Throughput maximization for energy efficient multi-node communications using actor-critic approach

We investigate the problem of average throughput maximization per total expended energy in packetized multinode wireless sensor communications. We consider a CDMA like multiple access scenario where multi transmitters are communicating with one receiving node. Since the transmitting nodes are typically distributed in different locations for wireless sensor applications, a good transmission strategy should be employed in each node to maximize throughput per unit energy in the node. We propose to use a distributed actor-critic algorithm to independently learn a good transmission strategy for each transmitting node. The resulting strategy adapts to the incoming traffic rate, buffer condition, and channel condition, which is influenced by both the location of the transmitting node and the other nodes' transmission strategy. Our proposed method achieves 1.5 to 6 times throughput per energy compared to the simple constant signal to interference ratio (CSIR) policy, particularly in high packet arrival. Moreover, the proposed algorithm is robust in tracking packet arrival rate variation.