Scheduling problems in parallel systems for telecommunications

The scheduling of the large number of tasks with various cooperation modes poses interesting theoretical problems in parallel systems used in telecommunications. Such systems are fully distributed ones, preventing coherent observability. In such systems no absolute time-space reference exists. The theoretically optimal set of local references is given as the limiting factor for the incoherent observability. The failures and/or modifications inherent in the massively parallel systems may change their configurations dynamically. Thus no optimal algorithms can be developed for the effective utilization of the resources available in such a system. The influence of the granularity level and of the cooperation modes of the processes on scheduling are investigated in order to identify areas for further study.ZusammenfassungDas Scheduling einer großcn Anzahl von Tasks mit verschiedenen Kooperationsmoden verursacht interessante theoretische Probleme in parallelen Systemen, so wie sie in der Telekommunikation vorkommen. Diese Systeme sind voll verteilt, was die kohärente Beobachtungsfähigkeit verhindert. In diesen Systemen existiert keine absolute Zeit-Raum Referenz. Die theoretisch optimale Menge der lokalen Referenzen definiert die Schranke der inkohärenten Beobachtungsfähigkeit. Die Ausfälle oder/und Veränderungen, die für massiv parallele Systeme charakteristisch sind, können deren Konfiguration dynamisch modifizieren. Deshalb ist es nicht möglich, optimale Algorithmen für die effektive Nutzung der verfügbaren Ressourcen zu entwickeln. Der Einfluß des Granularitätsniveaus und der Kooperationsmoden der Prozesse auf das Scheduling wird aufgezeigt, um für weitere Untersuchungen eine Grundlage zu bilden.

[1]  LamportLeslie Time, clocks, and the ordering of events in a distributed system , 1978 .

[2]  D. Parnas,et al.  On satisfying timing constraints in hard-real-time systems , 1991, SIGSOFT '91.

[3]  Gérard Le Lann,et al.  Distributed Systems - Towards a Formal Approach , 1977, IFIP Congress.

[4]  Eduardo B. Fernández,et al.  Bounds on the Number of Processors and Time for Multiprocessor Optimal Schedules , 1973, IEEE Transactions on Computers.

[5]  C. V. Ramamoorthy,et al.  Optimal Scheduling Strategies in a Multiprocessor System , 1972, IEEE Transactions on Computers.

[6]  Leslie Lamport,et al.  Time, clocks, and the ordering of events in a distributed system , 1978, CACM.

[7]  J.M. Duran,et al.  International standards for intelligent networks , 1992, IEEE Communications Magazine.

[8]  Nirwan Ansari,et al.  A Genetic Algorithm for Multiprocessor Scheduling , 1994, IEEE Trans. Parallel Distributed Syst..

[9]  Ignac Lovrek,et al.  Performance of Genetic Algorithm Used for Analysis of Call and Service Processing in Telecommunications , 1995, ICANNGA.

[10]  C. V. Ramamoorthy,et al.  System Modeling and Testing Procedures for Microdiagnostics , 1972, IEEE Transactions on Computers.

[11]  Lui Sha,et al.  Priority Inheritance Protocols: An Approach to Real-Time Synchronization , 1990, IEEE Trans. Computers.

[12]  Joe Armstrong,et al.  ERLANG - an experimental telephony programming language , 1990, International Symposium on Switching.

[13]  Kang G. Shin,et al.  Optimal Scheduling of Cooperative Tasks in a Distributed System Using an Enumerative Method , 1993, IEEE Trans. Software Eng..

[14]  G. Nemeth Routing, scheduling, timing and intractability , 1994, Proceedings of the First International Conference on Massively Parallel Computing Systems (MPCS) The Challenges of General-Purpose and Special-Purpose Computing.

[15]  Ignac Lovrek,et al.  An approach to massively parallel call and service processing in telecommunications , 1994, Proceedings of the First International Conference on Massively Parallel Computing Systems (MPCS) The Challenges of General-Purpose and Special-Purpose Computing.