S y n t h e s i z i n g P l a u s i b l e I n - PowerPoint PPT Presentation

S y n t h e s i z i n g P l a u s i b l e I n f r a s t r u c t u r e C o n fi g u r a t i o n s f o r E v a l u a t i n g E d g e C o mp u t i n g S y s t e ms T h o ma s R a u s c h @ t h r a u a t Clemens Lachner Pantelis A. Frangoudis Philipp Raith Schahram Dustdar TU Wien, Vienna Austria Distributed Systems Group HotEdge’20, June 25–26, 2020 https://dsg.tuwien.ac.at

USENIX HotEdge’19 2

3

Edge systems evaluation tools iFogSim Gupta et al. iFogSim: A toolkit for modeling and simulation of resource management techniques in the Internet of Things, Edge and Fog computing environments Mayer et al. EmuFog: Extensible and scalable emulation of large-scale fog computing infrastructures 4

What are representative infrastructure configurations for edge systems? 5

Urban Sensing Multi-Access Edge Computing Details in the paper! Array of Things, Huawei PoleStar Fadahuns et al. Locality sensitive request distribution for fog and cloud servers Industrial IoT Vehicular Networking 6 Eiza et al. Investigation of routing reliability of vehicular ad hoc networks Chen et al. Edge Computing in IoT-Based Manufacturing

City-Scale Edge Computing Fabric https://arrayofthings.github.io 7

Edge Topology Synthesizer 8

Conceptual model Nodes Links N o d e L i n k I n t e r n e t B a c k h a u l C o n n e c t i o n C e l l U p / D o w n l i n k L a t e n c y : 0 . 5 m s B W: 3 0 0 M B / s L A N C e l l C l o u d l e t S h a r e d L i n k C e l l I o T C o m p u t e C e l l Industrial IoT Scenario Host 9

Parameterized cell synthesis  Degree distributions? Probably not.  Cell (cluster) size  Heterogeneity: How different are the devices in the cell?  Density: How many nodes are in this cell compared to others?  ? What others would be useful 10

GeoCell Density https://www.senderkataster.at/karte lognorm( = 0.82, s=2.02) ( = 0.47, s=73.02) Density Density 0.01 0.2 0.00 0.0 0 25 50 75 100 125 150 175 0 2 4 6 8 10 12 14 Number of mobile base stations Number of AoT nodes 11

Programmatic creation of topologies (= networkx graph) topology = Topology() aot_node = IoTComputeBox(nodes=[nodes.rpi3, nodes.rpi3]) neighborhood = lambda size: SharedLinkCell( nodes=[ [aot_node] * size, IoTComputeBox([nodes.nuc] + ([nodes.tx2] * size * 2)) ], shared_bandwidth=500, backhaul=MobileConnection('internet_chix')) city = GeoCell( GraphML 5, nodes=[neighborhood], density=lognorm((0.82, 2.02))) GML cloudlet = Cloudlet( JSON 5, 2, backhaul=FiberToExchange('internet_chix')) YAML ... topology.add(city) topology.add(cloudlet) 12

Interconnecting topologies Internet Backbone Graph (static) Different backhaul graphs: FRA ● Internet exchanges US East 90 ms ● AWS regions 352 ms SYD 206 ms GeoCell(..., backhaul = Cloudlet(backhaul = FiberToExchange(‘aws_syd’)) FiberToExchange(‘aws_us_east’)) Application Graph (generated) 13

WLA LAN Ce Cell Clou Cl oudl dlet Up/Down Downlink Up/ p/Down Downlink Edg dge Networ work Visualization by Reinhold Preiner using TAM: https://github.com/rpreiner/tam 14 Simulation data from faas-sim: https://github.com/edgerun/faas-sim

N o d e L i n k I n t e r n e t B a c k h a u l C o n n e c t i o n C e l l U p / D o w n l i n k L a t e n c y : 0 . 5 m s B W: 3 0 0 M B / s L A N C e l l github.com/edgerun/ether S h a r e d L i n k C e l l C l o u d l e t I o T C o m p u t e C e l l Dipl.-Ing. (MSc), BSc Thomas Rausch Research Assistant TU Wien Information Systems Engineering Argentinierstrasse 8-194-02, Vienna, Austria T : +43 1 58801-184838 E : trausch@dsg.tuwien.ac.at https://dsg.tuwien.ac.at/staff/trausch 15