pith. sign in

arxiv: 1906.09962 · v1 · pith:G7I6I2Q2new · submitted 2019-06-21 · 💻 cs.DC

A Language for Programming Edge Clouds for Next Generation IoT Applications

Muthucumaru Maheswaran , Robert Wenger , Richard Olaniyan , Salman Memon , Olamilekan Fadahunsi , Richboy Echomgbe This is my paper

Pith reviewed 2026-05-25 19:05 UTC · model grok-4.3

classification 💻 cs.DC
keywords edge computingIoTprogramming languagefog computingdistributed nodestask placementmiddlewaredata filtering
0
0 comments X

The pith

A distributed-node programming language lets developers write IoT apps once and map tasks across cloud, fog, and device levels while handling failover and hotspots.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces a programming language and middleware for partitioning IoT applications into tasks that run on cloud, fog, and device tiers. It focuses on four specific concerns: placing tasks at the right level, filtering data to reduce network load, managing fog failover and data consistency, and responding to edge hotspots. The language uses a distributed-node model in which a single program targets a hierarchy of nodes rather than individual machines. This model supports new patterns for cognitive and data-heavy workloads, shown through a prototype implementation, a distributed shell, and a smart parking application.

Core claim

The unique distributed-node programming model embodied in the language enables new edge-oriented programming patterns that are highly suitable for cognitive or data-intensive edge computing workloads by addressing task placement at different levels, data filtering to limit network loading, fog fail-over, data consistency, and reacting to hotspots at the edge.

What carries the argument

The distributed-node programming model, which lets a program target a collection of nodes organized into a cloud-fog-device hierarchy.

Load-bearing premise

That one language and middleware can handle task placement, data filtering, failover, consistency, and hotspot reaction without unacceptable overhead or complexity in real deployments.

What would settle it

A test run of the smart parking app on the prototype where task placement fails to meet quality-of-service targets or failover causes data loss under simulated hotspot load would disprove the central claim.

read the original abstract

For effective use of edge computing in an IoT application, we need to partition the application into tasks and map them into the cloud, fog (edge server), device levels such that the resources at the different levels are optimally used to meet the overall quality of service requirements. In this paper, we consider four concerns about application-to-fog mapping: task placement at different levels, data filtering to limit network loading, fog fail-over, and data consistency, and reacting to hotspots at the edge. We describe a programming language and middleware we created for edge computing that addresses the above four concerns. The language has a distributed-node programming model that allows programs to be written for a collection of nodes organized into a cloud, fog, device hierarchy. The paper describes the major design elements of the language and explains the prototype implementation. The unique distributed-node programming model embodied in the language enables new edge-oriented programming patterns that are highly suitable for cognitive or data-intensive edge computing workloads. The paper presents result from an initial evaluation of the language prototype and also a distributed shell and a smart parking app that were developed using the programming language.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The paper introduces a programming language and associated middleware for edge-cloud IoT applications. It uses a distributed-node programming model to partition and map tasks across cloud, fog, and device levels, addressing four concerns: task placement, data filtering to reduce network load, fog fail-over and data consistency, and reaction to edge hotspots. The manuscript describes the language design, prototype implementation, and an initial evaluation consisting of a distributed shell and a smart-parking application.

Significance. If the distributed-node model demonstrably solves the four listed concerns without unacceptable overhead or complexity, the work would offer a concrete programming abstraction that could simplify development of cognitive and data-intensive edge workloads. The absence of quantitative performance data in the reported evaluation, however, leaves this potential unverified.

major comments (1)
  1. [initial evaluation] The initial-evaluation section reports only that a distributed shell and smart-parking application were developed; it supplies no latency, bandwidth, failover-time, consistency-cost, or hotspot-reaction measurements, nor any comparison against baselines. Consequently the central claim that the language addresses the four concerns without unacceptable overhead remains unsupported by evidence.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. We address the major comment regarding the evaluation section below.

read point-by-point responses

  1. Referee: [initial evaluation] The initial-evaluation section reports only that a distributed shell and smart-parking application were developed; it supplies no latency, bandwidth, failover-time, consistency-cost, or hotspot-reaction measurements, nor any comparison against baselines. Consequently the central claim that the language addresses the four concerns without unacceptable overhead remains unsupported by evidence.

    Authors: We agree that the initial evaluation section is limited to describing the development of the prototypes without quantitative measurements or baseline comparisons. This leaves the claims about addressing the four concerns (task placement, data filtering, failover/consistency, and hotspot reaction) without supporting performance evidence. The section was intended as a feasibility demonstration, but we acknowledge the referee's point that this is insufficient to substantiate the central claims. In the revised manuscript we will expand the evaluation with the requested metrics (latency, bandwidth, failover time, consistency cost, hotspot reaction) and comparisons against baselines. revision: yes

Circularity Check

0 steps flagged

No significant circularity; design claims rest on external prototype evaluation rather than self-referential reduction.

full rationale

The paper introduces a new distributed-node programming language and middleware to address task placement, data filtering, failover, consistency, and hotspots. No equations, fitted parameters, or derivation steps appear in the provided text. The central claim—that the language model enables suitable patterns—is presented as a design contribution whose value is to be assessed by external use and prototype apps (distributed shell, smart parking), not by any internal reduction to its own inputs. No self-citations are invoked as load-bearing uniqueness theorems, and no ansatz or renaming patterns are present. The absence of quantitative metrics is a verification gap, not a circularity issue.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 1 invented entities

The paper introduces a new language artifact; no free parameters, standard axioms, or invented physical entities are described. The distributed-node model is the core invention but lacks independent evidence beyond the prototype claim.

invented entities (1)
  • distributed-node programming model no independent evidence
    purpose: To allow programs written for collections of nodes in cloud-fog-device hierarchy
    Core new abstraction presented in the language; no external falsifiable evidence provided in abstract

pith-pipeline@v0.9.0 · 5748 in / 1125 out tokens · 17615 ms · 2026-05-25T19:05:56.255016+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A Fog Computing Framework for Autonomous Driving Assist: Architecture, Experiments, and Challenges

    eess.SP 2019-07 unverdicted novelty 3.0

    Proposes fog computing architecture with edge twins, ML forecasters for vehicle locations, and a box algorithm for hazard maps to assist autonomous driving, evaluated via simulations on real highway traces.

Reference graph

Works this paper leans on

41 extracted references · 41 canonical work pages · cited by 1 Pith paper · 1 internal anchor

  1. [1]

    Edge analytics in the internet of things.IEEE Pervasive Computing 2015; 14(2): 24–31

    Satyanarayanan M, Simoens P, Xiao Y, et al. Edge analytics in the internet of things.IEEE Pervasive Computing 2015; 14(2): 24–31

    work page 2015

  2. [2]

    The promise of edge computing.Computer2016; 49(5): 78–81

    Shi W, Dustdar S. The promise of edge computing.Computer2016; 49(5): 78–81

    work page

  3. [3]

    ETSI white paper 2015; 11(11): 1–16

    HuYC,PatelM,SabellaD,SprecherN,YoungV.Mobileedgecomputing:Akeytechnologytowards5G. ETSI white paper 2015; 11(11): 1–16

    work page 2015

  4. [4]

    Pervasive computing: Vision and challenges.IEEE Personal communications 2001; 8(4): 10–17

    Satyanarayanan M. Pervasive computing: Vision and challenges.IEEE Personal communications 2001; 8(4): 10–17

    work page 2001

  5. [5]

    Software-defined networking.INFOCOM keynote talk 2009; 17(2): 30–32

    McKeown N. Software-defined networking.INFOCOM keynote talk 2009; 17(2): 30–32

    work page 2009

  6. [6]

    Software-defined networking.Communications of the ACM 2013; 56(9): 16–19

    Kirkpatrick K. Software-defined networking.Communications of the ACM 2013; 56(9): 16–19

    work page 2013

  7. [7]

    P4: Programming protocol-independent packet processors.ACM SIGCOMM Computer Communication Review 2014; 44(3): 87–95

    Bosshart P, Daly D, Gibb G, et al. P4: Programming protocol-independent packet processors.ACM SIGCOMM Computer Communication Review 2014; 44(3): 87–95

    work page 2014

  8. [8]

    OpenFlow: enabling innovation in campus networks.ACM SIGCOMM Computer Communication Review 2008; 38(2): 69–74

    McKeown N, Anderson T, Balakrishnan H, et al. OpenFlow: enabling innovation in campus networks.ACM SIGCOMM Computer Communication Review 2008; 38(2): 69–74

    work page 2008

  9. [9]

    A network in a laptop: rapid prototyping for software-defined networks

    Lantz B, Heller B, McKeown N. A network in a laptop: rapid prototyping for software-defined networks. In: ACM. ; 2010: 19

    work page 2010

  10. [10]

    A hierarchical distributed fog computing architecture for big data analysis in smart cities

    Tang B, Chen Z, Hefferman G, Wei T, He H, Yang Q. A hierarchical distributed fog computing architecture for big data analysis in smart cities. In: ACM. ; 2015: 28. M. MaheswaranET AL 21

    work page 2015

  11. [11]

    Mobile fog: A programming model for large-scale applications on the internet of things

    Hong K, Lillethun D, Ramachandran U, Ottenwälder B, Koldehofe B. Mobile fog: A programming model for large-scale applications on the internet of things. In: ACM. ; 2013: 15–20

    work page 2013

  12. [12]

    Fog Computing: Focusing on Mobile Users at the Edge

    Luan TH, Gao L, Li Z, Xiang Y, Wei G, Sun L. Fog computing: Focusing on mobile users at the edge.arXiv preprint arXiv:1502.018152015

    work page internal anchor Pith review Pith/arXiv arXiv

  13. [13]

    2014: 117–122

    StojmenovicI.Fogcomputing:Acloudtothegroundsupportforsmartthingsandmachine-to-machinenetworks.In:IEEE. ; 2014: 117–122

    work page 2014

  14. [14]

    ACM SIGCOMM Computer Communication Review 2015; 45(5): 37–42

    GarciaLopezP,MontresorA,EpemaD,etal.Edge-centriccomputing:Visionandchallenges. ACM SIGCOMM Computer Communication Review 2015; 45(5): 37–42

    work page 2015

  15. [15]

    Cambridge University Press

    Liang B.Mobile edge computing. Cambridge University Press . 2017

    work page 2017

  16. [16]

    State machine replication for the masses with BFT-SMaRt

    Bessani A, Sousa J, Alchieri EE. State machine replication for the masses with BFT-SMaRt. In: IEEE. ; 2014: 355–362

    work page 2014

  17. [17]

    Fault tolerance-challenges, techniques and implementation in cloud computing.IJCSI International Journal of Computer Science Issues 2012; 9(1): 1694–0814

    Bala A, Chana I. Fault tolerance-challenges, techniques and implementation in cloud computing.IJCSI International Journal of Computer Science Issues 2012; 9(1): 1694–0814

    work page 2012

  18. [18]

    Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing

    Zaharia M, Chowdhury M, Das T, et al. Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing. In: USENIX Association. ; 2012: 2–2

    work page 2012

  19. [19]

    Load-balancing clusters in wireless ad hoc networks

    Amis AD, Prakash R. Load-balancing clusters in wireless ad hoc networks. In: IEEE. ; 2000: 25–32

    work page 2000

  20. [20]

    Sparrow: distributed, low latency scheduling

    Ousterhout K, Wendell P, Zaharia M, Stoica I. Sparrow: distributed, low latency scheduling. In: ACM. ; 2013: 69–84

    work page 2013

  21. [21]

    Probabilistic Recovery of Incomplete Sensed Data in IoT.IEEE Internet of Things Journal 2017

    Fekade B, Maksymyuk T, Kyryk M, Jo M. Probabilistic Recovery of Incomplete Sensed Data in IoT.IEEE Internet of Things Journal 2017

    work page 2017

  22. [22]

    Incremental packrat parsing

    Dubroy P, Warth A. Incremental packrat parsing. In: ACM. ; 2017: 14–25

    work page 2017

  23. [23]

    MQTT-Sâ/uni0102/uni0164A publish/subscribe protocol for Wireless Sensor Networks

    Hunkeler U, Truong HL, Stanford-Clark A. MQTT-Sâ/uni0102/uni0164A publish/subscribe protocol for Wireless Sensor Networks. In: IEEE. ; 2008: 791–798

    work page 2008

  24. [24]

    Manning Publications Co

    Carlson JL.Redis in action. Manning Publications Co. . 2013

    work page 2013

  25. [25]

    SimmhanY,ChoudhuryN,WickramaarachchiC,etal.Distributedprogrammingovertime-seriesgraphs.In:IEEE.;2015: 809–818

    work page 2015

  26. [26]

    SDIoT: a software defined based internet of things framework

    Jararweh Y, Al-Ayyoub M, Benkhelifa E, Vouk M, Rindos A, others . SDIoT: a software defined based internet of things framework. Journal of Ambient Intelligence and Humanized Computing 2015; 6(4): 453–461

    work page 2015

  27. [27]

    Software-defined internet of things for smart urban sensing.IEEE communications magazine2015; 53(9): 55–63

    Liu J, Li Y, Chen M, Dong W, Jin D. Software-defined internet of things for smart urban sensing.IEEE communications magazine2015; 53(9): 55–63

    work page

  28. [28]

    SPF: an SDN-based middleware solution to mitigate the IoT information explosion

    Tortonesi M, Michaelis J, Morelli A, Suri N, Baker MA. SPF: an SDN-based middleware solution to mitigate the IoT information explosion. In: IEEE. ; 2016: 435–442

    work page 2016

  29. [29]

    In: IEEE

    JararwehY,DoulatA,DarabsehA,AlsmiratM,Al-AyyoubM,BenkhelifaE.SDMEC:Softwaredefinedsystemformobile edge computing. In: IEEE. ; 2016: 88–93

    work page 2016

  30. [30]

    In: IEEE

    TruongNB,LeeGM,Ghamri-DoudaneY.Softwaredefinednetworking-basedvehicularadhocnetworkwithfogcomputing. In: IEEE. ; 2015: 1202–1207

    work page 2015

  31. [31]

    MIST: Mobility-inspired software-defined fog system

    Gebre-Amlak H, Lee S, Jabbari AM, et al. MIST: Mobility-inspired software-defined fog system. In: IEEE. ; 2017: 94–99

    work page 2017

  32. [32]

    rtgovops: A runtime framework for governance in large-scale software-defined iot cloud systems

    Nastic S, Vögler M, Inzinger C, Truong HL, Dustdar S. rtgovops: A runtime framework for governance in large-scale software-defined iot cloud systems. In: IEEE. ; 2015: 24–33

    work page 2015

  33. [33]

    Software-defined storage.Report2013

    Wu F, Sun G. Software-defined storage.Report2013. 22 M. MaheswaranET AL

    work page

  34. [34]

    In: IEEE

    Al-AyyoubM,JararwehY,BenkhelifaE,VoukM,RindosA,others.Sdsecurity:Asoftwaredefinedsecurityexperimental framework. In: IEEE. ; 2015: 1871–1876

    work page 2015

  35. [35]

    Software-defined mobility management: Architecture proposal and future directions.Mobile Networks and Applications 2016; 21(2): 226–236

    Contreras LM, Cominardi L, Qian H, Bernardos CJ. Software-defined mobility management: Architecture proposal and future directions.Mobile Networks and Applications 2016; 21(2): 226–236

    work page 2016

  36. [36]

    Orleans: cloud computing for everyone

    Bykov S, Geller A, Kliot G, Larus JR, Pandya R, Thelin J. Orleans: cloud computing for everyone. In: ACM. ; 2011: 16

    work page 2011

  37. [37]

    Dripcast–Server-less Java Programming Framework for Billions of IoT Devices

    Nakagawa I, Hiji M, Esaki H. Dripcast–Server-less Java Programming Framework for Billions of IoT Devices. In: IEEE. ; 2014: 186–191

    work page 2014

  38. [38]

    Calvin–merging cloud and iot.Procedia Computer Science 2015; 52: 210–217

    Persson P, Angelsmark O. Calvin–merging cloud and iot.Procedia Computer Science 2015; 52: 210–217

    work page 2015

  39. [39]

    Simurgh: A framework for effective discovery, programming, and integration of services exposed in IoT

    Khodadadi F, Dastjerdi AV, Buyya R. Simurgh: A framework for effective discovery, programming, and integration of services exposed in IoT. In: IEEE. ; 2015: 1–6

    work page 2015

  40. [40]

    Odessa: enabling interactive perception applications on mobile devices

    Ra MR, Sheth A, Mummert L, Pillai P, Wetherall D, Govindan R. Odessa: enabling interactive perception applications on mobile devices. In: ACM. ; 2011: 43–56

    work page 2011

  41. [41]

    Slipstream: scalable low-latency interactive perception on streaming data

    Pillai PS, Mummert LB, Schlosser SW, Sukthankar R, Helfrich CJ. Slipstream: scalable low-latency interactive perception on streaming data. In: ACM. ; 2009: 43–48

    work page 2009