Cognitive Call Admission Control for VoIP over IEEE 802.11 Using Bayesian Networks

Abstract

Abstract-In this paper we address the problem of provisioning Quality of Service (QoS) to Voice over IP applications in a Wireless LAN scenario based on the IEEE 802.11 standard. We propose the use of a Cognitive Network approach to design a Call Admission Control (CAC) scheme, according to which each user stores relevant information on its past network experience and then uses such information to build a Bayesian Network (BN), a probabilistic graphical model to describe the statistical relationships among network parameters. The BN is exploited to predict the voice call quality, as a function of the Link Layer conditions in the particular scenario considered. Such prediction on the present and future values of the QoS provided is directly exploited to design the cognitive CAC scheme, which is shown to significantly outperform state of the art CAC techniques in a realistic scenario.

A comprehensive survey on machine learning for networking: evolution, applications and research opportunities

“…As shown in Table 14, Admission control has leveraged ML extensively in a variety of networks, including ATM networks [95,189,190], wireless networks [8,36,359], cellular networks [66,67,281,372,458], ad hoc networks [452], and next generation networks [311]. To the best of our knowledge, Hiramatsu [189] was the first to propose NN based solutions controlling the admission of a service requesting resources for a basic call setup in ATM networks.…”

“…However, a potential disadvantage of NN based systems is that the confidence of the predicted output is unknown. As a remedy, a BN can predict the probability distribution of certain network variables for better performance in admission control [67,372]. Specifically, Bojovic et al [67] compare NN and BN models by applying them for admission control of calls in LTE networks.…”

“…Similarly, Quer et al [372] develop an admission control mechanism for VoIP calls in a WLAN. They employ BN to predict the voice call quality as a function of link layer conditions in the network, including the fraction of channel time occupied by voice and background best effort traffic, estimated frame error probabilities of voice and background traffic, and R-factor representing the posteriori performance.…”

Call admission control for wireless mesh network based on power interference modeling using directional antenna

“…The works by Baldo et al [18], and Yasukawa et al [15], including several other recent works [10,13,14,16,19,24,25], have modeled CAC based on measurements. This requires continuous monitoring of the network and execution of real time complex algorithms to support requests from users.…”

“…The IEEE 802.11 DCF MAC protocol enables nodes to have fair access to the wireless medium, which may prevent the WMN to support the QoS requirements of the services the network cater in particular in the case of medium congestion [16]. A CAC may play a relevant role here to provide QoS by preventing new flows that may keep entering the network even beyond the network's capacity.…”