Efficient Task Allocation with Communication Delay Based on Reciprocal Teams

This paper proposes a method to efficiently allocate tasks to appropriate agents by forming teams based on the reciprocity in distributed environments where communication delay is not ignorable. Recent applications on a variety of devices such as PCs, tablets, and smartphones run in different locations to provide location-oriented and time-constrained services. These services are usually realized by agents on these devices communicating with single or multiple service agents operating on servers that are also deployed at multiple points. Because timely response is a key factor for quality of services, communication delay is significant in these applications. Thus, we propose a method in which agents allocate tasks in such a widely distributed environment to reduce the delay of response to the requested tasks by extending our previous work. Then, we experimentally show that our method could improve the overall performance by identifying which agents have high-throughput of task execution from the local viewpoint.