Ramps: Next Generation Platform for Real Time and Resilient IoT Analytics using MmWave and Programmable Switches

Real time IoT analytics remains a challenging problem due to the distributed nature of the analytics platform (comprising sensors, edge server(s), and actuators), which raises three fundamental challenges of (i) how to map computations to a distributed and heterogeneous compute fabric, (ii) how to communicate multi-Gbps of data wirelessly between sensors and edge servers for high analytics accuracy, and (iii) how to effectively share the communication channel between multiple sensor-edge network streams. To meet these challenges, we envision an analytics platform that will tightly couple the application stack, the network stack, and emerging networking technologies, namely mmWave wireless and programmable switches, to meet both the computation and communication demands for real time IoT analytics.

[1]  Jörg Ott,et al.  FADES: Fine-Grained Edge Offloading with Unikernels , 2017, HotConNet@SIGCOMM.

[2]  Albert Y. Zomaya,et al.  CA-DAG: Modeling Communication-Aware Applications for Scheduling in Cloud Computing , 2015, Journal of Grid Computing.

[3]  Shangguang Wang,et al.  MVR: An Architecture for Computation Offloading in Mobile Edge Computing , 2017, 2017 IEEE International Conference on Edge Computing (EDGE).

[4]  Mark Handley,et al.  Re-architecting datacenter networks and stacks for low latency and high performance , 2017, SIGCOMM.

[5]  Li Zhang,et al.  Stage Aware Performance Modeling of DAG Based in Memory Analytic Platforms , 2016, 2016 IEEE 9th International Conference on Cloud Computing (CLOUD).

[6]  Nick McKeown,et al.  Programmable Packet Scheduling at Line Rate , 2016, SIGCOMM.

[7]  Xiaozhou Li,et al.  NetChain: Scale-Free Sub-RTT Coordination , 2018, NSDI.

[8]  Jörg Widmer,et al.  A detailed look into power consumption of commodity 60 GHz devices , 2017, 2017 IEEE 18th International Symposium on A World of Wireless, Mobile and Multimedia Networks (WoWMoM).

[9]  Jörg Widmer,et al.  Fast and Infuriating: Performance and Pitfalls of 60 GHz WLANs Based on Consumer-Grade Hardware , 2018, 2018 15th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON).

[10]  Dimitrios Koutsonikolas,et al.  802.11ad in Smartphones: Energy Efficiency, Spatial Reuse, and Impact on Applications , 2021, IEEE INFOCOM 2021 - IEEE Conference on Computer Communications.

[11]  Mingjian Cui,et al.  Machine Learning-Based Anomaly Detection for Load Forecasting Under Cyberattacks , 2019, IEEE Transactions on Smart Grid.

[12]  Dimitrios Koutsonikolas,et al.  Throughput Prediction on 60 GHz Mobile Devices for High-Bandwidth, Latency-Sensitive Applications , 2021, PAM.

[13]  Junda Liu,et al.  Multi-enterprise networking , 2000 .

[14]  Yaoliang Yu,et al.  Petuum: A New Platform for Distributed Machine Learning on Big Data , 2013, IEEE Transactions on Big Data.

[15]  Saurabh Bagchi,et al.  ApproxNet: Content and Contention Aware Video Analytics System for the Edge , 2019, ArXiv.

[16]  Somali Chaterji,et al.  Ambrosia: Reduction in Data Transfer from Sensor to Server for Increased Lifetime of IoT Sensor Nodes , 2021, ArXiv.

[17]  Vishal Shrivastav,et al.  Fast, scalable, and programmable packet scheduler in hardware , 2019, SIGCOMM.

[18]  Parameswaran Ramanathan,et al.  60 GHz Indoor Networking through Flexible Beams: A Link-Level Profiling , 2015, SIGMETRICS 2015.

[19]  Dimitrios Koutsonikolas,et al.  Multipath TCP in Smartphones Equipped with Millimeter Wave Radios , 2021, WiNTECH@MOBICOM.

[20]  John K. Ousterhout,et al.  Homa: a receiver-driven low-latency transport protocol using network priorities , 2018, SIGCOMM.

[21]  Lili Qiu,et al.  Jigsaw: Robust Live 4K Video Streaming , 2019, MobiCom.

[22]  Saurabh Bagchi,et al.  I-BOT: Interference-Based Orchestration of Tasks for Dynamic Unmanaged Edge Computing , 2020, ArXiv.

[23]  Saurabh Bagchi,et al.  ApproxDet: content and contention-aware approximate object detection for mobiles , 2020, SenSys.

[24]  Paul Wood,et al.  SOPHIA: Online Reconfiguration of Clustered NoSQL Databases for Time-Varying Workloads , 2019, USENIX Annual Technical Conference.

[25]  Franz Franchetti,et al.  Fast and accurate object detection in high resolution 4K and 8K video using GPUs , 2018, 2018 IEEE High Performance extreme Computing Conference (HPEC).

[26]  Dimitrios Koutsonikolas,et al.  An experimental study of the performance of IEEE 802.11ad in smartphones , 2021, Comput. Commun..

[27]  Wencong Xiao,et al.  Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads , 2019, USENIX Annual Technical Conference.

[28]  Gautam Kumar,et al.  pHost: distributed near-optimal datacenter transport over commodity network fabric , 2015, CoNEXT.

[29]  Matthieu Roy,et al.  Experience Report: Log Mining Using Natural Language Processing and Application to Anomaly Detection , 2017, 2017 IEEE 28th International Symposium on Software Reliability Engineering (ISSRE).

[30]  Dimitrios Koutsonikolas,et al.  MuSher: An Agile Multipath-TCP Scheduler for Dual-Band 802.11ad/ac Wireless LANs , 2019, IEEE/ACM Transactions on Networking.

[31]  Martin Wattenberg,et al.  TensorFlow.js: Machine Learning for the Web and Beyond , 2019, MLSys.

[32]  Longfei Shangguan,et al.  Spider: Next generation Live Video Analytics over Millimeter-Wave Networks , 2020 .

[33]  Kyu-Han Kim,et al.  WiFi-Assisted 60 GHz Wireless Networks , 2017, MobiCom.