Backup or Not: An Online Cost Optimal Algorithm for Data Analysis Jobs Using Spot Instances

Lin, Liduo; Pan, Li; Liu, Shijun

doi:10.1109/access.2020.3014978

Cited by 4 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, vehicles face various challenges, such as the timing of place reservation requests, leading to higher costs or missed opportunities for cost savings in this dynamic environment. Companies like Amazon Web Services (AWS), MTN, China Telecom, and Uninor utilize this method, adjusting prices in response to supply and demand [18], [19], [20]. In a prior study [12], we introduced a concept called a smart request, which is a strategically placed reservation request that allows vehicles to optimize bandwidth costs and mitigate potential risks associated with dynamic pricing and resource unavailability from MNOs.…”

Section: Introductionmentioning

confidence: 99%

Optimizing Bandwidth Reservation Decision Time in Vehicular Networks using Batched LSTM

Al-khatib,

Moessner,

Timinger

2024

IJACSA

View full text Add to dashboard Cite

Time-sensitive and safety-critical networked vehicular applications, such as autonomous driving, require deterministic guaranteed resources. This is achieved through advanced individual bandwidth reservations. The efficient timing of a vehicle decision to place a cost-efficient reservation request is crucial, as vehicles typically lack sufficient information about future bandwidth resource availability and costs. Predicting bandwidth costs often using time-series machine learning models like Long Short-Term Memory (LSTM). However, standard LSTM models typically require longer durations of multiple input data sets to achieve high accuracy. In certain scenarios, quick decisions must be made, even if the vehicle means sacrificing some accuracy. We propose a batched LSTM model to assist vehicles in placing bandwidth reservation requests within a limited data for an upcoming driving path. The model divides data during training to enhance computational efficiency and model performance. We validated our model using historical Amazon price data, providing a real-world scenario for experiment. The results demonstrate that the batched LSTM model not only achieves higher accuracy within a short input data duration but also significantly reduces bandwidth costs by up to 27% compared to traditional time-series machine learning models.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimizing Bandwidth Reservation Decision Time in Vehicular Networks using Batched LSTM

Al-khatib,

Moessner,

Timinger

2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…This means to interrupt another job that is currently executing, and to steal one of its nodes and assign it as a new resource to the failed job. This node stealing approach is inspired by similar ideas in cloud computing, where users who have paid for spot instances [4][5][6] can have their resources taken back without prior notification. To the best of our knowledge, this work is the first work that studies node stealing in an HPC framework.…”

mentioning

confidence: 99%

Improving batch schedulers with node stealing for failed jobs

Du,

Marchal,

Pallez

et al. 2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryAfter a machine failure, batch schedulers typically re‐schedule the job that failed with a high priority. This is fair for the failed job but still requires that job to re‐enter the submission queue and to wait for enough resources to become available. The waiting time can be very long when the job is large and the platform highly loaded, as is the case with typical HPC platforms. We propose another strategy: when a job fails, if no platform node is available, we steal one node from another job , and use it to continue the execution of despite the failure. In this work, we give a detailed assessment of this node stealing strategy using traces from the Mira supercomputer at Argonne National Laboratory. The main conclusion is that node stealing improves the utilization of the platform and dramatically reduces the flow of large jobs, at the price of slightly increasing the flow of small jobs.

show abstract

RISCLESS: A Reinforcement Learning Strategy to Guarantee SLA on Cloud Ephemeral and Stable Resources

Yalles

Handaoui

Dartois

et al. 2022

2022 30th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)

View full text Add to dashboard Cite

One of the main objectives of Cloud Providers (CP) is to guarantee the Service-Level Agreement (SLA) of customers while reducing operating costs. To achieve this goal, CPs have built large-scale datacenters. This leads, however, to underutilized resources and an increase in costs. A way to improve the utilization of resources is to reclaim the unused parts and re-sell them at a lower price. Providing SLA guarantees to customers on reclaimed resources is a challenge due to their high volatility. Some state-of-the-art solutions consider keeping a proportion of resources free to absorb sudden variation in workloads. Others consider stable resources on top of the volatile ones to fill in for the lost resources. However, these strategies either reduce the amount of reclaimable resources or operate on less volatile ones such as Amazon Spot instance. In this paper, we proposed RISCLESS, a Reinforcement Learning strategy to exploit unused Cloud resources. Our approach consists of using a small proportion of stable on-demand resources alongside the ephemeral ones in order to guarantee customers SLA and reduce the overall costs. The approach decides when and how much stable resources to allocate in order to fulfill customers' demands. RISCLESS improved the CPs' profits by an average of 15.9% compared to state-of-the-art strategies. It also reduced the SLA violation time by an average of 36.7% while increasing the amount of used ephemeral resources by 19.5% on average 1 .

show abstract

Backup or Not: An Online Cost Optimal Algorithm for Data Analysis Jobs Using Spot Instances

Cited by 4 publications

References 26 publications

Optimizing Bandwidth Reservation Decision Time in Vehicular Networks using Batched LSTM

Optimizing Bandwidth Reservation Decision Time in Vehicular Networks using Batched LSTM

Improving batch schedulers with node stealing for failed jobs

RISCLESS: A Reinforcement Learning Strategy to Guarantee SLA on Cloud Ephemeral and Stable Resources

Contact Info

Product

Resources

About