Lorenzo Ricciardi Celsi

A Q-Learning based approach to Quality of Experience control in cognitive Future Internet networks

The paper describes an innovative and fully cognitive approach which offers the opportunity to cope with some key limitations of the present telecommunication networks by means of the introduction of a novel architecture design in the perspective of the emerging Future Internet framework. Within this architecture, the Quality of Experience (QoE) Management functionalities are aimed at approaching the desired QoE level of the applications by dynamically selecting the most appropriate Class of Service supported by the network. In the present work, this selection is driven by an optimal and adaptive control strategy based on the renowned Q-Learning algorithm. The proposed dynamic approach differs from the traffic classification approaches found in the literature, where a static assignment of Classes of Service to applications is performed.

A distributed load balancing algorithm for the control plane in software defined networking

The increasing demand of bandwidth, low latency and reliability, even in mobile scenarios, has pushed the evolution of the networking technologies in order to satisfy the requirements of innovative services. In this context, Software Defined Networking (SDN), namely a new networking paradigm that proposes the decoupling of the control plane from the forwarding plane, enables network control centralization and automation of the network management. In order to address the performance issues related to the SDN Control Plane, this paper proposes a distributed load balancing algorithm with the aim of dynamically balancing the control traffic across a cluster of SDN Controllers, thus minimizing the latency and increasing the overall cluster throughput. The algorithm is based on game theory and converges to a specific equilibrium known as Wardrop equilibrium. Numerical simulations show that the proposed algorithm outperforms a standard static configuration approach.

On the control of energy storage systems for electric vehicles fast charging in service areas

This paper presents a real time control strategy for energy storage systems integration in electric vehicles fast charging applications combined with generation from intermittent renewable energy sources. A two steps approach taking advantage of the model predictive control methodology is designed on purpose to optimally allocate the reference charging power while managing the priority among the plugged vehicles and then control the storage for efficiently sustaining the charging process. Two different use cases are considered: in the former the charging area is disconnected from the grid, so that the objective is to minimize the deviation of electric vehicles charging power from the nominal value; in the latter the focus is on the point of connection to the grid and the need of mitigating the related power flow. In both cases the fundamental requirement for feasible control system operation is to guarantee stability of the storages state of charge over the time. Simulation results are provided and discussed in detail, showing the effectiveness of the proposed approach.

A distributed wardrop control algorithm for load balancing in smart grids

This paper presents a distributed strategy for load balancing in a smart grid, modeling demand and supply as a networked dynamical system. The algorithm, which is characterized by point-to-point communications among agents implemented at the level of local energy management systems, is proven to converge to a Wardrop equilibrium. Numerical simulations of realistic scenarios are reported to show the effectiveness of the proposed approach.

On the optimization of energy storage system placement for protecting power transmission grids against dynamic load altering attacks

In this paper a power system protection scheme based on energy storage system placement against closed-loop dynamic load altering attacks is proposed. The protection design consists in formulating a non-convex optimization problem, subject to a Lyapunov stability constraint and solved using a two-step iterative procedure. Simulation results confirm the effectiveness of the approach and the potential relevance of using energy storage systems in support of primary frequency regulation services.