Affiliation:
1. Islamic Azad University of Najafabad
Abstract
Abstract
Wireless mesh networks are appropriate and cost-effective infrastructure for Internet but due to the limited scalability and capacity, a lot of research has been doing on new ways to improve these limitations such as optimization of scheduling, routing, etc. In this paper focusing on time division multiple access (TDMA) method, a new algorithm for link scheduling in mesh networks based on Deep Learning is proposed which reduces the possibility of collision to zero by scheduling links. In this algorithm, we will try to size super frames and assign each link to a time slot in such a way that limitations are satisfied and finally, the end-to-end latency is minimized. Our results show that the proposed algorithm can schedule links with shorter super frames compared to other recent algorithms.
Publisher
Research Square Platform LLC
Reference21 articles.
1. Graph embedding-based wireless link scheduling with few training samples;Yu MG;IEEE Trans. on Wireless Communications
2. Dorigo, M., Birattari, M.: T.Stutzle, “Ant colony optimization”, IEEE computational intelligence magazine, vol. 1, no. 4, pp. 28–39, Nov. : (2006). (doi 10.1109/MCI.2006.329691)
3. Cappanera, P., Lenzini, L., Lori, A., Stea, G., Vaglini, G.: “ Link scheduling with end-to-end delay constraints in wireless mesh networks”, in 10th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM), pp. 1–9, Kos Island, Greece, June 2009 (doi: 10.1109/WOWMOM.2009.5282472)
4. Wabg, L.: “Link scheduling in multi-transmit-receive wireless mesh networks”, PhD Thesis, University of Wollongong, July (2015)
5. Shepard, C., Yu, H., Zhong, L.: “ArgosV2: a flexible many-antenna research platform”, in Proceedings of the 19th annual international conference on Mobile computing and networking (MOBICOM), Miami, USA, Sept. pp. 163–166 (doi: (2013). 10.1145/2500423.2505302)