Genetic Machine Learning algorithms in the optimization of communication efficiency in Wireless Sensor Networks

Towards a transmission power self-optimization in reliable Wireless Sensor Networks

“…In this particular work, the master node only fuses data that arrived within the same session. Thus, the number of required messages, the round time (RT) and the session time (ST) parameters are sent by the master node at the beginning of each session, forming the so called checkpoint [1]. Moreover, the master node computes the performance metrics during the checkpoint round in order to adjust the WSN.…”

“…Hereby, it will be necessary to also adopt the QoF metric to still guarantee the general QoS. Thus, QoF is the average number of received messages by the master node during the ST [1].…”

“…The round concept is used to synchronize nodes, and it also represents the periodicity of the data fusion task [1].…”

“…In dense networks, they are used in order to increase the sensor's reading dependability, to achieve a more accurate estimation of monitored environment and finally to assure longer network lifetime [1]. In these approaches, sensed scalars are sent to base stations that fuse the data with the objective to extract useful information from a set of readings.…”

“…Nowadays, WSNs have been increasingly deployed for both civil and military applications typically working in harsh environments. Considering sensor nodes, resources like processor, memory and battery are generally restricted, since their replacement is considered prohibitive due to hazardous and inaccessible places where they are supposed to operate [1]. In this context, fault tolerance or WSN's Efficiency (Ef), and power optimization to prolong the network's lifetime have become very important issues [7].…”