Performance Improvement in Satellite Networks Based on Markovian Weather Prediction

Abstract

Prediction of channel characteristics can be of immense value in improving the quality of signals in high frequency satellite systems. Making prediction of rainfall rate (RR) using Markov theory and using that prediction in an intelligent system (IS) to maintain the quality of service (QoS) in channels impacted by attenuation due to weather is the object of this paper. The paper describes the method of prediction rainfall rate (RRp) using weather collected by environment agencies and applying the predictions to gateway and ground terminal for optimal control of channel characteristics. This novel method of predicting weather characteristics using Markov theory supplies valuable data to develop an enhanced back propagation-learning algorithm to iteratively tune the IS to adapt to changing weather conditions. The effectiveness of the algorithm was tested on a simulated model for activating the weighted modulation and codepoint control. It demonstrated marked improvements in channel parameter tuning and signal quality.

Performance Evolution in Satellite Communication Networks Along with Markovian Channel Prediction

“…These combinations present a specialmodule of weather predict ion of different weights assigned toeach transition probability matrix along with Markov Chain oforder φ, where φ is fin ite and equal to 2 in our case. Thus,the prediction of the future state is dependent on the present,previous, and previous to previous states and is independent of the other earlier states [8].…”

“…The approach in grouping total rain conditions into classifiedblocks has been depicted in Figure 1. This classificationin actual data provides the basis for the data required to applyMarkovian theory in the prediction of rainfall rate [8]. To make the classificat ion of rainfall rate to better reflectlocal statistical weather patterns, two parameters can be adjusted:…”

“…A r (θ, RRpr): rain attenuation, as estimated in (15 Given these four attenuations, the total weather attenuationA W (θ,RR pr ), can be calculated fro m [5], [8], and [13]:…”

“…Algorithm for predicting the RR based onMarkov theory with fixed-duration weather data was written. Also, the IWACS used heuristic algorith ms that emp loyedfield inputs in problem solving, learning and discovery.The system adhered to formalized knowledge represent ations chemes practiced in the industry, and mach ine learning techniques,to reach optimal decisionin dealing with d ifferent atmosphericconditions [5], [8], [16], [42 ], and [43].The key feature of the IWACS is that it adjusts to signalvariations with a fast response time. In acco mplishing this, theemployed technique used feedback of SNR values fro m thereceiv ing end of the channel and uses that knowledge to mit igatefuture weather attenuations, thus preventing them fro mactually manifest in the channels.…”

“…These high frequencyoperations have enabled a wide variety of available and potentialapplicat ions and services including communicat ions, navigation,tele-med icine, remote sensing, distributed sensors networks,and wireless access to the internet. However, h igh frequencyoperations are prone to excessive digital transmissionerrors due to atmospheric attenuations [1]- [8].…”