Next-Generation Cloud/Edge/IoT/AI Systems

Project Overview

With this project, we investigate a wide variety of new techniques that facilitate

  • Use of emerging cloud, AI, and programming systems by the technologically underserved and those in disconnected or hard to reach areas (e.g. rural communities, remote settings, etc.)
  • Hybrid cloud use, including support for
    • Availability guarantees on pre-emptable (spot) instances
    • Cross-federation big data app deployment
  • Application Programming Interface (API) governance (deployment time and runtime)
  • Application Performance Monitoring (APM) as an integrated, efficient, and scalable PaaS service that enables web/cloud service response time SLAs
  • Automatic detection of performance anomolies, bottlenecks, workload changes with root cause identification -- across the PaaS stack over IaaS.
  • Novel prediction techniques (including new machine learning, artificial intelligence, and statistical techniques) for service and component downtime, fault tolerance, and execution time and cost estimation.
  • Edge cloud systems with support for
    • Efficient AI/ML that drive intelligent IoT applications (for ag, cities, ecology, and more)
    • Multi-analytics (multi-tenant) interference avoidance
    • Graceful degredation and fault tolerance
    • Self management (appliance-like)
  • New programming and deployment models for Cloud + IoT systems, including Serverless Functions-as-a-service

Team

Support

  • NSF CNS-1703560 (DatGeo)
  • NSF ACI-1541215 (Aristotle)
  • NSF CCF-1539586 (SmartFarm)
  • Huawei Corporation
  • Naval Engineering Education Consortium: ORN NEEC N00174-16-C-0020
  • NIH (1R01EB014877-01)

Publications and Presentations

  • The UCSB Lab for Research on Adaptive Computing Environments (RACELab)
  • R. Wolski, C. Krintz, F. Bakir, G. George, and W-T. Lin, CSPOT: Portable, Multi-scale Functions-as-a-Service for IoT (PDF), ACM Symposium on Edge Computing (SEC), Nov 2019
  • F. Bakir, R. Wolski, C. Krintz, and G. Sankar Ramachandran, Devices-as-Services: Rethinking Scalable Service Architectures for the Internet of Things (PDF), USENIX HotEdge, July 2019
  • M. Zhang, C. Krintz, R. Wolski, and M. Mock, Seneca: Fast and Low Cost Hyperparameter Search for Machine Learning Models (PDF), IEEE Cloud, July 2019
  • K. Carson, J. Thomason, M. Mock, R. Wolski and C. Krintz, Mandrake: Implementing Durabilty for Edge Clouds (PDF), IEEE Edge, July 2019
  • W-T. Lin, F. Bakir, C. Krintz, R. Wolski, and M. Mock, Data repair for Distributed, Event-based IoT Applications (PDF), ACM International Conference On Distributed and Event-Based Systems, June 2019
  • G. George, R. Wolski, C. Krintz, and J. Brevik, Analyzing AWS Spot Instance Pricing (PDF), International Conference on Cloud Engineering (IC2E), June 2019
  • Wei-Tsung Lin, Chandra Krintz, and Rich Wolski, Tracing Function Dependencies Across Clouds, (PDF), IEEE Cloud, July 2018
  • Wei-Tsung Lin, Michael Zhang, Chandra Krintz, and Rich Wolski, Tracking Causal Order in AWS Lambda Applications, (PDF), IEEE International Conference on Cloud Engineering (IC2E), June 2018
  • Hiranya Jayathilaka, Chandra Krintz, and Rich Wolski, Detecting Performance Anomalies in Cloud Platform Applications, (IEEExplore), IEEE Transactions on Cloud Computing (TCC), Feb 2018
  • S. Dimopoulos, C. Krintz, and R. Wolski, Justice: A Deadline-aware, Fair-share Resource Allocator for Implementing Multi-analytics,(PDF), IEEE Cluster, September, 2017 Won Best Paper Award!!
  • S. Dimopoulos, C. Krintz, and R. Wolski, PYTHIA: Admission Control for Multi-Framework, Deadline-Driven, Big Data Workloads,(PDF), IEEE Cloud, June, 2017
  • R. Wolski and J. Brevik, QPRED: Using Quantile Predictions to Improve Power Usage for Private Clouds,(PDF), IEEE Cloud, June, 2017
  • B. Drawert, A. Hellander, B. Bales, D. Banerjee, G. Bellesia, B. Daigle, G. Douglas, M. Gu, A. Gupta, S. Hellander, C. Horuk, D. Nath, A. Takkar, S. Wu, P. Lotstedt, C. Krintz, and L. Petzold, Stochastic Simulation Service: Bridging the Gap Between the Computational Expert and the Biologist, (PDF), PLOS Computational Biology, 2017
  • A. Pucher, R. Wolski, and C. Krintz, ExFed: Efficient Cross-Federation with Availability SLAs on Preemptible IaaS Instances, (PDF), IEEE International Conference on Cloud Engineering (IC2E), July, 2017
  • C. Krintz and R. Wolski, PaaS Cloud for Integrated Full Stack Monitoring, (PDF), ICT Insights, Issue 19, October, 2016
  • A. Rosales Elias, N. Golubovic, C. Krintz, and R. Wolski, Where's The Bear? -- Automating Wildlife Image Processing Using IoT and Edge Cloud Systems (Tech Report 2016-07), October, 2016
  • S. Dimopoulos, C. Krintz, and R. Wolski, Big Data Framework Interference In Restricted Private Cloud Settings (PDF), IEEE Conference on Big Data, December, 2016 (Pres)
  • H. Jayathilaka, R. Wolski, and C. Krintz, Service-Level Agreement Durability for Web Service Response Time (PDF), IEEE Conference on Cloud Computing Technology and Science (CloudCom'15). November, 2015
  • A. Chien, R. Wolski, and F. Yang, Zero-Carbon Cloud: A Volatile Resource for High-Performance Computing (PDF), International Workshop on Sustainable Higher Performance Computing 2015 in collaboration with the 13th IEEE International Conference on Dependable, Autonomic and Secure Computing (DACS 2015). September, 2015
  • H. Jayathilaka, R. Wolski, and C. Krintz, Response Time Service Level Agreements for Cloud-hosted Web Applications (PDF), ACM Symposium on Cloud Computing (SoCC'15). August, 2015
  • A. Pucher, R. Wolski, and C. Krintz, Providing Lifetime Service-Level-Agreements for Cloud Spot Instances (PDF), International Conference on Grid and Cloud Computing and Applications (GCA'15). July, 2015.
  • S. Dimopoulos, C. Krintz, and R. Wolski, SuperContra: Cross-Language, Cross-Runtime Contracts As a Service (PDF), IC2E Workshop on the Future of PaaS, March 2015
  • H. Jayathilaka, C. Krintz, and R. Wolski, EAGER: Deployment-time API Governance for Modern PaaS Clouds (PDF), IC2E Workshop on the Future of PaaS, March 2015
  • A. Pucher, C. Krintz, and R. Wolski, Using Trustworthy Simulation to Engineer Cloud Schedulers (PDF), IEEE International Conference on Cloud Engineering (IC2E), March, 2015.
  • Related project: Where's the Bear (WTB)
  • Related project: UCSB SmartFarm