Search

Advancements in technology, continuous innovation, and the emergence of the Industry 4.0 paradigm are driving Distribution System Operators toward increasingly competitive environments where flexible demand response mechanisms are essential. In many developing nations, however, the absence of standardized measurement frameworks across industrial process chains hinders the effective deployment of demand-side management models, leading to inefficiencies in data analysis and limiting the accurate assessment of large-scale consumers’ contributions to flexibility. To address this gap, the present study utilizes load profile data—specifically energy and power measurements obtained from utility meters—as input variables to generate disaggregated forecasts at 15-minute intervals across four defined time segments. The proposed approach is validated through performance metrics, with outcomes assessed using the Root Mean Square Error (RMSE) to quantify total methodological error. The framework integrates Machine Learning and Big Data techniques implemented in Python, employing Combinatorial Disaggregation Optimization alongside Factorial Hidden Markov Models to enhance prediction accuracy.