Hybrid forecasting of demand flexibility: A top-down approach for thermostatically controlled loads

• Published in: Energy and AI Vol. 20; p. 100487
• Main Authors: Massidda, Luca, Marrocu, Marino
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.05.2025; Elsevier
• Subjects: Causal machine learning; Conformalized quantile regression; Demand response; Demand side flexibility; Disaggregation of electricity consumption; Flexibility forecasting; Thermostatically controlled loads; Virtual battery model; Flexibility forecasting; Causal machine learning; Thermostatically controlled loads; Virtual battery model; Demand response; Conformalized quantile regression; Disaggregation of electricity consumption; Demand side flexibility
• ISSN: 2666-5468; 2666-5468
• DOI: 10.1016/j.egyai.2025.100487

Demand-side flexibility is crucial to balancing supply and demand, as renewable energy sources are increasingly integrated into the energy mix, and heating and transport systems are becoming more and more electrified. Historically, this balancing has been managed from the supply side. However, the shift towards renewable energy sources limits the controllability of traditional fossil fuel plants, increasing the importance of demand response (DR) techniques to achieve the required flexibility. Aggregators participating in flexibility markets need to accurately forecast the adaptability they can offer, a task complicated by numerous influencing variables. Based on a top-down approach, this study addresses the problem of forecasting electricity demand in the presence of flexibility from thermostatically controlled loads. We propose a hybrid model that combines data-driven techniques for probabilistic estimation of electricity consumption with a disaggregation of electricity consumption to identify the fraction of thermal loads, subject to flexibility, which is simulated by a virtual battery model. The technique is applied to a synthetic dataset that simulates the response of a European neighborhood to demand response interventions. The results demonstrate the model’s ability to accurately predict both the reduction in electricity demand during DR events and the subsequent rebound in consumption. The model achieves a mean absolute percentage error (MAPE) lower than 17.0%, comparable to the accuracy without flexibility. The results obtained are compared with a direct data-driven approach, demonstrating the validity and effectiveness of our model. [Display omitted] •A hybrid model forecasts demand-side flexibility of thermostatically controlled loads.•Conformalized Quantile Regression provides a probabilistic forecast of district load.•Causal machine learning disaggregates thermal loads without direct measurements.•System response to set-point changes is simulated via a virtual battery model.•The hybrid model is validated against data-driven approaches on a synthetic dataset.