Emanuele De Santis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Emanuele De Santis has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Alessandro Giuseppi
University of Rome “La Sapienza
8 shared publications - Alessandro Di Giorgio
University of Rome La Sapienza,DIAG Department,Rome,Italy
6 shared publications - Francesco Liberati
University of Rome La Sapienza,DIAG Department,Rome,Italy
6 shared publications - Francesco Delli Priscoli
Department of Computer, Control and Management Engineering, University of Rome La Sapienza, Rome, Italy
3 shared publications - Andrea Wrona
Sapienza University of Rome, Via Ariosto 25
2 shared publications Antonio Pietrabissa
Sapienza University of Rome and Space Research Group of CRAT Roma Italy
2 shared publications
Latest Publications
- Open Access
- 1 October 2026
- Published by KEAI Publishing in Journal of Automation and Intelligence
Post-fault user-cell association in 5G wireless networks via federated dueling double deep Q-networks
- 1 October 2026
- Published by KEAI Publishing in Journal of Automation and Intelligence
Open AccessPost-fault user-cell association in 5G wireless networks via federated dueling double deep Q-networks
- Open Access
- 1 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control Systems Technology
- Vol. 34 (3) , 1133-1148
Adaptive Estimation of Pennes’ Bio-Heat Equation: Observer Design and PINNs-Based Implementation
This article presents a multiple-model (MM) adaptive framework for state estimation of uncertain parabolic reaction-diffusion partial differential equations, with specific application to superficial oncological hyperthermia (HT). The effectiveness of such thermal processes critically depends on real-time temperature assessment—a significant difficulty when relying on intrinsically sparse thermometry. This challenge is further compounded by uncertainties in patient-specific properties, particularly blood perfusion rate, during tissue heating. The problem is formulated as a state estimation of the governing Pennes’ bio-heat equation (PBHE), developing an MM adaptive estimation framework capable of dealing with uncertain parameters in the process dynamics and using only noninvasive boundary measurements. The validation process revealed limitations in traditional numerical simulation methods, prompting a novel implementation leveraging physics-informed learning—an approach well-suited for scenarios with known governing equations but limited training data. The experimental validation using a muscle-equivalent phantom with controlled perfusion simulation provides evidence of the method’s effectiveness in realistic conditions. This is the first demonstration of adaptive estimation of parabolic partial differential equations (PDEs) based on physiscs informed learning methods. The proposed methodology offers three key advantages: elimination of domain discretization requirements, thereby enabling continuous spatiotemporal monitoring; real-time estimation capabilities for PDE solutions; scalability to higher dimensional input spaces for an increased adaptability.
- 1 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control Systems Technology
- Vol. 34 (3) , 1133-1148
Open AccessAdaptive Estimation of Pennes’ Bio-Heat Equation: Observer Design and PINNs-Based Implementation
This article presents a multiple-model (MM) adaptive framework for state estimation of uncertain parabolic reaction-diffusion partial differential equations, with specific application to superficial oncological hyperthermia (HT). The effectiveness of such thermal processes critically depends on real-time temperature assessment—a significant difficulty when relying on intrinsically sparse thermometry. This challenge is further compounded by uncertainties in patient-specific properties, particularly blood perfusion rate, during tissue heating. The problem is formulated as a state estimation of the governing Pennes’ bio-heat equation (PBHE), developing an MM adaptive estimation framework capable of dealing with uncertain parameters in the process dynamics and using only noninvasive boundary measurements. The validation process revealed limitations in traditional numerical simulation methods, prompting a novel implementation leveraging physics-informed learning—an approach well-suited for scenarios with known governing equations but limited training data. The experimental validation using a muscle-equivalent phantom with controlled perfusion simulation provides evidence of the method’s effectiveness in realistic conditions. This is the first demonstration of adaptive estimation of parabolic partial differential equations (PDEs) based on physiscs informed learning methods. The proposed methodology offers three key advantages: elimination of domain discretization requirements, thereby enabling continuous spatiotemporal monitoring; real-time estimation capabilities for PDE solutions; scalability to higher dimensional input spaces for an increased adaptability.
- Open Access
- 13 March 2026
- Published by Elsevier in Sustainable Energy, Grids and Networks
- Vol. 46
On the participation of electric vehicle aggregates in the ancillary services market according to the ARERA resolution 300/17
- 13 March 2026
- Published by Elsevier in Sustainable Energy, Grids and Networks
- Vol. 46
Open AccessOn the participation of electric vehicle aggregates in the ancillary services market according to the ARERA resolution 300/17
- Open Access
- 9 September 2025
- Published by Elsevier in Sustainable Energy, Grids and Networks
A hybrid model predictive control-deep reinforcement learning algorithm with application to plug-in electric vehicles smart charging
- 9 September 2025
- Published by Elsevier in Sustainable Energy, Grids and Networks
Open AccessA hybrid model predictive control-deep reinforcement learning algorithm with application to plug-in electric vehicles smart charging
- 4 March 2025
- Published by Springer Nature
- p. 84-95
A Cooperative Feature Removal Mechanism for Cell Outage Detection in Wireless Telecommunication Networks
- 4 March 2025
- Published by Springer Nature
- p. 84-95
A Cooperative Feature Removal Mechanism for Cell Outage Detection in Wireless Telecommunication Networks
- 4 March 2025
- Published by Springer Nature
- p. 289-305
AdaLightLog: Enhancing Application Logs Anomaly Detection via Adaptive Federating Learning
- 4 March 2025
- Published by Springer Nature
- p. 289-305
AdaLightLog: Enhancing Application Logs Anomaly Detection via Adaptive Federating Learning
- 17 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Impact of Reservation on the Performance of Optimal Control in Electric Vehicles Fast Charging Stations
Service stations equipped with multiple delivery points for plug-in electric vehicles fast charging are expected to gradually replace petrol-based service stations. Operators interested in managing the new stations are going to face key challenges in terms of sizing the station's point of connection to the grid so as to render the provision of the service economically viable. As connection fees depend on the plant nominal power, sustainability is expected to come from the integration in the area of local generation from renewable energy sources and an electric energy storage device. This paper presents an approach based on optimal control methodology for regulating the energy flows at the point of connection of a service station with the grid. The control goal is to optimally balance the Plug-in Electric Vehicle (PEV) recharging power through the Energy Storage System (ESS), while also taking into account an uncertain number of charging requests and local generation. The overall objective is to lower as much as possible the power flowing at the point of connection with the grid, while providing as much as possible maximum power to the single PEVs. A model predictive control (MPC) algorithm is proposed to control the ESS. The single MPC iteration is based on continuous time optimal control. The core contribution of this paper is in the study of the impact of the level of uncertainty of the charging power (i.e., the number of charging requests by the PEV owners) on the performance of the controller. Simulation results show that reservations of the charging service represent a key aspect to take into account for taking decisions on the size of service station point of connection, even with the aforementioned control architecture.
- 17 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Impact of Reservation on the Performance of Optimal Control in Electric Vehicles Fast Charging Stations
Service stations equipped with multiple delivery points for plug-in electric vehicles fast charging are expected to gradually replace petrol-based service stations. Operators interested in managing the new stations are going to face key challenges in terms of sizing the station's point of connection to the grid so as to render the provision of the service economically viable. As connection fees depend on the plant nominal power, sustainability is expected to come from the integration in the area of local generation from renewable energy sources and an electric energy storage device. This paper presents an approach based on optimal control methodology for regulating the energy flows at the point of connection of a service station with the grid. The control goal is to optimally balance the Plug-in Electric Vehicle (PEV) recharging power through the Energy Storage System (ESS), while also taking into account an uncertain number of charging requests and local generation. The overall objective is to lower as much as possible the power flowing at the point of connection with the grid, while providing as much as possible maximum power to the single PEVs. A model predictive control (MPC) algorithm is proposed to control the ESS. The single MPC iteration is based on continuous time optimal control. The core contribution of this paper is in the study of the impact of the level of uncertainty of the charging power (i.e., the number of charging requests by the PEV owners) on the performance of the controller. Simulation results show that reservations of the charging service represent a key aspect to take into account for taking decisions on the size of service station point of connection, even with the aforementioned control architecture.
- Open Access
Electric Vehicle Fast Charging: A Congestion-Dependent Stochastic Model Predictive Control under Uncertain Reference
This paper presents a control strategy aimed at efficiently operating a service area equipped with stations for plug-in electric vehicles’ fast charging, renewable energy sources, and an electric energy storage unit. The control requirements here considered are in line with the perspective of a service area operator, who aims at avoiding peaks in the power flow at the point of connection with the distribution grid, while providing the charging service in the minimum time. Key aspects of the work include the management of uncertainty in the charging power demand and generation, the design of congestion and state-dependent weights for the cost function, and the comparison of control performances in two different hardware configurations of the plant, namely BUS and UPS connection schemes. All of the above leads to the design of a stochastic model predictive controller aimed at tracking an uncertain power reference, under the effect of an uncertain disturbance affecting the output and the state of the plant in the BUS and UPS schemes respectively. Simulation results show the relevance of the proposed control strategy, according to an incremental validation plan focused on the tracking of selected references, the mitigation of congestion, the stability of storage operation over time, and the mitigation of the effect of uncertainty.
Open AccessElectric Vehicle Fast Charging: A Congestion-Dependent Stochastic Model Predictive Control under Uncertain Reference
This paper presents a control strategy aimed at efficiently operating a service area equipped with stations for plug-in electric vehicles’ fast charging, renewable energy sources, and an electric energy storage unit. The control requirements here considered are in line with the perspective of a service area operator, who aims at avoiding peaks in the power flow at the point of connection with the distribution grid, while providing the charging service in the minimum time. Key aspects of the work include the management of uncertainty in the charging power demand and generation, the design of congestion and state-dependent weights for the cost function, and the comparison of control performances in two different hardware configurations of the plant, namely BUS and UPS connection schemes. All of the above leads to the design of a stochastic model predictive controller aimed at tracking an uncertain power reference, under the effect of an uncertain disturbance affecting the output and the state of the plant in the BUS and UPS schemes respectively. Simulation results show the relevance of the proposed control strategy, according to an incremental validation plan focused on the tracking of selected references, the mitigation of congestion, the stability of storage operation over time, and the mitigation of the effect of uncertainty.
- 5 April 2022
- Published by Springer Nature in Machine Intelligence Research
- Vol. 19 (2) , 127-137
Satellite Integration into 5G: Deep Reinforcement Learning for Network Selection
- 5 April 2022
- Published by Springer Nature in Machine Intelligence Research
- Vol. 19 (2) , 127-137
Satellite Integration into 5G: Deep Reinforcement Learning for Network Selection
- Open Access
Optimal Control of Plug-In Electric Vehicles Charging for Composition of Frequency Regulation Services
This paper presents a novel control system for the participation of plug-in electric vehicles (PEVs) in the provisioning of ancillary services for frequency regulation, in a way that is transparent to the driver and harmonized with the smart charging service requirements. Given a power-frequency droop curve, which specifies how the set of PEVs collectively participate to the provisioning of the frequency regulation service (we call this curve a “global” droop curve), we propose an algorithm to compute “local” droop curves (one for each PEV), which are optimized according to the current status of the PEV and the current progress of the smart recharging session. Once aggregated, the local droop curves match the global one (so that the PEVs contribute as expected to the provisioning of the ancillary service). One innovative aspect of the proposed algorithm is that it is specifically designed to be interoperable with the algorithms that control the PEV recharging process; hence, it is transparent to the PEV drivers. Simulation results are presented to validate the proposed solution.
Open AccessOptimal Control of Plug-In Electric Vehicles Charging for Composition of Frequency Regulation Services
This paper presents a novel control system for the participation of plug-in electric vehicles (PEVs) in the provisioning of ancillary services for frequency regulation, in a way that is transparent to the driver and harmonized with the smart charging service requirements. Given a power-frequency droop curve, which specifies how the set of PEVs collectively participate to the provisioning of the frequency regulation service (we call this curve a “global” droop curve), we propose an algorithm to compute “local” droop curves (one for each PEV), which are optimized according to the current status of the PEV and the current progress of the smart recharging session. Once aggregated, the local droop curves match the global one (so that the PEVs contribute as expected to the provisioning of the ancillary service). One innovative aspect of the proposed algorithm is that it is specifically designed to be interoperable with the algorithms that control the PEV recharging process; hence, it is transparent to the PEV drivers. Simulation results are presented to validate the proposed solution.