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

arXiv: https://arxiv.org/abs/2112.08916 · HTML: https://mlsanity.com/paper/2112.08916/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 62 references that are in the map.
- First posted on arXiv 16 Dec 2021.

## Builds on (most cited first, 27 of 27)

- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Optimizing Neural Networks with Kronecker-factored Approximate Curvature](https://mlsanity.com/paper/1503.05671/) (2015)
- [PyHessian: Neural Networks Through the Lens of the Hessian](https://mlsanity.com/paper/1912.07145/) (2019)
- [Teacher-Student Curriculum Learning](https://mlsanity.com/paper/1707.00183/) (2017)
- [ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning](https://mlsanity.com/paper/2006.00719/) (2020)
- [Implicit Gradient Regularization](https://mlsanity.com/paper/2009.11162/) (2020)
- [Hessian-based Analysis of Large Batch Training and Robustness to Adversaries](https://mlsanity.com/paper/1802.08241/) (2018)
- [Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation](https://mlsanity.com/paper/1908.00598/) (2019)
- [Aleatoric and Epistemic Uncertainty with Random Forests](https://mlsanity.com/paper/2001.00893/) (2020)
- [Natural-Parameter Networks: A Class of Probabilistic Neural Networks](https://mlsanity.com/paper/1611.00448/) (2016)
- [COSCO: Container Orchestration using Co-Simulation and Gradient Based Optimization for Fog Computing Environments](https://mlsanity.com/paper/2104.14392/) (2021)
- [An Uncertainty-Aware Approach to Optimal Configuration of Stream Processing Systems](https://mlsanity.com/paper/1606.06543/) (2016)
- [All One Needs to Know about Fog Computing and Related Edge Computing Paradigms: A Complete Survey](https://mlsanity.com/paper/1808.05283/) (2018)
- [Dynamic Scheduling for Stochastic Edge-Cloud Computing Environments using A3C learning and Residual Recurrent Neural Networks](https://mlsanity.com/paper/2009.02186/) (2020)
- [Augmenting Max-Weight with Explicit Learning for Wireless Scheduling with Switching Costs](https://mlsanity.com/paper/1808.01618/) (2018)
- [HealthFog: An Ensemble Deep Learning based Smart Healthcare System for Automatic Diagnosis of Heart Diseases in Integrated IoT and Fog Computing Environments](https://mlsanity.com/paper/1911.06633/) (2019)
- [PreGAN: Preemptive Migration Prediction Network for Proactive Fault-Tolerant Edge Computing](https://mlsanity.com/paper/2112.02292/) (2021)
- [FogBus: A Blockchain-based Lightweight Framework for Edge and Fog Computing](https://mlsanity.com/paper/1811.11978/) (2018)
- [DeFog: Fog Computing Benchmarks](https://mlsanity.com/paper/1907.10890/) (2019)
- [POND: Pessimistic-Optimistic oNline Dispatching](https://mlsanity.com/paper/2010.09995/) (2020)
- [HUNTER: AI based Holistic Resource Management for Sustainable Cloud Computing](https://mlsanity.com/paper/2110.05529/) (2021)
- [Generative Optimization Networks for Memory Efficient Data Generation](https://mlsanity.com/paper/2110.02912/) (2021)
- [MCDS: AI Augmented Workflow Scheduling in Mobile Edge Cloud Computing Systems](https://mlsanity.com/paper/2112.07269/) (2021)
- [Internet of Things (IoT) and New Computing Paradigms](https://mlsanity.com/paper/1812.00591/) (2018)
- [RBED: Reward Based Epsilon Decay](https://mlsanity.com/paper/1910.13701/) (2019)

## Built on by (most cited first, 5 of 5)

- [FlexiBERT: Are Current Transformer Architectures too Homogeneous and Rigid?](https://mlsanity.com/paper/2205.11656/) (2022)
- [CAROL: Confidence-Aware Resilience Model for Edge Federations](https://mlsanity.com/paper/2203.07140/) (2022)
- [PROMPT: Learning Dynamic Resource Allocation Policies for Network Applications](https://mlsanity.com/paper/2201.07916/) (2022)
- [MetaNet: Automated Dynamic Selection of Scheduling Policies in Cloud Environments](https://mlsanity.com/paper/2205.10642/) (2022)
- [RAPID: Enabling Fast Online Policy Learning in Dynamic Public Cloud Environments](https://mlsanity.com/paper/2304.04797/) (2023)

## Abstract (arXiv)

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.