Deadline Assignment and Tardiness Control for Real-Time Data Services

Zhou, Yan; Kang, Kyoung-Don

doi:10.1109/ecrts.2010.20

Cited by 4 publications

(6 citation statements)

References 24 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If there exists at least one satisfaction time within the deadline, the query is satisfied; otherwise, it is violated. These query semantics follow the query model in real-time databases [17,18]. Consequently, when the resource is restricted, the management objective of VOL is to maximize the rate of satisfied queries under resource constraints.…”

Section: Framework Architecturementioning

confidence: 99%

Resource-Efficient Sensor Data Management for Autonomous Systems Using Deep Reinforcement Learning

Jeong

Yoo

et al. 2019

Sensors

View full text Add to dashboard Cite

Hyperconnectivity via modern Internet of Things (IoT) technologies has recently driven us to envision “digital twin”, in which physical attributes are all embedded, and their latest updates are synchronized on digital spaces in a timely fashion. From the point of view of cyberphysical system (CPS) architectures, the goals of digital twin include providing common programming abstraction on the same level of databases, thereby facilitating seamless integration of real-world physical objects and digital assets at several different system layers. However, the inherent limitations of sampling and observing physical attributes often pose issues related to data uncertainty in practice. In this paper, we propose a learning-based data management scheme where the implementation is layered between sensors attached to physical attributes and domain-specific applications, thereby mitigating the data uncertainty between them. To do so, we present a sensor data management framework, namely , which adopts reinforcement learning (RL) techniques to manage the data quality for CPS applications and autonomous systems. To deal with the scale issue incurred by many physical attributes and sensor streams when adopting RL, we propose an action embedding strategy that exploits their distance-based similarity in the physical space coordination. We introduce two embedding methods, i.e., a user-defined function and a generative model, for different conditions. Through experiments, we demonstrate that the framework with the action embedding outperforms several known heuristics in terms of achievable data quality under certain resource restrictions. We also test the framework with an autonomous driving simulator, clearly showing its benefit. For example, with only 30% of updates selectively applied by the learned policy, the driving agent maintains its performance about 96.2%, as compared to the ideal condition with full updates.

show abstract

Section: Framework Architecturementioning

confidence: 99%

Resource-Efficient Sensor Data Management for Autonomous Systems Using Deep Reinforcement Learning

Jeong

Yoo

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…The k th sampling point and the k th sampling period are equal to the time kP and time interval [(k − 1)P, kP ), respectively. 1 To closely support the desired average/transient DDR, our feedback-based DDR control scheme depicted in Figure 2 executes the following procedure at every sampling point:…”

Section: Fig 2 Ddr Control Loopmentioning

confidence: 99%

“…Although our approach is not limited to a specific data-intensive real-time application, our prototype models an online stock quote system often used to 1. In this paper, we set the sampling period P = 1s.…”

Section: A Real-time Database Prototypementioning

confidence: 99%

See 1 more Smart Citation

Deadline Assignment and Feedback Control for Differentiated Real-Time Data Services

Zhou

Kang

2015

IEEE Trans. Knowl. Data Eng.

Self Cite

View full text Add to dashboard Cite

It is challenging to process real-time data service requests, such as online trade or traffic monitoring requests, within their deadlines, while providing differentiated real-time data services. To address the problem, we present new approaches to 1) assigning deadlines to real-time data service requests based on their data access needs and service classes to differentiate realtime data services when the system is busy and 2) closely supporting the specified target delay to deadline ratio (DDR)−the ratio of actual data service delays to deadlines−via feedback control even in the presence of dynamic workloads. Further, we have actually implemented our approaches by extending an open source database unlike most existing work on real-time databases. The experimental results show that our approach closely supports the target DDR bound and service differentiation requirements among the service classes unlike the tested baselines representing the current state of the art in real-time database research.

show abstract

“…In this case, if the server is overloaded it is better not to process additional requests to guarantee a low maximum response time. In this overload case, the server refuses service to a fraction of requests to maintain a tardiness bound [19]. Similarly, in the case of the GPU we have developed a feedback-controller in the CPU which periodically measures the processing time and quality of the process on the GPU and accordingly throttles the admission of new requests.…”

Section: Online Scheduling With Feedback Controlmentioning

confidence: 99%

Anytime Algorithms for GPU Architectures

Mangharam

Saba

2011

2011 IEEE 32nd Real-Time Systems Symposium

View full text Add to dashboard Cite

Most algorithms are run-to-completion and provide one answer upon completion and no answer if interrupted before completion. On the other hand, anytime algorithms have a monotonic increasing utility with the length of execution time. Our investigation focuses on the development of time-bounded anytime algorithms on Graphics Processing Units (GPUs) to trade-off the quality of output with execution time. Given a time-varying workload, the algorithm continually measures its progress and the remaining contract time to decide its execution pathway and select system resources required to maximize the quality of the result. To exploit the quality-time tradeoff, the focus is on the construction, instrumentation, on-line measurement and decision making of algorithms capable of efficiently managing GPU resources. We demonstrate this with a Parallel A* routing algorithm on a CUDA-enabled GPU. The algorithm execution time and resource usage is described in terms of CUDA kernels constructed at design-time. At runtime, the algorithm selects a subset of kernels and composes them to maximize the quality for the remaining contract time. We demonstrate the feedback-control between the GPU-CPU to achieve controllable computation tardiness by throttling request admissions and the processing precision. As a case study, we have implemented AutoMatrix, a GPU-based vehicle traffic simulator for real-time congestion management which scales up to 16 million vehicles on a US street map. This is an early effort to enable imprecise and approximate real-time computation on parallel architectures for stream-based timebounded applications such as traffic congestion prediction and route allocation for large transportation networks. ©2011 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. Abstract-Most algorithms are run-to-completion and provide one answer upon completion and no answer if interrupted before completion. On the other hand, anytime algorithms have a monotonic increasing utility with the length of execution time. Our investigation focuses on the development of time-bounded anytime algorithms on Graphics Processing Units (GPUs) to trade-off the quality of output with execution time. Given a time-varying workload, the algorithm continually measures its progress and the remaining contract time to decide its execution pathway and select system resources required to maximize the quality of the result. To exploit the quality-time tradeoff, the focus is on the construction, instrumentation, on-line measurement and decision making of algorithms capable of efficiently managing GPU resources. We demonstrate this with a Parallel A* routing algorithm on a CUDA-enabled GPU. The algorithm execution time and resource usage is described in terms of CUDA kernels cons...

show abstract

Deadline Assignment and Tardiness Control for Real-Time Data Services

Cited by 4 publications

References 24 publications

Resource-Efficient Sensor Data Management for Autonomous Systems Using Deep Reinforcement Learning

Resource-Efficient Sensor Data Management for Autonomous Systems Using Deep Reinforcement Learning

Deadline Assignment and Feedback Control for Differentiated Real-Time Data Services

Anytime Algorithms for GPU Architectures

Contact Info

Product

Resources

About