Research on Data Link Channel Decoding Optimization Scheme for Drone Power Inspection Scenarios

With the rapid development of smart grids, the deployment number of transmission lines has significantly increased, posing significant challenges to the detection and maintenance of power facilities. Unmanned aerial vehicles (UAVs) have become a common means of power inspection. In the context of drone power inspection, drone clusters are used as relays for long-distance communication to expand the communication range and achieve data transmission between patrol drones and base stations. Most of the communication occurs in the air-to-air channel between UAVs, which requires high reliability of communication between drone relays. Therefore, the main focus of this paper is on decoding schemes for drone air-to-air channels. Given the limited computing resources and battery capacity of a drone, as well as the large amount of power data that needs to be transmitted between drone relays, this paper aims to design a high-accuracy and low-complexity decoder for LDPC long-code decoding. We propose a novel shared-parameter neural-network-normalized minimum sum decoding algorithm based on codebook quantization, applying deep learning to traditional LDPC decoding methods. In order to achieve high decoding performance while reducing complexity, this scheme utilizes codebook-based weight quantization and parameter sharing methods to improve the neural-network-normalized minimum sum (NNMS) decoding algorithm. Simulation experimental results show that the proposed method has a better BER performance and low computational complexity. Therefore, the LDPC decoding algorithm designed effectively meets the drone characteristics and the high channel decoding performance requirements. This ensures efficient and reliable data transmission on the data link between drone relays.