Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Optimizing Energy and Latency in 6G Smart Cities with Edge CyberTwins

Amine Abouaomar, Badr Ben Elallid, Nabil Benamar

TL;DR

This work tackles the energy-latency trade-off in 6G smart-city network slicing at scale by introducing an edge-aware CyberTwin framework that combines a hybrid scheduler, compressive-sensing digital twins, solar-energy forecasting, and PUF-based security. The method partitions latency-critical slices to centralized AI while handling delay-tolerant traffic with federated learning, aided by renewable-aware HRASS+ allocation and secure edge attestation. Key results show a 52.3% reduction in energy for non-real-time slices and URLLC latency around 0.9 ms with high SLA compliance, scalable to 50{,}000 devices/km² with modest CPU overhead, and robust 99.7% attack detection via PUF-based security. The approach offers practical impact for large-scale smart cities by enabling energy-efficient, low-latency operation across heterogeneous IoT slices while maintaining security and scalability.

Abstract

The proliferation of IoT devices in smart cities challenges 6G networks with conflicting energy-latency requirements across heterogeneous slices. Existing approaches struggle with the energy-latency trade-off, particularly for massive scale deployments exceeding 50,000 devices km. This paper proposes an edge-aware CyberTwin framework integrating hybrid federated learning for energy-latency co-optimization in 6G network slicing. Our approach combines centralized Artificial Intelligence scheduling for latency-sensitive slices with distributed federated learning for non-critical slices, enhanced by compressive sensing-based digital twins and renewable energy-aware resource allocation. The hybrid scheduler leverages a three-tier architecture with Physical Unclonable Function (PUF) based security attestation achieving 99.7% attack detection accuracy. Comprehensive simulations demonstrate 52% energy reduction for non-real-time slices compared to Diffusion-Reinforcement Learning baselines while maintaining 0.9ms latency for URLLC applications with 99.1% SLA compliance. The framework scales to 50,000 devices km with CPU overhead below 25%, validated through NS-3 hybrid simulations across realistic smart city scenarios.

Optimizing Energy and Latency in 6G Smart Cities with Edge CyberTwins

TL;DR

This work tackles the energy-latency trade-off in 6G smart-city network slicing at scale by introducing an edge-aware CyberTwin framework that combines a hybrid scheduler, compressive-sensing digital twins, solar-energy forecasting, and PUF-based security. The method partitions latency-critical slices to centralized AI while handling delay-tolerant traffic with federated learning, aided by renewable-aware HRASS+ allocation and secure edge attestation. Key results show a 52.3% reduction in energy for non-real-time slices and URLLC latency around 0.9 ms with high SLA compliance, scalable to 50{,}000 devices/km² with modest CPU overhead, and robust 99.7% attack detection via PUF-based security. The approach offers practical impact for large-scale smart cities by enabling energy-efficient, low-latency operation across heterogeneous IoT slices while maintaining security and scalability.

Abstract

The proliferation of IoT devices in smart cities challenges 6G networks with conflicting energy-latency requirements across heterogeneous slices. Existing approaches struggle with the energy-latency trade-off, particularly for massive scale deployments exceeding 50,000 devices km. This paper proposes an edge-aware CyberTwin framework integrating hybrid federated learning for energy-latency co-optimization in 6G network slicing. Our approach combines centralized Artificial Intelligence scheduling for latency-sensitive slices with distributed federated learning for non-critical slices, enhanced by compressive sensing-based digital twins and renewable energy-aware resource allocation. The hybrid scheduler leverages a three-tier architecture with Physical Unclonable Function (PUF) based security attestation achieving 99.7% attack detection accuracy. Comprehensive simulations demonstrate 52% energy reduction for non-real-time slices compared to Diffusion-Reinforcement Learning baselines while maintaining 0.9ms latency for URLLC applications with 99.1% SLA compliance. The framework scales to 50,000 devices km with CPU overhead below 25%, validated through NS-3 hybrid simulations across realistic smart city scenarios.

Paper Structure

This paper contains 34 sections, 9 equations, 4 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. 6G Network Slicing and Resource Allocation
  4. Federated Learning in Wireless Networks
  5. Digital Twins and Edge Computing
  6. Energy Optimization
  7. Security in Network Slicing
  8. System Model
  9. System Model
  10. Network Architecture
  11. Traffic Models
  12. Resource Constraints
  13. Energy Model
  14. Threat Model
  15. Problem Formulation
  16. ...and 19 more sections

Figures (4)

  • Figure 1: Energy consumption comparison across algorithms, showing the proposed framework significantly outperforms Diffusion-RL, Static Slicing, HRASS, and FedAvg.
  • Figure 2: Latency performance across slice types, showing URLLC slices consistently meeting the sub-1ms target and SLA compliance.
  • Figure 3: Latency scaling under increasing device density, with sub-1ms performance sustained up to the 50,000 devices/km² design target.
  • Figure 4: PUF-based security performance over time and per-attack detection rates, showing consistent high accuracy approaching the 99.7% security threshold across all attack types.