Applying Residential Demand Response: An Easy-to-Adopt Approach to Encourage Implementation in Italy

This thesis investigates the practical implementation of a residential demand response (DR) strategy, focusing on real-time price (RTP) forecasting and optimal appliance scheduling. Given the complexity of the Italian electricity market and the challenges it poses to residential consumers, the study proposes a localized DR strategy that relies on accurate RTP prediction and user-convenient appliance scheduling. A primary objective of this research is to demonstrate the viability of an LSTM-based price prediction model as an effective tool for forecasting RTP, outperforming traditional ARIMA models, despite using a single input feature. The superior performance of LSTM neural networks in recognizing and learning from past price patterns contributes to enhancing the efficiency of the DR strategy. A further significant aspect of this study is the introduction of a straightforward Mixed-Integer Linear Programming (MILP) model for appliance scheduling. This model, designed to work effectively within the computational constraints of a residential smart meter, leverages user-defined constraints to ensure optimal appliance operation without causing user discomfort. The user-friendly nature of this model makes it a realistic and practical solution for real-world DR applications. The study demonstrates the effectiveness of the proposed DR strategy, achieving substantial electricity cost savings. A key advantage of the proposed strategy is its localized nature, eliminating the need for demand response aggregator intermediaries and mitigating network investment requirements. This feature, along with the protection of consumer privacy, contributes to making the proposed DR approach an appealing solution for the Italian residential sector, hence encouraging the adoption of DR strategies. The study also acknowledges the limitations inherent in the adopted approach, such as the dependence on accurate price predictions and the simplification of the scheduling algorithm, offering avenues for future research to refine the DR strategy further. Overall, this thesis contributes valuable insights into the practical implementation of a localized DR strategy, adding to the existing body of knowledge in the field of residential energy management.