skip to main content

Explore Research Products in the NSF-PAR

Title: A Decomposition-based Architecture for Distributed Cyber-Foraging of Multiple Edge Functions
Edge computing is an emerging paradigm whose goal is to boost with cloud resources available at the edge the computational capability of otherwise weak devices. This paradigm is mostly attractive to reduce user perceived latency. A central mechanism in edge computing is cyber-foraging, i.e., the search and delegation to capable edge cloud processes of tasks too complex, time consuming or resource intensive to be running on user devices or low-latency demanding to be running remotely, as a form of edge function. An edge function is any network or device-specific process that may be run on an edge process instead. Despite the recent interest for this technology from industry and academia, cyber-foraging techniques and protocols have yet to be standardized. In this paper, we leverage decomposition theory to propose an architecture providing insights in the design and implementation of protocols for cyber-foraging of multiple edge functions. In contrast with several existing solutions, we argue that the (distributed) cyber-foraging orchestration should be policy-based and not an ad-hoc solution, i.e., either a pure edge cloud burden or a device decision. To this end, via simulations, we show how our approach can be used by edge computing providers and application programmers to compare and evaluate different alternative cyber-foraging solutions. Our decomposition-based approach has general applicability to other network utility maximization problems, even outside the edge computing domain.  more » « less
Award ID(s):
1647084
NSF-PAR ID:
10082118
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
2018 4th IEEE Conference on Network Softwarization and Workshops (NetSoft)
Page Range / eLocation ID:
247 to 251
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ( , ACM Symposium on Edge Computing)
    null (Ed.)
    Internet of Things (IoT) devices are becoming increasingly prevalent in our environment, yet the process of programming these devices and processing the data they produce remains difficult. Typically, data is processed on device, involving arduous work in low level languages, or data is moved to the cloud, where abundant resources are available for Functions as a Service (FaaS) or other handlers. FaaS is an emerging category of flexible computing services, where developers deploy self-contained functions to be run in portable and secure containerized environments; however, at the moment, these functions are limited to running in the cloud or in some cases at the "edge" of the network using resource rich, Linux-based systems. In this work, we investigate NanoLambda, a portable platform that brings FaaS, high-level language programming, and familiar cloud service APIs to non-Linux and microcontroller-based IoT devices. To enable this, NanoLambda couples a new, minimal Python runtime system that we have designed for the least capable end of the IoT device spectrum, with API compatibility for AWS Lambda and S3. NanoLambda transfers functions between IoT devices (sensors, edge, cloud), providing power and latency savings while retaining the programmer productivity benefits of high-level languages and FaaS. A key feature of NanoLambda is a scheduler that intelligently places function executions across multi-scale IoT deployments according to resource availability and power constraints. We evaluate a range of applications that use NanoLambda to run on devices as small as the ESP8266 with 64KB of ram and 512KB flash storage. 
    more » « less
  2. ; ( , 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON))
    null (Ed.)
    In recent years, the addition of billions of Internet of Thing (IoT) device spawned a massive demand for computing service near the edge of the network. Due to latency, limited mobility, and location awareness, cloud computing is not capable enough to serve these devices. As a result, the focus is shifting more towards distributed platform service to put ample computing power near the edge of the networks. Thus, paradigms such as Fog and Edge computing are gaining attention from researchers as well as business stakeholders. Fog computing is a new computing paradigm, which places computing nodes in between the Cloud and the end user to reduce latency and increase availability. As an emerging technology, Fog computing also brings newer security challenges for the stakeholders to solve. Before designing the security models for Fog computing, it is better to understand the existing threats to Fog computing. In this regard, a thorough threat model can significantly help to identify these threats. Threat modeling is a sophisticated engineering process by which a computer-based system is analyzed to discover security flaws. In this paper, we applied two popular security threat modeling processes - CIAA and STRIDE - to identify and analyze attackers, their capabilities and motivations, and a list of potential threats in the context of Fog computing. We posit that such a systematic and thorough discussion of a threat model for Fog computing will help security researchers and professionals to design secure and reliable Fog computing systems. 
    more » « less
  3. ; ( , IEEE UEMCON 2019)
    In recent years, the addition of billions of Internet of Thing (IoT) device spawned a massive demand for computing service near the edge of the network. Due to latency, limited mobility, and location awareness, cloud computing is not capable enough to serve these devices. As a result, the focus is shifting more towards distributed platform service to put ample com- puting power near the edge of the networks. Thus, paradigms such as Fog and Edge computing are gaining attention from researchers as well as business stakeholders. Fog computing is a new computing paradigm, which places computing nodes in between the Cloud and the end user to reduce latency and increase availability. As an emerging technology, Fog computing also brings newer security challenges for the stakeholders to solve. Before designing the security models for Fog computing, it is better to understand the existing threats to Fog computing. In this regard, a thorough threat model can significantly help to identify these threats. Threat modeling is a sophisticated engineering process by which a computer-based system is analyzed to discover security flaws. In this paper, we applied two popular security threat modeling processes – CIAA and STRIDE – to identify and analyze attackers, their capabilities and motivations, and a list of potential threats in the context of Fog computing. We posit that such a systematic and thorough discussion of a threat model for Fog computing will help security researchers and professionals to design secure and reliable Fog computing systems. 
    more » « less
  4. ; ; ( , 2018 4th IEEE Conference on Network Softwarization and Workshops (NetSoft))
    Cyber foraging techniques have been proposed in edge computing to support resource-intensive and latency-sensitive mobile applications. In a natural or man-made disaster scenario, all cyber foraging challenges are exacerbated by two problems: edge nodes are scarce and hence easily overloaded and failures are common due to the ad-hoc hostile conditions. In this paper, we study the use of efficient load profiling and migration strategies to mitigate such problems. In particular, we propose FORMICA, an architecture for cyber foraging orchestration, whose goal is to minimize the completion time of a set of jobs offloaded from mobile devices. Existing service offloading solutions are mainly concerned with outsourcing a job out of the mobile responsibility. Our architecture supports both mobile-based offloading and backend-driven onloading i.e., the offloading decision is taken by the edge infrastructure and not by the mobile node. FORMICA leverages Gelenbe networks to estimate the load profile of each node of the edge computing infrastructure to make proactive load profiling decisions. Our evaluation on a proof-of-concept implementation shows the benefits of our policy-based architecture in several (challenged disaster) scenarios but its applicability is broad to other IoT-based latency-sensitive applications. 
    more » « less
  5. ; ; ; ( , The International Journal of High Performance Computing Applications)

    Data volumes are exploding as sensors proliferate and become more capable. Edge computing is envisioned as a path to distribute processing and reduce latency. Many models of Edge computing consider small devices running conventional software. Our model includes a more lightweight execution engine for network microservices and a network scheduling framework to configure network processing elements to process streams and direct the appropriate traffic to them. In this article, we describe INDIANA, a complete framework for in-network microservices. We will describe how the two components-the INDIANA network Processing Element (InPE) and the Flange Network Operating System (NOS)-work together to achieve effective in-network processing to improve performance in edge to cloud environments. Our processing elements provide lightweight compute units optimized for efficient stream processing. These elements are customizable and vary in sophistication and resource consumption. The Flange NOS provides first-class flow based reasoning to drive function placement, network configuration, and load balancing that can respond dynamically to network conditions. We describe design considerations and discuss our approach and implementations. We evaluate the performance of stream processing and examine the performance of several exemplar applications on networks of increasing scale and complexity.

     
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email