MTCP:A Novel Solution to Improve TCP Over Wireless Networks
Publish place: چهارمین کنفرانس بین المللی علوم و مهندسی
Publish Year: 1395
نوع سند: مقاله کنفرانسی
زبان: English
View: 428
This Paper With 18 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ICESCON04_181
تاریخ نمایه سازی: 25 آذر 1395
Abstract:
TCP is a popular transport protocol used in present day internet. When packet losses occurs, TCP assumes that packet losses are due to congestion, and responds by reducing its congestion window. When a TCP connection traverses, a wireless link, a significant fraction of packet losses may occur due transmission errors. TCP responds to such losses also by reducing congestion window. This results in significant degradation in TCP performance.We design a protocol named MTCP, which is used by a TCP sender to guess the actual cause of packet loss (congestion or transmission loss) and take appropriate actions. This congestion avoidance technique evaluates the round-trip times and throughput gradient to predict cause of losses and sets congestion window appropriately. This solution also 1) modifies multiplicative decrease algorithm to TCP Reno-the most widely deployed TCP version in practice-by adjusting the slow start threshold according to perceived network congestion level rather than a fixed drop factor and 2) it modifies the linear increase algorithm so that connection can stay longer in the phase and achieve more throughput. Based on NS (Network Simulation) studies, we show that MTCP achieve significant throughput. We define 17 scenarios and achieve throughput improvement up to 85%. A designated feature of MTCP is that it only modifies TCP sender without changing receiver side protocol stack and is a proactive rather than reactive to detect loss.
Keywords:
Modified transmission control protocol (MTCP) , round-trip time (RTT) , congestion window (CWND) , congestion loss
Authors
Mohammad Etemad
South Pars Gas Complex, Assaluyeh, IRAN
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :