Takao Yamaguchi

Proposal of a Reaction-Diffusion based Congestion Control Method for Wireless Mesh Networks

This paper proposes a congestion control method for a wireless mesh network. Each intermediate node has separate transmission buffers for each of next hop nodes. By following the mathematical reaction-diffusion formulation, an intermediate node simultaneously performs local optimization control that balances buffer occupancy among its transmission buffers and global optimization control that suppresses the variation in occupancy between intermediate nodes along the path. As a result, packets are distributed over the whole path and further a network and buffer overflow is prevented. The results of our simulation show that the proposed method can provide better communication quality under loaded condition.

Memory Aware Dynamic Load Balancing for Networks-on-Chip

Shared memory systems typically suffer from transmission load concentration on memories and routers. In this paper, we propose the method that resolves the load concentration problem and improves the memory access performance. This is achieved by distinguishing between the destination memories, balancing transmission load of memories and routers dynamically assuming shared memory system that has multiple memories. Hardware mounting evaluation reveal the proposed method improves the issue of transmission load concentration on shared memory system. In the 16 processing core, 4 memory system model, throughput was improved three times over conventional method, without significantly increasing the mounting footprint.