HUNTER: AI based holistic resource management for sustainable cloud computing

Tuli, Shreshth; Gill, Sukhpal Singh; Xu, Minxian; Garraghan, Peter; Bahsoon, Rami; Dustdar, Schahram; Sakellariou, Rizos; Rana, Omer; Buyya, Rajkumar; Casale, Giuliano; Jennings, Nicholas R.

doi:10.1016/j.jss.2021.111124

Cited by 58 publications

(36 citation statements)

References 33 publications

(84 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Workload Model. We assume a bag-of-tasks workload model, where a set of independent tasks enter each LEI at the start of each scheduling interval [36], [50]. These are generated from the users and are transferred to the edge broker via gateway devices or IoT sensors.…”

Section: A Environment Assumptions and Problem Formulationmentioning

confidence: 99%

DRAGON: Decentralized Fault Tolerance in Edge Federations

Tuli

Casale

Jennings

2023

IEEE Trans. Netw. Serv. Manage.

Self Cite

View full text Add to dashboard Cite

Edge Federation is a new computing paradigm that seamlessly interconnects the resources of multiple edge service providers. A key challenge in such systems is the deployment of latency-critical and AI based resource-intensive applications in constrained devices. To address this challenge, we propose a novel memory-efficient deep learning based model, namely generative optimization networks (GON). Unlike GANs, GONs use a single network to both discriminate input and generate samples, significantly reducing their memory footprint. Leveraging the low memory footprint of GONs, we propose a decentralized faulttolerance method called DRAGON that runs simulations (as per a digital modeling twin) to quickly predict and optimize the performance of the edge federation. Extensive experiments with real-world edge computing benchmarks on multiple Raspberry-Pi based federated edge configurations show that DRAGON can outperform the baseline methods in fault-detection and Quality of Service (QoS) metrics. Specifically, the proposed method gives higher F1 scores for fault-detection than the best deep learning (DL) method, while consuming lower memory than the heuristic methods. This allows for improvement in energy consumption, response time and service level agreement violations by up to 74, 63 and 82 percent, respectively.

show abstract

Section: A Environment Assumptions and Problem Formulationmentioning

confidence: 99%

DRAGON: Decentralized Fault Tolerance in Edge Federations

Tuli

Casale

Jennings

2023

IEEE Trans. Netw. Serv. Manage.

Self Cite

View full text Add to dashboard Cite

show abstract

“…As a result, using AI in the cloud can improve the cloud's performance, efficiency, and digital transformation [42]. AI in the cloud computing environment is a crucial key to enabling organisations to become more efficient, strategic and insight-driven, while at the same time providing greater flexibility, agility and cost savings [43]. As a result, we turned to industry insiders for their insights about the expanding importance of AI in cloud computing.…”

Section: Cloud Computingmentioning

confidence: 99%

AI for Next Generation Computing: Emerging Trends and Future Directions

Gill,

Xu,

Ottaviani

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Autonomic computing investigates how systems can achieve (user) specified "control" outcomes on their own, without the intervention of a human operator. Autonomic computing fundamentals have been substantially influenced by those of control theory for closed and open-loop systems. In practice, complex systems may exhibit a number of concurrent and inter-dependent control loops. Despite research into autonomic models for managing computer resources, ranging from individual resources (e.g., web servers) to a resource ensemble (e.g., multiple resources within a data center), research into integrating Artificial Intelligence (AI) and Machine Learning (ML) to improve resource autonomy and performance at scale continues to be a fundamental challenge. The integration of AI/ML to achieve such autonomic and self-management of systems can be achieved at different levels of granularity, from full to human-in-the-loop automation. In this article, leading academics, researchers, practitioners, engineers, and scientists in the fields of cloud computing, AI/ML, and quantum computing join to discuss current research and potential future directions for these fields. Further, we discuss challenges and opportunities for leveraging AI and ML in next generation computing for emerging computing paradigms, including cloud, fog, edge, serverless and quantum computing environments.

show abstract

“…We do not have any cloud broker; instead, we run the scheduling policies as FaaS functions on a serverless platform such as AWS Lambda or Azure Serverless. As is common in prior work [6], [8], [28], we consider a discrete-time control problem, i.e., we divide the timeline into fixed-size execution intervals (of ∆ seconds) and denote the t-th interval by I t . A scheduling decision is made at the start of each interval for all incoming tasks in the previous interval.…”

Section: A System Model and Problem Formulationmentioning

confidence: 99%

“…We calculate the IPS, RAM and Disk utilizations, i.e., c i t , r i t , s i t for task w i t and cj t , rj t , sj t for host h j using the Docker Inspect 4 utility in Python and the iozone 5 linux benchmarking tool. The costs µ j are taken from Azure VM pricing calculator 6 for the UK-South and East-US Azure datacenters. The serverless Azure cost, ρ, is taken from the Azure Serverless pricing calculator 7 .…”

Section: B Setupmentioning

confidence: 99%

See 1 more Smart Citation

MetaNet: Automated Dynamic Selection of Scheduling Policies in Cloud Environments

Tuli¹,

Casale²,

Jennings³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Task scheduling is a well-studied problem in the context of optimizing the Quality of Service (QoS) of cloud computing environments. In order to sustain the rapid growth of computational demands, one of the most important QoS metrics for cloud schedulers is the execution cost. In this regard, several data-driven deep neural networks (DNNs) based schedulers have been proposed in recent years to allow scalable and efficient resource management in dynamic workload settings. However, optimal scheduling frequently relies on sophisticated DNNs with high computational needs implying higher execution costs. Further, even in non-stationary environments, sophisticated schedulers might not always be required and we could briefly rely on low-cost schedulers in the interest of cost-efficiency. Therefore, this work aims to solve the non-trivial meta problem of online dynamic selection of a scheduling policy using a surrogate model called MetaNet. Unlike traditional solutions with a fixed scheduling policy, MetaNet on-the-fly chooses a scheduler from a large set of DNN based methods to optimize task scheduling and execution costs in tandem. Compared to state-of-the-art DNN schedulers, this allows for improvement in execution costs, energy consumption, response time and service level agreement violations by up to 11, 43, 8 and 13 percent, respectively.

show abstract

HUNTER: AI based holistic resource management for sustainable cloud computing

Cited by 58 publications

References 33 publications

DRAGON: Decentralized Fault Tolerance in Edge Federations

DRAGON: Decentralized Fault Tolerance in Edge Federations

AI for Next Generation Computing: Emerging Trends and Future Directions

MetaNet: Automated Dynamic Selection of Scheduling Policies in Cloud Environments

Contact Info

Product

Resources

About