Martina Panfili

Optimal Planning and Routing in Medium Voltage PowerLine Communications Networks

This paper deals with the problem of deploying a PowerLine Communication (PLC) network over a medium voltage (MV) power grid. The PLC network is used to connect the end nodes (ENs) of the MV grid to the service provider by means of PLC network nodes enabled as access points. In particular, a network planning problem is faced wherein we require to define the PLC network topology by deciding which MV network nodes are to be enabled as access points. An optimization problem is then formulated, which minimizes the cost of enabling the access points and maximizes the reliability of PLC network paths in a multi-objective optimization fashion. This work also considers resiliency (i.e., it guarantees the PLC network connectivity even in case of link faults) and capacity constraints (i.e., it checks that there are enough resources to transmit the estimated amount of traffic over the PLC network paths). As a byproduct, the optimization algorithm also returns the optimal routing. Simulations based on realistic MV network topologies validate the proposed approach.

Resilient planning of PowerLine Communications networks over Medium Voltage distribution grids

In this paper a network planning problem aiming to enable underground Medium Voltage (MV) power grids to resilient PowerLine Communications (PLCs) is faced. The PLC network is used to connect PLC End Nodes (ENs) located into the secondary substations to the energy management system of the utility by means of PLC network nodes enabled as Access Points. An optimization problem is formulated, aiming to optimally allocate the Access Points to the substations and the repeaters to the MV feeders. A multi-objective optimization approach is used, in order to keep in balance the needs of minimizing the cost of equipment allocation and maximizing the reliability of PLC network paths. Resiliency and capacity constraints are properly modeled, in order to guarantee the communications even under faulted link conditions. As a byproduct, the optimization algorithm also returns the optimal routing. Simulations performed on a realistic underground MV distribution grid validate the proposed approach.

A Resource Allocation Algorithm of Multi-cloud Resources Based on Markov Decision Process

Cloud technologies can nowadays be considered as commodities. The possibility of getting access to storage, computing and networking virtual resources empowers any business that needs dynamic IT capabilities. The Cloud Management Broker (CMB) plays a crucial role to handle heterogeneous virtualized cloud resources in order to offer a unique set of interfaces to the cloud users. Moreover, the CMB is in charge of optimizing the usage of the cloud resources, satisfying the requirements declared by the users. This paper proposes a novel multi-cloud resource allocation algorithm, based on a Markov Decision Process (MDP), capable of dynamically assigning the resources requests to a set of IT resources (storage or computing resources), with the aim of maximizing the expected CMB revenue. Simulation results show the feasibility and the higher performances obtained by the proposed algorithm, compared to a greedy approach.

An approximate dynamic programming approach to resource management in multi-cloud scenarios

ABSTRACT The programmability and the virtualisation of network resources are crucial to deploy scalable Information and Communications Technology (ICT) services. The increasing demand of cloud services, mainly devoted to the storage and computing, requires a new functional element, the Cloud Management Broker (CMB), aimed at managing multiple cloud resources to meet the customers’ requirements and, simultaneously, to optimise their usage. This paper proposes a multi-cloud resource allocation algorithm that manages the resource requests with the aim of maximising the CMB revenue over time. The algorithm is based on Markov decision process modelling and relies on reinforcement learning techniques to find online an approximate solution.

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 Future Internet oriented user centric extended intelligent transportation system

Intelligent Transportation Systems (ITS) are changing the way people plan a journey and travel around the world. Advanced mobility information systems, as well as intelligent multimodal mobility services, may take considerable advantage of consolidated technologies from emerging ICT frameworks. In this paper we propose an Extended Intelligent Transportation System (ExITS) consisting of a basic ITS equipped with a User Centric Control System (UCCS). The proposed ExITS relies on service personalization methodologies and is conceived as a Future Internet (FI) oriented, closed-loop, user centric architecture integrating and controlling ITS services. The proposed UCCS considers the trip planning service and takes into account both explicit and implicit user preferences in selecting travel solutions satisfying a given user request. The aim of the UCCS is to drive the trip planning service in proposing to the user travel typologies tailored to personal preferences. Implicit preferences are automatically inducted by similarity based unsupervised machine learning techniques and verified by a closed-loop control mechanism triggered by explicit user feedback.

A lexicographic approach to constrained MDP admission control

This paper proposes a Reinforcement Learning-based lexicographic approach to the Call Admission Control (CAC) problem in communication networks. The CAC problem is modeled as a multi-constrained Markov Decision Problem (MDP). To overcome the problems of the standard approaches to the solution of constrained MDP, a multi-constraint lexicographic approach is defined, and an on-line implementation based on Reinforcement Learning techniques is proposed. Simulations validate the proposed approach.

A lexicographie approach to constrained MDP Admission Control

This paper proposes a Reinforcement Learning-based lexicographic approach to the Call Admission Control (CAC) problem in communication networks. The CAC problem is modeled as a multi-constrained Markov Decision Problem (MDP). To overcome the problems of the standard approaches to the solution of constrained MDP, a multi-constraint lexicographic approach is defined, and an on-line implementation based on Reinforcement Learning techniques is proposed. Simulations validate the proposed approach.