1,720,983 research outputs found
Reinforcement Learning and Cooperative Receding Horizon approaches for the routing problem
No full textAn adaptive Cooperative Receding Horizon controller for the multivehicle routing problem
Full text linkThe objective of the Vehicle Routing Problem (VRP), in the meaning of this paper, is to find the best path for a vehicle, or the best paths for a fleet of vehicles, with the aim of visiting a set of targets.
Possible applications of the vehicle routing problem include surveillance, exploration, logistic, transportation, relief systems, etc. A lot of research has been carried out so far, but the VRP remains a complex and computationally expensive combinatorial problem, leading to the difficulty to actually solve the problem on-line. This paper presents a technique based on the Cooperative Receding Horizon (CRH) approach proposed in [Li06], in which a sequence of optimization problems are computed over a planning horizon and the decisions are applied only over a shorter action horizon, in order to rapidly adapt to possible configuration changes (e.g., new targets appearance). Moreover, the proposed algorithm is able to
dynamically adapt to the time-variable configuration of both vehicles and targets as well as to handle the discovery of unknown targets. Several proof of concept simulations show the enhancements of the proposed technique in comparison to the one in [Li06]
MQ-Routing: Mobility-, GPS- and energy-aware routing protocol in MANETs for disaster relief scenarios
No full textMobile-Ad-Hoc-Networks (MANETs) are self-configuring networks of mobile nodes, which communicate through wireless links. The main issues in MANETs include the mobility of the network nodes, the scarcity of computational, bandwidth and energy resources. Thus, MANET routing protocols should explicitly consider network changes and node changes into the algorithm design. MANETs are particularly suited to guarantee connectivity in disaster relief scenarios, which are often impaired by the absence of network infrastructures. Moreover, such scenarios entail strict requirements on the lifetime of the device batteries and on the reactivity to possibly frequent link failures. This work proposes a proactive routing protocol, named MQ-Routing, aimed at maximizing the minimum node lifetime and at rapidly adapting to network topology changes. The proposed protocol modifies the Q-Routing algorithm, developed via Reinforcement Learning (RL) techniques, by introducing: (i) new metrics, which account for the paths availability and the energy in the path nodes, and which are dynamically combined and adapted to the changing network topologies and resources; (ii) a fully proactive approach to assure the protocol usage and reactivity in mobile scenarios. Extensive simulations validate the effectiveness of the proposed protocol, through comparisons with both the standard Q-Routing and the Optimized Link State Routing (OLSR) protocols. © 2012 Elsevier B.V. All rights reserved
A distributed multi-path algorithm for wireless ad-hoc networks based on Wardrop routing
No full textWireless ad-hoc networks are collections of devices which are able to communicate each other through wireless links. Those networks differ from infrastructure-based wireless networks for the absence of a centralized coordinator which handles all the communications among the devices. This leads to higher probability of packets collision, congestion of links, etc. Moreover, wireless links are characterized by an intrinsic high and time varying packet loss ratio, due to external noise and interferences. The objective of this paper is to present a new distributed multi-path algorithm (i.e., traffic is split among multiple paths) for wireless ad-hoc networks with the aims of (i) increasing the throughput of the applications running onto the network (ii) explicitly accounting for the packet loss of the wireless links and (iii) guaranteeing that the routing process converges to stable paths. The algorithm is developed by using the concept of Wardrop equilibrium. Simulation results show the higher throughput achieved by the proposed routing algorithm, compared to shortest path routing protocols, based on hop count and on packet loss metrics. © 2013 IEEE
A distributed bandwidth allocation algorithm for bluetooth wireless networks based on Wardrop equilibrium
No full textIn the project DAAS, wireless communications in zone with explosive atmosphere (ATEX) are investigated. In particular, Bluetooth multi-hop networks, also called Bluetooth scatternets, are a clear candidate due to their low transmission power. The problem of bandwidth allocation in Bluetooth scatternets is dealt with in this paper: given the average traffic flows which the network has to transmit, the problem seeks an efficient capacity allocation which is feasible (i.e., it allows to transmit all the traffic flows). A distributed algorithm is developed, that converges to a Wardrop equilibrium such that, in the final capacity allocazione, the delays incurred by all traffic flows are the same. © 2015 Technical Committee on Control Theory, Chinese Association of Automation
A dynamic load balancing algorithm for Quality of Service and mobility management in next generation home networks
No full textHeterogeneity of connection technologies and nodes mobility open new challenges in home networks control strategies. Moreover, user's needs are changing towards applications requiring high transmission speeds such as 3D gaming, enhanced interactivity and high definition video. Each of those applications puts several constraints on the network capabilities to guarantee requirements on the Quality of Service. In this paper we introduce an innovative concept based on fast load balancing algorithm operating on top of a convergence layer, in order to rapidly react to network changes and contemporaneously to satisfy strict application demands. We formulated the load balancing problem as a Multi-Commodity Flow and resolved it with a column generation approach using Lagrangian Relaxation and Dijkstra algorithm. The load balancing problem computational complexity is decreased with respect to state of the art load balancing solutions based on linear programming techniques. Proof of concept simulation results are reported
Energy balancing in multi-hop Wireless Sensor Networks: An approach based on reinforcement learning
No full textWireless Sensor Networks (WSNs) are made of spatially distributed autonomous sensors, which cooperate to monitor a certain physical or environmental condition and pass their data through a network to a central data sink. A promising field of application of WSNs is planet exploration, in which a continuous monitoring of the surface is necessary, to have a clear notion of planet conditions and prepare for a future manned mission. The potentially large size of the region to be monitored and the line-of-sight limitations on remote planets (for instance the Moon, as studied in the SWIPE project [1]), impose constraints on the possibility to have 1-hop sensor-sink communication. Therefore, the sensors must be able to create and maintain a multi-hop ad hoc network, to allow sensed data to reach the sink. This paper extends the Q-Routing algorithm, designed for fixed and mobile networks, in order to be applicable in WSNs. The proposed routing algorithm aims at optimizing the network lifetime, by balancing the routing effort among the sensors, taking into account their current residual batteries, while minimizing the control overhead. Simulation results show an increase of performances, in grid-based networks, which are common topologies for WSNs. © 2014 IEEE
Convergence in Home Gigabit Networks: Implementation of the Inter-MAC Layer as a Pluggable Kernel Module
No full textMany new broadband, emerging applications such as high definition 3D video streaming or on-line gaming are going to be part of the future home. Current home networks are still not capable to cope with the tight requirements asked by these kind of applications. Moreover, many underlying wired and wireless transmission technologies are available, but no solution to reach a convergent framework is available. In this paper, we present a preliminary software implementation of a novel solution, called Inter-MAC, that realizes the convergence at MAC layer enabling a reliable and high performance delivery of application data and services. Our results show how it is possible to split flows onto different technologies when the overloading of a single link would cause unacceptable delay and packet loss results. This is done in a plug and play fashion: loading a kernel module in a running Linux machine
Load balancing strategy in heterogeneous meshed home access network
No full textToday???s homes are equipped with a multitude of devices using several communication technologies such as Ethernet, Wi-fi, Power Line Communications and Optical Wireless Communications forming a heterogeneous network environment. User???s needs are changing towards applications requiring high transmission speeds such as 3D gaming, enhanced interactivity, virtual reality, high definition video. Each of those applications puts several constraints on the capabilities of the network to guarantee requirements on the quality of service (QoS). This document proposes a novel solution for load balancing in multi-technology meshed networks in order to achieve QoS requirements for all applications running in the home environment. Formulating the problem as a Multi-Commodity Flow, resolving it with a column generation approach that uses Lagrangean Relaxation and Dijkstra algorithm, the effective computational complexity of the load balancing problem is decreased respect to a standard linear programming solution. Because of home gateway limited computational power and energy considerations, the linear programming solution is not feasible in home environment
A proactive link-failure resilient routing protocol for MANETs based on reinforcement learning
No full textMobile-Ad-Hoc-Networks (MANET) are self-configuring networks of mobile nodes, which communicate through wireless links. One of the main issues in MANETs is the mobility of the network nodes: routing protocols should explicitly consider network changes into the algorithm design. MANETs are particularly suited to guarantee connectivity in disaster relief scenarios, which are often impaired by the absence of network infrastructures. This work proposes a proactive routing protocol, developed via Reinforcement Learning (RL) techniques, to dynamically choose the most stable path, basing on GPS information, among the feasible ones and to consequently increase resiliency to link failures. Simulations show the effectiveness of the proposed protocol, through comparison with the Optimized Link State Routing (OLSR) protocol. © 2012 IEEE
- …
