatch and reserve decisions because they do not quantify risk. This study investigates probabilistic forecasting of short-horizon solar generation using quantile regression on a public dataset of solar output and meteorological variables. This study proposes a hybrid attention–convolution model that combines an attention-based encoder to capture long-range temporal dependencies with a causal temporal convolution module that extracts fast local fluctuations using only past information, preventing information leakage. The two representations are fused and decoded jointly across multiple future horizons to produce consistent quantile trajectories. Experiments against representative machine-learning and deep-learning baselines show improved probabilistic accuracy and competitive central forecasts, while illustrating an important sharpness–calibration trade-off relevant to risk-aware grid operation. Key novelties include a multi-horizon quantile formulation at 15 min resolution for one-hour-ahead PV increments, a HybridCNN–STTransformer that fuses causal temporal convolutions with Transformer attention, and a horizon-token decoder that models inter-horizon dependencies to produce consistent multi-step quantile trajectories; reliability/sharpness diagnostics and post hoc calibration are discussed for operational risk-aware use.
CNN , hybrid deep learning , multi-horizon prediction , photovoltaic forecasting , pinball loss , probabilistic forecasting , quantile regression , sub-hourly time series , Transformer
Text of the article Перейти на текст статьи
Faculty of Information Technology, L. N. Gumilyov Eurasian National University, Astana, 010000, Kazakhstan
Higher School of Information Technology and Engineering, Astana International University, Astana, 010000, Kazakhstan
Department of Software Engineering, International Engineering-Technological University, Almaty, 050000, Kazakhstan
Mechanics and Mathematics Faculty, L. N. Gumilyov Eurasian National University, Astana, 010000, Kazakhstan
“Lumox-AI” Individual Entrepreneur, Astana, 010000, Kazakhstan
Faculty of Information Technology
Higher School of Information Technology and Engineering
Department of Software Engineering
Mechanics and Mathematics Faculty
“Lumox-AI” Individual Entrepreneur
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026