GOSH: Task Scheduling Using Deep Surrogate Models in Fog Computing Environments

TL;DR

This paper introduces GOSH, a novel deep surrogate model-based scheduler for fog computing that improves task allocation efficiency, reduces SLA violations, and adapts quickly to resource constraints using advanced gradient and uncertainty optimization techniques.

Contribution

GOSH employs second-order gradient optimization and heteroscedastic deep surrogate models to enhance scheduling accuracy and efficiency in fog environments, addressing uncertainties and training brittleness.

Findings

GOSH outperforms baseline methods in energy, response time, and SLA violations.

GOSH* achieves better scores but is limited to high resource scenarios.

Real experiments show up to 18% energy savings, 27% response time reduction, and 82% SLA violation decrease.

Abstract

Recently, intelligent scheduling approaches using surrogate models have been proposed to efficiently allocate volatile tasks in heterogeneous fog environments. Advances like deterministic surrogate models, deep neural networks (DNN) and gradient-based optimization allow low energy consumption and response times to be reached. However, deterministic surrogate models, which estimate objective values for optimization, do not consider the uncertainties in the distribution of the Quality of Service (QoS) objective function that can lead to high Service Level Agreement (SLA) violation rates. Moreover, the brittle nature of DNN training and prevent such models from reaching minimal energy or response times. To overcome these difficulties, we present a novel scheduler: GOSH i.e. Gradient Based Optimization using Second Order derivatives and Heteroscedastic Deep Surrogate Models. GOSH uses a second-order gradient based optimization approach to obtain better QoS and reduce the number of iterations to converge to a scheduling decision, subsequently lowering the scheduling time. Instead of a vanilla DNN, GOSH uses a Natural Parameter Network to approximate objective scores. Further, a Lower Confidence Bound optimization approach allows GOSH to find an optimal trade-off between greedy minimization of the mean latency and uncertainty reduction by employing error-based exploration. Thus, GOSH and its co-simulation based extension GOSH*, can adapt quickly and reach better objective scores than baseline methods. We show that GOSH* reaches better objective scores than GOSH, but it is suitable only for high resource availability settings, whereas GOSH is apt for limited resource settings. Real system experiments for both GOSH and GOSH* show significant improvements against the state-of-the-art in terms of energy consumption, response time and SLA violations by up to 18, 27 and 82 percent, respectively.