Using Machine Learning with Wide Area Networks (WANs) Dr. Mariam Kiran Energy Sciences Network (ESnet) ANTG Research Group Lawrence Berkeley National Lab Summer Student 2017 Talk 1
Agenda • Machine learning (ML) is everywhere: – Is it the Next Hype or substantial? • But what exactly in ML versus AI (versus deep learning)? • Some thoughts on Networks with additional ML support • The future? Current projects: – Project 1: ‘Talking’ to Networks – Project 2: Self-healing Networks 2
ML Riding the Wave ML at the peak 3
Is Machine Learning New?
Is it New? • NOPE! • Science Fiction has been exploring it for ages • Brought the main ideas around AI and human interactions 5
ML in the 90s… • Computers becoming smarter: – Playing Chess with your Computer – Making games difficult for players • A number of innovations in multiple areas of – Speech recognition – Image recognition – Robotics – Philosophy of mind 6
What is the Difference between AI, ML and DL Nvidia blog • Turing‘s paper “Can Machines Think!” – Turing Test : Exhibit human-like intelligence • Recently seen in movies • Machine learning is an approach to achieve AI – spam filters, HR • Deep learning is one of the techniques for ML: • Recent advances due to GPU and HPC processing (previously very slow, too much data, need training to work) • Mainly for image and speech recognition – commercial apps
AI Tree (subset is defined as ML techniques) Evolutionary algorithms (Genetic algorithms, Optimization evolutionary strategies, etc) technique Swarm intelligence (ant colony, particle swarm, more) Networks : graph algorithm (routing – shortest path) Expert systems AI Fuzzy systems Convolutional networks Neural Where ever learning Deep belief networks Networks involved (training): ML Deep boltzman networks Many more…. Stacked autoencoders
Trying out Deep Learning Libraries • Google’s DNN platform TensorFlow used to tag unlabeled videos, recognize images with 70% accuracy and predict Gmail replies • Scikit-learn good for learning, python library • NERSC for data analysis in simulations, e.g. climate image analysis HPC innovation: analyze massive data sets, quick training • Model and data parallelism • Toolkit Language Use Processing capability Caffe C++ Images and video Distributed (HPC, GPU) TensorFlow Python Images, regression, video, text, Distributed speech (HPC, GPU) Theano Python Images Distributed (HPC, GPU) Torch Lua Images and speech Distributed (HPC, GPU)
Choosing Algorithms for Specific Problems Deep neural Input Data Applied for Variants network Feed forward Hierarchical data • General classification • Deep belief networks neural network representations • Clustering (uses restricted anomaly finding boltzman machine for • • feature extraction activation function) • Convolutional neural networks Recurrent Sequential data Sequential learning, Long short term memory neural network representation especially useful when (LTSM) used for speech (i.e. time series time relationship exists. translation. data) • There are many variants of DNNs. Papers and researchers in each specific DNN • DeepMind used Deep Q-learning for Attari and Go • Action-pairs based on learned data.
Each algorithm is chosen depending on data being explored and problem being explored (some 50% accuracy, others 80% accuracy) 12
Also Choose Techniques based on ‘Learning’ Ontology based reasoning Rule based systems (expert systems) Knowledge based reasoning Kalman filter Bayesian networks Machine learning Hidden Markov models Probabilistic reasoning Decision trees Supervised Support vector machines Data-driven reasoning Deep boltzman Unsupervised Using statistical Semi supervised K-means classification (need training)
Range of possibilities of ML algorithms • Problem • Data • Processing/Experience What would Networks do with Machine learning?
ESnet Background • R&E networks for science (CERN, LHC, and more) • Provide reliable robust network connections to enable science workflows • Investigate research and techniques to help build better networks • Guarantees for our scientists for network needs (users) 16
For example: Many Actors, softwares, data, etc …. GISAXS Slot-die printing of Organic photovoltaics HipGISAXS & RMC - 19 - Borrowed from E Dart
ESnet Team continually engaged • Science workflows (using NSI or OSCARS) Designing for – Multi-domain provisioning • Specific science cases • Transfer tools and protocols (using Globus) (TCP research) • End-users – Ease of use, Reliable • Network engineers • R&E Networks support big data oriented services (using ScienceDMZ) – Dedicated Bandwidth on demand, loss free Teams: – Isolation Science Engagement, – Monitoring (perfSonar) Software, Infrastructure, – Network virtualization SDN Testbed, etc • Network research – Virtualization, SDN, switches, routers, etc 20
A Day in the Life of a Packet 21
Traffic Volume Growing Exponentially 1990 2030 2017 22
Managing Multiple Sites • Different traffic requirements • Quality of service, bandwidth, speed, time-based deliveries, etc • Reliability and heterogeneity 23
Automating Networks using ML Predict traffic peak times • Find anomalies for security threats • Optimize how paths are currently • utilized Predict link failures • Understand or predict user behavior • and network use These are Core Network Research • Problems!
Most uses of Machine Learning in Networks (IETF forums) • Network Security – Normal and outlier behaviors in traffic • Change or predict possible behavior – This <QoS value> will cause this <event Y> with probability <P> • Bug detection – Software or hardware faults • WAN path optimization – Anticipate congestion – Divert traffic to alternate paths
Problem becomes quite Complex • WAN are complete system with multiple layers • Focus on specific case studies • Over 2000 papers in the area
WANS are complex!
Depends on what we use ML for… User traffic User traffic data (directed flows) WAN Topology (traffic engineering) (flow-level, traffic prediction, adaptation, path optimization, link failure) Infrastructure traffic data (Packet-level, queues, TCP, UDP) Infrastructure-level modifications (Switches, deployment, etc) 28
What is Most Published? 60 50 No. of papers (2010-2017) 40 30 20 10 0 User Traffic Traffic Engineering Packet-level Optimizing improvements infrastructure ML Non-ML • Most ML techniques used for classification (of traffic) and prediction (failures) • Recent Google papers have been most influential: – B4, Jupiter, BwE, etc. (data center to user-based provisioning) • Network tools enhanced by embedding informed decisions such as traffic awareness for: – Forming topologies, optimum path finding – Improve path utilizations depending on traffic
Contribute to Research (tools, software, papers) • Simple graph optimization algorithms still largely used (non-ML) • Room for unexplored ML techniques • Game theory also seems a promising area (local vs global) • Our applications are more complex, more actors and requirements – We need to develop network techniques catering to science workflows Global optimum Local optimum 30
• Studying ML to understand how we can apply to our problems • Start with simple algorithms and progress to more complex tasks • Depends on the Goals we want to achieve Current Solutions being explored: Two projects using ML Intent-driven networks: INDIRA Self-healing networks
Intent-driven networks (user-level) • Focuses on improving user network interaction • Intent-based network – Solution: development of the INDIRA tool – Use of semantic ontology – Network provisioning and rendering of commands – Current state – interaction with multiple tools (NSI, globus, and more) 32
Setting the Stage scientist Network Network Network universities engineer engineer engineer R&E DoE ESnet networks facilities scientist scientist Network scientist engineer instruments I want to watch a movie tonight on netflix I want to stream the big data directly into the cache scientist of my super computer I want to see my real time high resolution big data visualization • Applications have complex workloads • Network behavior tailored for my application ‘ intent ’ • Difficult to fulfill these diverse set of needs • Learning curve is huge and complex Difficult to specify needs in ‘english’ • • Specify in high-level language, portable, multi-domain 33
Recommend
More recommend
