An Optimization Solution for Packet Scheduling: A Pipeline-Based Genetic Algorithm Accelerator

Abstract

Abstract. The dense wavelength division multiplexing (DWDM) technique has been developed to provide a tremendous number of wavelengths/channels in an optical fiber. In the multi-channel networks, it has been a challenge to effectively schedule a given number of wavelengths and variable-length packets into different wavelengths in order to achieve a maximal network throughput. This optimization process has been considered as difficult as the job scheduling in multiprocessor scenario, which is well known as a NP-hard problem. In current research, a heuristic method, genetic algorithms (GAs), is often employed to obtain the near-optimal solution because of its convergent property. Unfortunately, the convergent speed of conventional GAs cannot meet the speed requirement in high-speed networks. In this paper, we propose a novel hyper-generation GAs (HG-GA) concept to approach the fast convergence. By the HG-GA, a pipelined mechanism can be adopted to speed up the chromosome generating process. Due to the fast convergent property of HG-GA, which becomes possible to provide an efficient scheduler for switching variable-length packets in high-speed and multi-channel optical networks.

Computational intelligence in photonics technology and optical networks: A survey and future perspectives

“…When optical technology reaches a mature state and components like optical buffers or all-optical packet header recognition chips will become cost-effective solutions, then optical packet switching (OPS) will become a reality. We should expect then new design and optimization issues for packet switched networks, employing again heuristics and genetic algorithms [109], and following also similar methodologies as in the previously existed communications technology [89,108].…”

Design and implementation of subchannelization scheduler in IEEE 802.16 broadband wireless access systems

“…But currently there does not exist in the literature any technique specifically designed for searching and finding the best solution among all possible solutions. We will use the converging characteristic of the GA (Sheu et al, 2003) to solve the issue of finding the best solution among all possible solutions generated from all possible combinations of parameters in the FFTSS. By implementing this scheduling technique we will get better transmission efficiency in the FFT execution and consequently it will transmit all users' information in a minimum amount of time.…”

Application of Hardware Architecture of Genetic Algorithm for Optimal Packet Scheduling

“…In recently years, GA has become an important way to solve this problem. It is concluded that crossover and mutation of chromosome and fitness function calculation can converge faster and therefore allow an efficient way to find the approach optimal solution [3].…”