Method and device for heuristically learning routing protocol in wireless sensor network

Abstract

The invention discloses a method and device for heuristically learning a routing protocol in a wireless sensor network, and the method comprises the steps: carrying out the determination through a method for calculating a target Q value through a pre-constructed routing algorithm inspired by a distributed neural network corresponding to a first sensor node during the selection of a next-hop sensor node; according to the method, a two-layer learning structure is constructed, and discrete sensor nodes at the bottom layer interact with neighbor sensor nodes to carry out reinforcement learning; a distributed neural network is constructed at a high layer to enlighten underlying learning, so that a neural network fitting model is dynamically constructed in the autonomous learning process of each sensor node, the learning process of each sensor node is enlighted from a global perspective, the learning efficiency and learning precision of node learning are improved, and the learning efficiency of the sensor node is improved. The decision of each sensor node timely follows the change of a network topology structure, and the data packet transmission rate, the node survival ratio and the node energy standard deviation are improved.

Description

technical field [0001] The present application relates to the technical field of wireless sensors, and in particular, to a method and apparatus for heuristically learning routing protocols in wireless sensor networks. Background technique [0002] Wireless sensor networks have penetrated into all aspects of life, and have a wide range of applications in agriculture, industry, military, medical, transportation, fishing, drones and other fields. Wireless sensor networks consist of a large number of low-cost, low-power sensors, which are easy to deploy, and nodes transmit data through short-range wireless communication. The wireless sensor network continuously detects the environment and sends data packets to the base station in a single-hop or multi-hop manner. Since the sensor node is powered by a battery, its energy is limited. If it is too far from the base station, the sensor cannot directly send the data packet to the base station, but can only be relayed by other sensor...

AI Technical Summary

Problems solved by technology

The cluster head aggregates and forwards data packets. When the data packets it forwards are large and the data distance is very long, the power consumption of the cluster head will be very large, and the nodes will easily lose energy and die prematurely.

Images