Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

GENIO: Synergizing Edge Computing with Optical Network Infrastructures

Carmine Cesarano, Alessio Foggia, Gianluca Roscigno, Luca Andreani, Roberto Natella

TL;DR

The paper addresses the challenge of delivering low-latency, bandwidth-intensive edge services within existing telecom access networks by integrating edge computing into Passive Optical Network (PON) infrastructures. It proposes the GENIO platform, a three-layer (cloud, edge, far edge) architecture with MADE Cloud/Edge/Far Edge and ECSO running on disaggregated OLTs (dOLT) to orchestrate and execute edge workloads using VOLTHA/ONOS and Kubernetes. Through PureEdgeSim-based experiments on off-the-shelf hardware, GENIO demonstrates feasibility and outperforms a traditional edge setup across smart city, e-health, smart building, and AI-generated content workloads, highlighting reductions in latency and improvements in task success rates. The work indicates GENIO's practical value for telecom operators to repurpose existing PON infrastructure into a scalable, secure distributed edge, with potential applicability to 5G and IoT deployments.

Abstract

Edge computing has emerged as a paradigm to bring low-latency and bandwidth-intensive applications close to end-users. However, edge computing platforms still face challenges related to resource constraints, connectivity, and security. We present GENIO, a novel platform that integrates edge computing within existing Passive Optical Network (PON) infrastructures. GENIO enhances central offices with computational and storage resources, enabling telecom operators to leverage their existing PON networks as a distributed edge computing infrastructure. Through simulations, we show the feasibility of GENIO in supporting real-world edge scenarios, and its better performance compared to a traditional edge computing architecture.

GENIO: Synergizing Edge Computing with Optical Network Infrastructures

TL;DR

The paper addresses the challenge of delivering low-latency, bandwidth-intensive edge services within existing telecom access networks by integrating edge computing into Passive Optical Network (PON) infrastructures. It proposes the GENIO platform, a three-layer (cloud, edge, far edge) architecture with MADE Cloud/Edge/Far Edge and ECSO running on disaggregated OLTs (dOLT) to orchestrate and execute edge workloads using VOLTHA/ONOS and Kubernetes. Through PureEdgeSim-based experiments on off-the-shelf hardware, GENIO demonstrates feasibility and outperforms a traditional edge setup across smart city, e-health, smart building, and AI-generated content workloads, highlighting reductions in latency and improvements in task success rates. The work indicates GENIO's practical value for telecom operators to repurpose existing PON infrastructure into a scalable, secure distributed edge, with potential applicability to 5G and IoT deployments.

Abstract

Edge computing has emerged as a paradigm to bring low-latency and bandwidth-intensive applications close to end-users. However, edge computing platforms still face challenges related to resource constraints, connectivity, and security. We present GENIO, a novel platform that integrates edge computing within existing Passive Optical Network (PON) infrastructures. GENIO enhances central offices with computational and storage resources, enabling telecom operators to leverage their existing PON networks as a distributed edge computing infrastructure. Through simulations, we show the feasibility of GENIO in supporting real-world edge scenarios, and its better performance compared to a traditional edge computing architecture.

Paper Structure

This paper contains 16 sections, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Background
  3. GENIO Platform Architecture
  4. Overview
  5. MADE Cloud
  6. MADE Edge
  7. Made Far Edge
  8. Interactions between MADE Cloud and MADE Edge
  9. ECSO
  10. Security-by-design
  11. Use Cases and Simulation
  12. Edge Computing Scenarios
  13. Simulation environment
  14. Hardware configurations
  15. Experimental Results
  16. ...and 1 more sections

Figures (4)

  • Figure 1: Traditional PON topology for the access network.
  • Figure 2: On the left, the deployment of GENIO across cloud, edge, and far edge layers. On the right, the GENIO software architecture, which includes the MADE and ECSO components
  • Figure 3: Simulation environment for the GENIO setup in PureEdgeSim
  • Figure 4: Latency and task success rate comparison across four edge scenarios, contrasting GENIO and baseline architectures for different CPU types.