Adaptive allocation of resources and call admission control for wireless ATM using genetic algorithms

In wireless ATM-based networks, admission control is required to reserve resources in advance for calls requiring guaranteed services. In the case of a multimedia call, each of its substreams (i.e., video, audio, and data) has its own distinct quality of service (QoS) requirements (e.g., cell loss rate, delay, jitter, etc.). The network attempts to deliver the required QoS by allocating an appropriate amount of resources (e.g., bandwidth, buffers). The negotiated QoS requirements constitute a certain QoS level that remains fixed during the call (static allocation approach). Accordingly, the corresponding allocated resources also remain unchanged. We present and analyze an adaptive allocation of resources algorithm based on genetic algorithms. In contrast to the static approach, each substream declares a preset range of acceptable QoS levels (e.g., high, medium, low) instead of just a single one. As the availability of resources in the wireless network varies, the algorithm selects the best possible QoS level that each substream can obtain. In case of congestion, the algorithm attempts to free up some resources by degrading the QoS levels of the existing calls to lesser ones. This is done, however, under the constraint of achieving maximum utilization of the resources while simultaneously distributing them fairly among the calls. The degradation is limited to a minimum value predefined in a user-defined profile (UDP). Genetic algorithms have been used to solve the optimization problem. From the user perspective, the perception of the QoS degradation is very graceful and happens only during overload periods. The network services, on the other hand, are greatly enhanced due to the fact that the call blocking probability is significantly decreased. Simulation results demonstrate that the proposed algorithm performs well in terms of increasing the number of admitted calls while utilizing the available bandwidth fairly and effectively.

[1]  Alexandros Eleftheriadis,et al.  Meeting QoS Challenges for Scalable Video Flows in Multimedia Networking , 1995 .

[2]  Mahmoud Naghshineh,et al.  End-to-end QoS provisioning in multimedia wireless/mobile networks using an adaptive framework , 1997, IEEE Commun. Mag..

[3]  Daniela Panno,et al.  A comparative analysis of fuzzy versus conventional policing mechanisms for ATM networks , 1996, TNET.

[4]  Ender Ayanoglu,et al.  Wireless ATM: limits, challenges, and proposals , 1996, IEEE Wirel. Commun..

[5]  Christos Douligeris,et al.  Rate Regulation with Feedback Controller in ATM Networks - A Neural Network Approach , 1997, IEEE J. Sel. Areas Commun..

[6]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1996, Springer Berlin Heidelberg.

[7]  Donald F. Towsley,et al.  Supporting stored video: reducing rate variability and end-to-end resource requirements through optimal smoothing , 1998, TNET.

[8]  Li-Der Chou,et al.  Bandwidth allocation of virtual paths using neural-network-based genetic algorithms , 1998 .

[9]  David Hutchison,et al.  Qos support for distributed multimedia communications , 1996 .

[10]  I. W. Habib.  Applications of neurocomputing in traffic management of ATM networks , 1996 .

[11]  David Hutchison,et al.  Filters: QoS Support Mechanisms for Multipeer Communications , 1996, IEEE J. Sel. Areas Commun..

[12]  Mahmoud Naghshineh,et al.  Issues in Wireless Access Broadband Networks , 1996 .

[13]  David Hutchison,et al.  QoS Adaption and Flow Filtering in ATM Networks , 1994, IWACA.

[14]  Hui Zhang,et al.  Service disciplines for guaranteed performance service in packet-switching networks , 1995, Proc. IEEE.

[15]  Christos Douligeris,et al.  Application of Neural Networks and Machine Learning in Network Design , 1997, IEEE J. Sel. Areas Commun..

[16]  Anthony S. Acampora.  Wireless ATM: a perspective on issues and prospects , 1996, IEEE Wirel. Commun..

[17]  Ralf Steinmetz,et al.  Issues ofReserving Resources in Advance , 1995, NOSSDAV.

[18]  Masayuki Yamamura,et al.  A Genetic Algorithm for Function Optimization , 2002 .

[19]  Abdelhakim Hafid,et al.  Some principles for quality of service management , 1997, Distributed Syst. Eng..

[20]  Andrew T. Campbell,et al.  Active filters: delivering scaled media to mobile devices , 1997, Proceedings of 7th International Workshop on Network and Operating System Support for Digital Audio and Video (NOSSDAV '97).

[21]  Christos Douligeris,et al.  Neuro-fuzzy control in ATM networks , 1997, IEEE Commun. Mag..

[22]  David Hutchinson,et al.  Continuous media filters for heterogeneous internetworking , 1996, Electronic Imaging.

[23]  Mark William Garrett.  Contributions toward real-time services on packet switched networks , 1993 .

[24]  Li-Der Chou,et al.  Buffer management using genetic algorithms and neural networks , 1995, Proceedings of GLOBECOM '95.

[25]  Andrew T. Campbell,et al.  A survey of QoS architectures , 1998, Multimedia Systems.

[26]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .