A Cross-Layer Adaptation Scheme for Improving IEEE 802.11e QoS by Learning

• Published in: IEEE transactions on neural networks Vol. 17; no. 6; pp. 1661 - 1665
• Main Authors: Chiapin Wang, Po-Chiang Lin, Lin, T.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.11.2006; Institute of Electrical and Electronics Engineers
• Subjects: Access control; Adaptation; Adaptive algorithm; Algorithms; Applied sciences; Artificial intelligence; Bit error rate; Channels; Computer Communication Networks; Computer science; control theory; systems; Computer simulation; Computer systems and distributed systems. User interface; Connectionism. Neural networks; Exact sciences and technology; IEEE 802.11e wireless local area networks (WLAN); Information Storage and Retrieval - methods; Information Storage and Retrieval - standards; Learning; Media Access Protocol; Multidimensional systems; Neural networks; Neural Networks (Computer); neural networks (NNs); On-line systems; Optimization; Pattern Recognition, Automated - methods; Physical layer; Quality Control; Quality of service; quality of service (QoS); Signal Processing, Computer-Assisted; Software; Standardization; Telecommunication traffic; Traffic control; United States; Wireless LAN; United States; Access control; Wireless LAN; neural networks (NNs); Adaptive algorithm; quality of service (QoS); IEEE 802.11e wireless local area networks (WLAN); Neural network; Service quality; Computer security; Optimization
• ISSN: 1045-9227; 1941-0093
• DOI: 10.1109/TNN.2006.883014

In this letter, we propose a cross-layer adaptation scheme which improves IEEE 802.11e quality of service (QoS) by online adapting multidimensional medium access control (MAC)-layer parameters depending on the application-layer QoS requirements and physical layer (PHY) channel conditions. Our solution is based on an optimization approach which utilizes neural networks (NNs) to learn the cross-layer function. Simulations results demonstrate the effectiveness of our adaptation scheme