Adaptive Request Prioritization in Dynamic Service-Oriented Systems

Abstract

The availability of scarce resources in a serviceoriented system demands for context-aware selection policies that adapt based on service-level agreements (SLAs). One of the open issues is to prioritize service requests in dynamically changing environments where concurrent instances of processes may compete for resources. Here we propose a runtime monitoring approach to observe the actual state of the system. We argue that priorities should be assigned to requests based on potential violations of SLA objectives. While most existing work in the area of quality of service monitoring and SLA modeling focuses typically on purely technical systems, we consider service-oriented systems spanning both softwarebased services and human actors. Adaptive request scheduling in such systems is challenging due to the poorly predictable behavior of human actors in performing tasks. Our approach helps to cope with these challenges by prioritizing service requests that may cause violations of SLAs and corresponding objectives that are associated with processes.

QoS-Based Task Scheduling in Crowdsourcing Environments

“…This work is a continuation of a previous work [14] where scheduling was used to re-prioritize service requests to minimize SLA penalties. In this paper we used scheduling for task-worker assignment in a similar manner to fulfill SLAs.…”

Autonomic Prioritization of Enterprise Transactions Based on Bid-Price Controls

“…In addition, the authors conclude that inefficiencies resulting from queuing effects in the service network cannot be avoided as the determination of the right amount of instances per process type allowed to enter the system in a certain period -a major contribution of the work presented in this paper-is not considered. Khazankin, et al proposes an approach to resolve the problem of coarse-grained prioritization by dynamically determining individual schedules (orders) of workflow instances for each service individually [17]. Also based on utility functions, for each service their algorithm orders waiting workflow instances by the estimated penalty difference when scheduling a particular workflow instance and when delaying the instance.…”

Rescue Wings: Mobile Computing and Active Services Support for Disaster Rescue

“…A number of request scheduling algorithms have been proposed (e.g., [42]- [46]). In Rescue Wings, any request for Update Targets (updating the focused targets) is preferentially sent to available service instances of the Dyn map, and all the requests for other ISS services are scheduled using a priority based scheme [46] in combination with a frequentrequest-sequence-pattern (FRSP) based approach. That is, the requests are grouped by UserID of the servants.…”