Industrial Wireless Sensor Networks usually have a centralized management approach, where a device known as Network Manager is responsible for the overall configuration, definition of routes, and allocation of communication resources. Graph routing is used to increase the reliability of the communications through path redundancy. Some of the state-ofthe-art graph routing algorithms use weighted cost equations to define preferences on how the routes are constructed. The characteristics and requirements of these networks complicate to find a proper set of weight values to enhance network performance. Reinforcement Learning can be useful to adjust these weights according to the current operating conditions of the network. We present the Q-Learning Reliable Routing with a Weighting Agent approach, where an agent adjusts the weights of a state-of-the-art graph routing algorithm. The states of the agent represent sets of weights, and the actions change the weights during network operation. Rewards are given to the agent when the average network latency decreases or the expected network lifetime increases. Simulations were conducted on a WirelessHART simulator considering industrial monitoring applications with random topologies. Results show, in most cases, a reduction of the average network latency while the expected network lifetime and the communication reliability are at least as good as what is obtained by the state-of-the-art graph routing algorithms.

No abstract

No abstract

No abstract

No abstract