CSci 8980 Machine Learning in Computer Systems

TL;DR: CAPES is a model-less deep reinforcement learning based unsupervised system parameter tuning framework that uses deep neural network for implementation. It uses the Q learning paradaigm to suggest changes to the systems parameters such that it optimizes for performance/efficiency or whatever the end goal is. Problem statement Often systems need tweaking to make it work such that its performance is at its possible best or on other words many systems applications need optimizing to attain the best result. Tuning for such optimum configuration needs a lot of time, domain knowledge and expertise which could be hard if the enterprise is small enterprise where they cannot afford both time and money to attain the optimum. Through this paper Yan Li, et al. try to propose a generalized framework that can to the task of parameter tuning for any target system online such that its performance meets the specified goal. This paper masks the need for prior domain knowledge and adapt...

Introduction: The idea in this paper is similar to a paper[ Auto DBMS Tuning... ] we have discussed on class before. In the paper[ Auto DBMS Tuning... ], the author use ML model to automatically tune database knobs, while in this paper the author use ML model to optimize the combination of components in a complex software system to achieve better performance. The whole framework could be divided into 3 parts: 1.   Dane: A light weight programming language for implementing small components. These components could be assembled together to build a large scale software system. Some of these components may have the same function but do jobs in different ways. The main contribution of Dane is that it is fast so that different component could be dynamically rewired with very low cost. 2.   A perception, assembly and learning framework (PAL): It contains 2 modules: 1). Assembly Module. It could assemble different components to implement a feature. 2). Perception Mod...

Authors:  Barry Porter†, Matthew Grieves†, Roberto Rodrigues Filho† and David Leslie‡ †School of Computing and Communications; ‡Department of Mathematics and Statistics Lancaster University, UK Overview:  It's a very interesting paper. This paper gives a new idea for developing software: components and runtime adaptor, and it divides the runtime adaptor into 3 layers. First, the paper designs a new "glue" language named Dana to describe component interface and low level relationships. Then it proposes the "Perception, Assembly and Learning" layer (PAL) for: connecting components (assembly) to a full software system, collecting component's metrics/performance (perception) and provide interface for the learning layer. The highest learning layer will analyze the provided metrics and given action feedback for dynamic tuning. Main points in this paper:  REX: Dana, PAL and Learning Dana: - Describe components' interfaces and dependence relationship ...

Authors: Li Chen, Justinas Lingys, Kai Chen, Feng Liu Current method for Datacenter traffic optimization: A monitoring system is used for traffic data collection, after enough data is collected it is presented to engineers who perform data analysis, apply their application layer knowledge to produce a heuristic. This heuristic is tested using run simulation tools to find the optimal parameter settings. This process takes weeks or even months. In this way traffic optimization policies are generated for varying traffic load, flow size distribution, traffic concentration, etc. The problem: Due to the large turn around time there is data staleness because the characteristics traffic distribution that the system was built on maybe different from the current traffic characteristics and even when the traffic distributions are the same there maybe parameter- environment miss match which leads to a performance degradation. Both these problems can be avoided is the turn around time i...

Introduction: In this paper, the authors are trying to obtain optimal network topology in data center networks using a machine learning approach. In this paper, they use multiple neural network models which take input a traffic demand matrix and output a network topology. The network topology is optimized to achieve the best value for a network metric provided by the data center operator. Motivation: Data centers networks are a critical part of the infrastructure. Congestion in some switch can bring down the performance of a large part of the system. The authors argue that most of the data centers use static network topologies and overprovision them to handle different scales of traffic. This increases the investment cost and resource consumption at runtime. The authors propose to use dynamically reconfigurable networks which can change the topology depending on the traffic demand. Research questions addressed by the paper: In this paper, they propose models that are capable ...

Authors: Mowei Wang, Yong Cui, Shihan Xiao, Xin Wang, Dan Yang, Kai Chen, Jun Zhu Motivation: Adopting new network components (e.g., optical circuit switches or wireless radios) into the data center networks (DCNs) has become a very common approach to improve the DCN’s performance in recent days. However, how to find the optimal (or near-optimal) topology configuration to support the dynamic traffic demands has become a key challenge. In order to address this challenge, this paper proposes the xWeaver which can find the best global topology to meet the overall traffic demands in a practical DCN. xWeaver is a traffic-driven deep learning system with three key design features: expressive learning framework, data-driven feature extraction, and traffic-topology mapping learning. Experiments demonstrate that xWeaver outperforms other solutions such as Weight-matching and Sample, and it can update its model parameters for new traffic smoothly without extensive retraining ev...

Authors - Anwesha Das, Frank Mueller, Paul Hargrove, Eric Roman, Scott Baden Main idea - Uses Machine Learning to predict when a particular node would cause failure in a HPC. Current trend is to use reactive approaches for failure recovery. Checkpoints/Restarts which cause significant overhead. Important terminologies -  1. Lead time = (Failure occurrence Time – Time at which an impending failure is flagged by the algorithm) 2. Earlier the failure flagged -> Higher the lead time -> more time for secondary actions 3. Failure Chain: Exact sequence of phrases which lead upto a node failure 4. False Positives = Very similar to the failure chains but NOT leading to a failure Research questions answered via the paper: 1. Predict short lead times, pin-point the failure location 2. Analyze lead time sensitivity for feasible proactive measures Proposed Solution -  What does it try to do? 1. Node A may fail at location B 2. Analysis is done between the trade off...