Deep Learning approach for the Multilink Selection Problem in Avionic Networks

In the Aeronautical Telecommunication Network, the aircraft has equipped with different physical radio stations and has the capabilities to use different Air/Ground data link for communications between the airborne segment and the ground segment. The COMET system considers a heterogenous set of radio access technologies. Each datalink has its transmission characteristics regarding the differences in data rate capacity, transmission delay, packet loss rate and the money cost. Besides, different Aeronautical Communication services applications have different QoS requirements, security requirements, for example, critical and non-critical safety communication services. In different phases of flight, various A/G datalinks could be available at the same time. In this paper, a multi-attribute decision-making model has been proposed to solve the multilink selection problem in ATN environment. The Deep Learning approach for Multilink Selection (DL-MS) has been applied to reduce the running time, and at the same time, still guarantees the accuracy of the optimal link selection solution.