Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

CIVIC: Cooperative Immersion Via Intelligent Credit-sharing in DRL-Powered Metaverse

Amr Aboeleneen, Mohamed Abdallah, Aiman Erbad, Amr Salem

Abstract

The Metaverse faces complex resource allocation challenges due to diverse Virtual Environments (VEs), Digital Twins (DTs), dynamic user demands, and strict immersion needs. This paper introduces CIVIC (Cooperative Immersion Via Intelligent Credit-sharing), a novel framework optimizing resource sharing among multiple Metaverse Service Providers (MSPs) to enhance user immersion. Unlike existing methods, CIVIC integrates VE rendering, DT synchronization, credit sharing, and immersion-aware provisioning within a cooperative multi-MSP model. The resource allocation problem is formulated as two NP-hard challenges: a non-cooperative setting where MSPs operate independently and a cooperative setting utilizing a General Credit Pool (GCP) for dynamic resource sharing. Using Deep Reinforcement Learning (DRL) for tuning resources and managing cooperating MSPs, CIVIC achieves 12-36% higher request completion, 23-70% higher fulfillment rates, 20-60% more served clients, and up to 51% more fairly distributed requests, all with competitive costs. Extensive experiments demonstrate CIVIC's resilience, adaptability, and robust performance under dynamic load conditions and unexpected demand surges, making it suitable for real-world distributed Metaverse infrastructures.

CIVIC: Cooperative Immersion Via Intelligent Credit-sharing in DRL-Powered Metaverse

Abstract

The Metaverse faces complex resource allocation challenges due to diverse Virtual Environments (VEs), Digital Twins (DTs), dynamic user demands, and strict immersion needs. This paper introduces CIVIC (Cooperative Immersion Via Intelligent Credit-sharing), a novel framework optimizing resource sharing among multiple Metaverse Service Providers (MSPs) to enhance user immersion. Unlike existing methods, CIVIC integrates VE rendering, DT synchronization, credit sharing, and immersion-aware provisioning within a cooperative multi-MSP model. The resource allocation problem is formulated as two NP-hard challenges: a non-cooperative setting where MSPs operate independently and a cooperative setting utilizing a General Credit Pool (GCP) for dynamic resource sharing. Using Deep Reinforcement Learning (DRL) for tuning resources and managing cooperating MSPs, CIVIC achieves 12-36% higher request completion, 23-70% higher fulfillment rates, 20-60% more served clients, and up to 51% more fairly distributed requests, all with competitive costs. Extensive experiments demonstrate CIVIC's resilience, adaptability, and robust performance under dynamic load conditions and unexpected demand surges, making it suitable for real-world distributed Metaverse infrastructures.

Paper Structure

This paper contains 26 sections, 2 theorems, 31 equations, 11 figures, 6 tables.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORK
  3. SYSTEM MODEL
  4. Network Architecture and Entities
  5. Metaverse Service Providers (MSPs)
  6. Cluster Heads (Heads) and Virtual Rooms (VRooms)
  7. Virtual Reality Clients (VRCs)
  8. Immersion, Resource Scaling and Cost Models
  9. Immersion
  10. Resource Scalability
  11. Cost
  12. PROBLEM FORMULATION
  13. Problem $\boldsymbol{P}$: Non-cooperative setting
  14. Problem $\boldsymbol{\bar{P}}$: Cooperative setting
  15. Problems complexity
  16. ...and 11 more sections

Key Result

Theorem 1

The decision version of $\boldsymbol{\bar{P}}$ (objective eq:objective2 with constraints (c1)--(c13) and GCP update eq:pool_dynamics) is NP-hard. $\blacktriangleleft$$\blacktriangleleft$

Figures (11)

  • Figure 1: The main system model, composed of geographically distributed Metaverse service providers, serving multiple Heads who host virtual Rooms of their physical entity and enhance their clients' immersion with their DTs synchronization
  • Figure 2: The proposed Cooperative Immersion Via Intelligent Credit-sharing in DRL-Powered Metaverse (CIVIC)
  • Figure 3: Reward Convergence for non-GCP (non-cooperative) DRL solution, while increasing number of requests and number of MSPs
  • Figure 4: Comparing our non-GCP (non-cooperative) DRL-based solution to other Baselines
  • Figure 5: Assessing the DRL-based Solution tolerance
  • ...and 6 more figures

Theorems & Definitions (4)

  • Theorem 1: NP-hardness of the cooperative problem $\bar{P}$
  • proof : Proof
  • Theorem 2: NP-hardness of the non cooperative problem $\boldsymbol{P}$
  • proof : Proof