A load balanced routing algorithm based on congestion prediction for LEO satellite networks

This paper presents a load balancing routing algorithm based on congestion prediction (LBRA-CP) so as to realize an efficient load balancing over the entire Low Earth Orbit satellite networks. A multi-objective optimization model is built, which not only adopts modifying factor to adjust path cost, but also uses congestion prediction to foresee inter-satellite link congestion. Then an ant colony algorithm is utilized to solve this model, resulting in finding an optimal path for every connection request. Meanwhile, in order to improve the reliability of LBRA-CP, the valve of the pheromone evaporation coefficient is discussed in this paper. The performance is measured by the receiver's throughput, the link utilization and the end-to-end delay. Simulation results show that LBRA-CP performs well in balancing traffic load and increases the receiver's throughput. Meanwhile, the end-to-end delay can meet the requirement of video transmission.