1-1hit |
Node placement optimization in ShuffleNets is a combinatorial optimization problem. In this paper, a new heuristic node placement algorithm, called Lookahead Algorithm, is proposed. Its performance is compared with the lower bounds derived in [1], as well as some existing algorithms in the literature. Significant reduction in weighted mean hop distance hd is obtained, especially when the traffic distribution in ShuffleNets is highly skewed. Consider a ShuffleNet with 8 nodes, the hd obtained using Lookahead Algorithm is only 1.90% above the lower bound under the skewed traffic distribution (with traffic skew factor γ = 100), and 16.04% under uniform random traffic distribution.