MQ-Routing: Mobility-, GPS- and energy-aware routing protocol in MANETs for disaster relief scenarios

Survey on Simulation for Mobile Ad-Hoc Communication for Disaster Scenarios

“…Macone et al [60] OLSR, MQ-Routing and Q-Routing and Dynamic Source Routing (DSR) [68] under a disaster scenario. Reactive protocols find routes using broadcast requests and unicasts for replies.…”

“…Macone et al [60] proposed MQ-Routing, a proactive protocol that aims at maximizing the minimum node lifetime. It considers the node's availability and energy to proactively build paths and uses the Q-Routing protocol as a baseline, which applies reinforcement learning to the shortest-path routing problem in a fixed topology.…”

Optimal planning of sensor networks for asset tracking in hospital environments

“…For each asset, the path discovery problem is formulated as a Reinforcement Learning (RL) task [18]. Considering an agent taking decisions in a statistical environment, RL is a methodology, widely used in the literature for routing problems (e.g., [12]) which computes the agent's optimal policy based on the observation of the environment after a decision is taken. In brief, the RL task is organized in stages t ∈ [1,2,…,T], where T can also be infinite, and requires the definition of a finite state space S, a finite set A(s) of actions a which can be chosen in state s, a reward function r which maps each state to a real number.…”

A distributed multi-path algorithm for wireless ad-hoc networks based on Wardrop routing

“…Three main classes of routing algorithms have been and are currently studied: proactive, reactive and hybrid algorithms. Proactive algorithms set up in advance all source-destination paths within the network, regardless the necessity of forwarding a data traffic flow to a specific destination node (e.g., [1], [16] and [17]). In reactive algorithms, source-destination paths are calculated on-demand, as soon as a data traffic flow needs to be transmitted (e.g., [2], [18]).…”