the dynamic behaviour of some workload allocation algorithms is studied to identify instability conditions induced either by an external overload situation or by a workload reallocation, triggered by the failure of some of the requested resources. We use concepts, drawn from that part of system theory which is known as Thom's Catastrophe theory, such as the Drift and the Potential Functions. The method is then applied to workload balancing in a Distributed Database sytem; however our method can be extended to other kind of systems which can be found in the telecommunication networks and in the distributed computing systems areas. We first deal with simple examples to show how the instability conditions show up, then we show its application ...
Abstract—Large-scale distributed cyber-physical systems will have many sensors/actuators (each with ...
This thesis is about coping with variability in outcomes for complex stochastic systems. We focus on...
We study the phenomenon of entrainment in processor sharing networks, whereby, while individual netw...
This thesis is about coping with variability in outcomes for complex stochastic systems. We focus on...
The performance of computer systems depends, among other things, on the workload. This motivates the...
In this paper we analyse a very simple dynamic work-stealing algorithm. In the work-generation model...
The overall efficiency of parallel algorithms is most decisively effected by the strategy applied fo...
Load balancing is the process of redistributing the work load among nodes of the distributed system ...
Many systems are designed to handle workloads with characteristics that are assumed to be static. T...
Solutions to resource allocation problems and other related synchronization problems in distributed ...
The phenomenon of system catastrophe often occurs in a system with a network structure. A system’s r...
or use of any of the information contained in it must acknowledge this thesis as the source of the q...
Distributed termination detection (DTD) algorithms are important since they detect globally stable s...
This paper presents a method for qualitative and quantitative analysis of load sharing algorithms, u...
Distributed termination detection (DTD) algorithms are important since they detect globally stable s...
Abstract—Large-scale distributed cyber-physical systems will have many sensors/actuators (each with ...
This thesis is about coping with variability in outcomes for complex stochastic systems. We focus on...
We study the phenomenon of entrainment in processor sharing networks, whereby, while individual netw...
This thesis is about coping with variability in outcomes for complex stochastic systems. We focus on...
The performance of computer systems depends, among other things, on the workload. This motivates the...
In this paper we analyse a very simple dynamic work-stealing algorithm. In the work-generation model...
The overall efficiency of parallel algorithms is most decisively effected by the strategy applied fo...
Load balancing is the process of redistributing the work load among nodes of the distributed system ...
Many systems are designed to handle workloads with characteristics that are assumed to be static. T...
Solutions to resource allocation problems and other related synchronization problems in distributed ...
The phenomenon of system catastrophe often occurs in a system with a network structure. A system’s r...
or use of any of the information contained in it must acknowledge this thesis as the source of the q...
Distributed termination detection (DTD) algorithms are important since they detect globally stable s...
This paper presents a method for qualitative and quantitative analysis of load sharing algorithms, u...
Distributed termination detection (DTD) algorithms are important since they detect globally stable s...
Abstract—Large-scale distributed cyber-physical systems will have many sensors/actuators (each with ...
This thesis is about coping with variability in outcomes for complex stochastic systems. We focus on...
We study the phenomenon of entrainment in processor sharing networks, whereby, while individual netw...