Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Decentralized and Self-Adaptive Approach for Monitoring Volatile Edge Environments

Shashikant Ilager, Jakob Fahringer, Alessandro Tundo, Ivona Brandić

TL;DR

This paper tackles the limitations of centralized monitoring in volatile edge environments by proposing DEMon, a completely decentralized and self-adaptive monitoring system. DEMon combines a gossip-based information dissemination layer with a Leaderless Quorum Consensus (LQC) retrieval mechanism to ensure fast, trustworthy access to monitoring data without a central controller. The authors implement a lightweight Python prototype (SR, IDC, IRC, DQC) and validate it through extensive container-based experiments and a Raspberry Pi edge-use-case, demonstrating fast convergence, low resource usage, and robust data retrieval even under high node churn or failures. The work offers practical impact for edge and IoT deployments by enabling scalable, trustable, and low-overhead monitoring that supports latency-sensitive offloading and resource management, while outlining future directions for richer query support and security features.

Abstract

Edge computing provides resources for IoT workloads at the network edge. Monitoring systems are vital for efficiently managing resources and application workloads by collecting, storing, and providing relevant information about the state of the resources. However, traditional monitoring systems have a centralized architecture for both data plane and control plane, which increases latency, creates a failure bottleneck, and faces challenges in providing quick and trustworthy data in volatile edge environments, especially where infrastructures are often built upon failure-prone, unsophisticated computing and network resources. Thus, we propose DEMon, a decentralized, self-adaptive monitoring system for edge. DEMon leverages the stochastic gossip communication protocol at its core. It develops efficient protocols for information dissemination, communication, and retrieval, avoiding a single point of failure and ensuring fast and trustworthy data access. Its decentralized control enables self-adaptive management of monitoring parameters, addressing the trade-offs between the quality of service of monitoring and resource consumption. We implement the proposed system as a lightweight and portable container-based system and evaluate it through experiments. We also present a use case demonstrating its feasibility. The results show that DEMon efficiently disseminates and retrieves the monitoring information, addressing the challenges of edge monitoring.

A Decentralized and Self-Adaptive Approach for Monitoring Volatile Edge Environments

TL;DR

This paper tackles the limitations of centralized monitoring in volatile edge environments by proposing DEMon, a completely decentralized and self-adaptive monitoring system. DEMon combines a gossip-based information dissemination layer with a Leaderless Quorum Consensus (LQC) retrieval mechanism to ensure fast, trustworthy access to monitoring data without a central controller. The authors implement a lightweight Python prototype (SR, IDC, IRC, DQC) and validate it through extensive container-based experiments and a Raspberry Pi edge-use-case, demonstrating fast convergence, low resource usage, and robust data retrieval even under high node churn or failures. The work offers practical impact for edge and IoT deployments by enabling scalable, trustable, and low-overhead monitoring that supports latency-sensitive offloading and resource management, while outlining future directions for richer query support and security features.

Abstract

Edge computing provides resources for IoT workloads at the network edge. Monitoring systems are vital for efficiently managing resources and application workloads by collecting, storing, and providing relevant information about the state of the resources. However, traditional monitoring systems have a centralized architecture for both data plane and control plane, which increases latency, creates a failure bottleneck, and faces challenges in providing quick and trustworthy data in volatile edge environments, especially where infrastructures are often built upon failure-prone, unsophisticated computing and network resources. Thus, we propose DEMon, a decentralized, self-adaptive monitoring system for edge. DEMon leverages the stochastic gossip communication protocol at its core. It develops efficient protocols for information dissemination, communication, and retrieval, avoiding a single point of failure and ensuring fast and trustworthy data access. Its decentralized control enables self-adaptive management of monitoring parameters, addressing the trade-offs between the quality of service of monitoring and resource consumption. We implement the proposed system as a lightweight and portable container-based system and evaluate it through experiments. We also present a use case demonstrating its feasibility. The results show that DEMon efficiently disseminates and retrieves the monitoring information, addressing the challenges of edge monitoring.
Paper Structure (27 sections, 12 figures, 3 tables, 3 algorithms)

This paper contains 27 sections, 12 figures, 3 tables, 3 algorithms.

Table of Contents

  1. Introduction
  2. Motivation and Background
  3. A Use Case for a Decentralized Edge Monitoring System
  4. Gossip Protocol
  5. DEMon: Decentralised Edge Monitoring and Control
  6. State Repository (SR)
  7. Information Dissemination Controller (IDC)
  8. Nodes Network Management
  9. Node Insertion
  10. Node Deletion
  11. State Repository Management
  12. Illustration and Running Example of the IDC
  13. Information Retrieval Controller(IRC)
  14. DEMon Query Client (DQC)
  15. Prototype Implementation
  16. ...and 12 more sections

Figures (12)

  • Figure 1: An edge use case where mobile users offload a computational task to the nearest and less loaded edge node hosting an AI-based application.
  • Figure 2: The architecture of the DEMon monitoring system.
  • Figure 3: The sequence diagram of the DEMon monitoring system, illustrates the flow of messages between nodes in one round of gossiping.
  • Figure 4: Performance of gossip protocol.
  • Figure 5: A number of messages for convergence between FogMon2 and DEMon. Here, we set 3 different configurations of FogMon2 (number of Leader nodes) and gossip_count=2 for DEMon.
  • ...and 7 more figures