Matteo Ranaboldo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Matteo Ranaboldo has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Laia Ferrer-Martí
Universitat Politècnica de Catalunya – Barcelona Tech
6 shared publications Alberto García-Villoria
5 shared publicationsRafael Pastor Moreno
5 shared publications- Bruno Domenech
Universitat Politècnica de Catalunya – Barcelona Tech
4 shared publications - Eduard Bullich-Massagué
Centre dInnovaci Tecnolgica en Convertidors Estatics i Accionaments (CITCEA), ETS dEnginyeria Industrial de Barcelona, Universitat Politcnica de Catalunya (UPC), Barcelona, Spain
4 shared publications - Marc Juanpera
Universitat Politècnica de Catalunya – Barcelona Tech
4 shared publications
Latest Publications
- Open Access
- 24 October 2026
- Published by Elsevier in SSRN Electronic Journal
A Safe Deep Reinforcement Learning Approach to Mitigating Demand Response Load Rebounds for TSOs
Industrial demand response is essential for grid stability amid increasing variable renewable energy penetration. However, explicit demand response adoption is hindered by post-activation demand spikes, known as load rebounds. This paper proposes a methodology for transmission system operators to manage load rebounds in high-voltage networks with limited supply-side flexibility. First, a rolling-horizon model combining mixed-integer linear and constraint programming schedules an energy-intensive steel plant under implicit and explicit demand response programmes and generates feasible flexibility offers for balancing markets. Second, the industrial model is embedded in a modified high-voltage CIGRE stress-test network to simulate load rebounds after flexibility activations. Finally, in a safe deep reinforcement learning approach, a recurrent Proximal Policy Optimisation agent dispatches distributed demand-side flexibility and the reactive power of static var compensators to manage the network and mitigate load rebounds. A safety projection verifies each action of the agent with a power flow and, when an operational limit is violated, corrects it with a quadratic program built on exact power flow sensitivities; when no safe action exists, the action of minimal measured violation is applied. Compared with local voltage control alone, the agent reduces the hours with voltage violations from 12.2\% to 1.2\% and those with line loadings above the operational limit of 80\% of the thermal rating from 45.9\% to 3.6\%, with limited demand-side and no supply-side flexibility. The results support coordination schemes between transmission and distribution system operators in which distributed flexibility absorbs the rebounds of large industrial activations, enabling broader industrial participation in balancing markets through dynamic, voluntary flexibility.
- 24 October 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA Safe Deep Reinforcement Learning Approach to Mitigating Demand Response Load Rebounds for TSOs
Industrial demand response is essential for grid stability amid increasing variable renewable energy penetration. However, explicit demand response adoption is hindered by post-activation demand spikes, known as load rebounds. This paper proposes a methodology for transmission system operators to manage load rebounds in high-voltage networks with limited supply-side flexibility. First, a rolling-horizon model combining mixed-integer linear and constraint programming schedules an energy-intensive steel plant under implicit and explicit demand response programmes and generates feasible flexibility offers for balancing markets. Second, the industrial model is embedded in a modified high-voltage CIGRE stress-test network to simulate load rebounds after flexibility activations. Finally, in a safe deep reinforcement learning approach, a recurrent Proximal Policy Optimisation agent dispatches distributed demand-side flexibility and the reactive power of static var compensators to manage the network and mitigate load rebounds. A safety projection verifies each action of the agent with a power flow and, when an operational limit is violated, corrects it with a quadratic program built on exact power flow sensitivities; when no safe action exists, the action of minimal measured violation is applied. Compared with local voltage control alone, the agent reduces the hours with voltage violations from 12.2\% to 1.2\% and those with line loadings above the operational limit of 80\% of the thermal rating from 45.9\% to 3.6\%, with limited demand-side and no supply-side flexibility. The results support coordination schemes between transmission and distribution system operators in which distributed flexibility absorbs the rebounds of large industrial activations, enabling broader industrial participation in balancing markets through dynamic, voluntary flexibility.
- 1 October 2026
- Published by Springer Nature
- p. 59-74
The System Reference Architecture of a Digital Platform for Energy and Production Management in Manufacturing
- 1 October 2026
- Published by Springer Nature
- p. 59-74
The System Reference Architecture of a Digital Platform for Energy and Production Management in Manufacturing
- Open Access
- 17 August 2026
- Published by Elsevier in SSRN Electronic Journal
Multi-day Q-learning architecture for the optimal battery management in energy communities
This paper proposes a Q-learning architecture for the optimal scheduling of a shared battery storage in energy communities, featuring an extended three-day optimization horizon. The study addresses the challenge of managing common storage system under heterogeneous conditions, where participants have distinct demand profiles and different electricity tariffs. The proposed methodology introduces a hybrid optimization framework that couples a Q-learning agent with an intra-day mathematical model scheduler. Operating on a three-day rolling window, the Q-learning agent learns to determine the optimal state of charge at the end of each day (SoC_H+24) to minimize electricity costs over multiple days, while the MILP model computes the optimal hourly battery strategy based on these strategic targets. The results demonstrate that the proposed architecture outperforms a conventional 24-hour scheduling by anticipating inter-day price fluctuations and energy trends. These findings validate the effectiveness of the hybrid approach in performing cross-day energy shifting, ultimately achieving superior long-term economic savings.
- 17 August 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessMulti-day Q-learning architecture for the optimal battery management in energy communities
This paper proposes a Q-learning architecture for the optimal scheduling of a shared battery storage in energy communities, featuring an extended three-day optimization horizon. The study addresses the challenge of managing common storage system under heterogeneous conditions, where participants have distinct demand profiles and different electricity tariffs. The proposed methodology introduces a hybrid optimization framework that couples a Q-learning agent with an intra-day mathematical model scheduler. Operating on a three-day rolling window, the Q-learning agent learns to determine the optimal state of charge at the end of each day (SoC_H+24) to minimize electricity costs over multiple days, while the MILP model computes the optimal hourly battery strategy based on these strategic targets. The results demonstrate that the proposed architecture outperforms a conventional 24-hour scheduling by anticipating inter-day price fluctuations and energy trends. These findings validate the effectiveness of the hybrid approach in performing cross-day energy shifting, ultimately achieving superior long-term economic savings.
- Open Access
- 9 April 2026
- Published by Elsevier in SSRN Electronic Journal
Two-stage Industrial Flexibility Framework: Internal Cooperative Optimization and External Flexibility Assessment
This paper proposes a two-stage framework for industrial cluster flexibility that separates day-ahead internal coordination from downstream balancing market assessment. In Step 1, a MILP based internal market optimization selects the combination of baseline and Alternative Production Plans (APPs) across industrial sites while coordinating shared PV and ESS resources to minimize cluster operating cost and emissions. In Step 2, the cluster wide schedule obtained in Step 1 is used as the basis for a deterministic external market assessment that checks which machine level flexibility can actually be delivered, determines when the aggregated response is large enough for mFRR participation, forms feasible shutdown sets, and estimates the corresponding revenue potential under market activation. The framework is evaluated on a synthetic industrial cluster derived by the FLEX4FACT project. Results show that cooperative internal scheduling creates substantial value, while the downstream Step 2 assessment identifies the bid-feasible flexibility that can be offered once machine-level constraints are enforced. The framework provides a practical and operationally grounded pathway for translating production constrained industrial flexibility into coordinated market participation, while highlighting the complementary roles of internal optimization and external market assessment in industrial flexibility aggregation.
- 9 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessTwo-stage Industrial Flexibility Framework: Internal Cooperative Optimization and External Flexibility Assessment
This paper proposes a two-stage framework for industrial cluster flexibility that separates day-ahead internal coordination from downstream balancing market assessment. In Step 1, a MILP based internal market optimization selects the combination of baseline and Alternative Production Plans (APPs) across industrial sites while coordinating shared PV and ESS resources to minimize cluster operating cost and emissions. In Step 2, the cluster wide schedule obtained in Step 1 is used as the basis for a deterministic external market assessment that checks which machine level flexibility can actually be delivered, determines when the aggregated response is large enough for mFRR participation, forms feasible shutdown sets, and estimates the corresponding revenue potential under market activation. The framework is evaluated on a synthetic industrial cluster derived by the FLEX4FACT project. Results show that cooperative internal scheduling creates substantial value, while the downstream Step 2 assessment identifies the bid-feasible flexibility that can be offered once machine-level constraints are enforced. The framework provides a practical and operationally grounded pathway for translating production constrained industrial flexibility into coordinated market participation, while highlighting the complementary roles of internal optimization and external market assessment in industrial flexibility aggregation.
- Open Access
- 30 January 2025
- Published by Elsevier in Applied Energy
- Vol. 384
Sustainable optimal production scheduling methodology under implicit demand response and carbon policy: A manufacturing industry case study
- 30 January 2025
- Published by Elsevier in Applied Energy
- Vol. 384
Open AccessSustainable optimal production scheduling methodology under implicit demand response and carbon policy: A manufacturing industry case study
- Top Cited PapersOpen Access
- 31 July 2024
- Published by Elsevier in Renewable and Sustainable Energy Reviews
- Vol. 203
A comprehensive overview of industrial demand response status in Europe
- 31 July 2024
- Published by Elsevier in Renewable and Sustainable Energy Reviews
- Vol. 203
Top Cited PapersOpen AccessA comprehensive overview of industrial demand response status in Europe
- 14 September 2023
- Published by Springer Nature
- p. 634-649
A Framework for Enabling Manufacturing Flexibility and Optimizing Industrial Demand Response Services
- 14 September 2023
- Published by Springer Nature
- p. 634-649
A Framework for Enabling Manufacturing Flexibility and Optimizing Industrial Demand Response Services
- Open Access
A meta-heuristic method to design off-grid community electrification projects with renewable energies
- Open Access
- 1 July 2015
- Published by Elsevier in Solar Energy
- Vol. 117, 268-281
Off-grid community electrification projects based on wind and solar energies: A case study in Nicaragua
- 1 July 2015
- Published by Elsevier in Solar Energy
- Vol. 117, 268-281
Open AccessOff-grid community electrification projects based on wind and solar energies: A case study in Nicaragua