Integrated Resource Management and Scheduling with Multi-Resource Constraints

Ghosh, Satadal; Hansen, Jeffery P.; Rajkumar, Ragunathan; Lehoczky, John P.

doi:10.1109/real.2004.25

Cited by 69 publications

(52 citation statements)

References 7 publications

(4 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This has since been extended to include multi-resource cases in [13]. This paper takes a similar approach, but special care is taken so that the optimization is solvable in realtime and also focuses more on parameter estimation.…”

Section: Related Researchmentioning

confidence: 99%

A convex optimization-based approach to control of uncertain execution platforms

Lindberg

2010

49th IEEE Conference on Decision and Control (CDC)

View full text Add to dashboard Cite

Abstract-The problem of resource management in a system of a-priori unknown software components executing on nondeterministic hardware is considered. The approach uses on-line parameter estimation to address uncertainties and combines this with a convex optimization-based control scheme able to handle overload situations. An algorithm to solve the optimization in real-time is presented together with performance analysis through simulations. An implementation of the approach is experimentally compared with a static analysis scheme using worst case a-priori estimates. It is demonstrated that the presented approach outperforms the static scheme in situations with uncertainty and that the advantage increases as uncertainty grows.

show abstract

Section: Related Researchmentioning

confidence: 99%

A convex optimization-based approach to control of uncertain execution platforms

Lindberg

2010

49th IEEE Conference on Decision and Control (CDC)

View full text Add to dashboard Cite

show abstract

“…Furthermore, in addition to the validity constraint, T can also be optimized according to an objective function. Different objective functions may lead to different ways to assign deadlines and thus, different solutions [18] [19][31] [29]. In other words, a solution of the deadline assignment problem T specifies a set of {T ij }, u = 1..n, j = 1..m i where 1) assigning D…”

Section: Cp U Ijmentioning

confidence: 99%

“…In the third category, essentially, previous work has shown the need for integrating the task scheduler and the network scheduler referred to as multi-resource coordination/reservation and scheduling problem [18] [19][31] [29]. In [29][25], the approach is to allocate the resources such that the end-toend delay can be guaranteed while optimizing the general resource utilization.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

iDSRT: Integrated Dynamic Soft Real-Time Architecture for Critical Infrastructure Data Delivery over WLAN

Nguyen

Rivas

Nahrstedt

2009

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Abstract. Critical Infrastructures (CIs) such as the Power Grid play an important role in our lives. Of all important aspects of CIs, real-time data delivery is the most important one because appropriate decisions cannot be made without having data delivered in a timely manner. Also, the current trend for the real-time data delivery system, specifically SCADA (Supervisory Control and Data Acquisition) systems, is to move from a closed system toward an open system that has an open architecture and uses mature computer and communication technologies. Specifically, CIs tend to adopt micro-processor-based devices a.k.a. Intelligent Electronic Devices (IEDs) with commodity multi-threaded operating systems such as Linuxbased OSs and COTS wireless LAN technology such as 802.11 WLAN. However, these trends pose a question of whether real-time guarantees, using these technologies, are feasible and can be practically implemented without many modifications of the commodity platform. In this paper, we present a design and implementation of iDSRT, a system that provides endto-end soft real-time data delivery guarantees over 802.11 WLAN with minimal changes of the operating system and no changes in the MAC layer. iDSRT consists of three important and integrated schedulers: task scheduler, packet scheduler and node scheduler to achieve the goal. The integration requires a coordination mechanism among these components. We formulate this coordination problem as a convex optimization problem that can be solved using standard convex optimization techniques. We implement iDSRT in Linux and evaluate it in an experimental testbed. The results are promising and show that iDSRT can successfully achieve soft real-time guarantees with very low packet loss rate compared to 802.11 best-effort systems.

show abstract

“…To facilitate the radar's ability to dynamically prioritize its search and track tasking, a radar resource manager must optimize the allocation of radar resources to each function. Existing resource management approaches for a single radar are addressed in [2], [3] to reduce target state uncertainty. For multiple shipboard radars, [4] balances the relative residual radar resource capacity to minimize target migrations from one ship's search sector to another ship's sector.…”

Section: Introductionmentioning

confidence: 99%

Distributed multi-target search and track assignment using consensus-based coordination

Paley

2013

2013 Ieee Sensors

View full text Add to dashboard Cite

Abstract-This paper presents a distributed, consensus-based approach to optimize radar resource management for ballistic missile surveillance and tracking. Each radar determines their preferred radar-to-target assignment by balancing radar loading and minimizing total radar usage. A unique global radar-totarget assignment that is robust to resource estimation error is generated by a distributed consensus algorithm. Performance is validated via Monte Carlo simulations.

show abstract

Integrated Resource Management and Scheduling with Multi-Resource Constraints

Abstract: Abstract

Cited by 69 publications

References 7 publications

A convex optimization-based approach to control of uncertain execution platforms

A convex optimization-based approach to control of uncertain execution platforms

iDSRT: Integrated Dynamic Soft Real-Time Architecture for Critical Infrastructure Data Delivery over WLAN

Distributed multi-target search and track assignment using consensus-based coordination

Contact Info

Product

Resources

About