In this paper, we develop locally optimized scheduling and power control algorithms for multi-hop wireless networks under SINR interference models. Our scheme can be implemented in a fully distributed manner and requires only that each node solve a simple local optimization problem. Since, in our algorithms, each node operates independently of other nodes, it needs to predict the behavior of neighboring nodes when carrying out its local optimization. For such prediction, our proposed algorithms exploit the past records of neighboring nodes' scheduling and power control decisions. Through simulations, we show that our algorithms significantly outperform the state-of-the-art.
展开▼