5G Architect Jobs (NOW HIRING)

Jul 02, 2026 4 min read

PROJ Service Migration in Cellular Networks

This project has three focus parts: Cellular Networks Testbed, LLMs, and optimization algorithms.

Cellular Networks Testbed

Image from: Real-Time Service Migration in Edge Networks: A Survey

The testbed architecture spans four tiers: Central Cloud, Regional MEC, Aggregation MEC, and Local MEC.Primary focus: Regional MEC and Aggregation MEC.Regional MEC, Aggregation MEC, and Local MEC should be deployed to my PVE Testbed.

Each MEC site (or per Metro (metropolitan area) / PoP (Point of Presence)) needs its own control plane because:

• Survivability: If WAN/backhaul drops, the site keeps running. A single, stretched cluster loses control-plane access and flakes.
• Latency/etcd constraints: Kubernetes control-plane (etcd) hates WAN latency/packet-loss; cross-site RTTs >~5-10 ms and jitter cause elections and outages.
• Blast radius & upgrades: Failures and rollouts stay local, enabling per-site upgrades.
• Regulatory / tenancy: Site-level isolation simplifies policy and compliance.

TODO Central Cloud

Cloud (Azure)High-level design: Azure Virtual WAN (Standard) with four hubs in a full inter-hub mesh. Regional spokes (AKS VNets) attach to their nearest hub; inter-hub routing provides global any-to-any.

Regions (paired for HA/DR):

• East US 2 (VA) - primary; paired with Central US (closest to UVA)
• Central US (IA) - DR for East US 2
• West US 3 (AZ) - west capacity/DR; paired with East US
• East US (VA) - additional east capacity and the formal pair for West US/West US 3

(All selected regions provide Availability Zones.)

TODO Regional MEC (e.g., Richmond PoP)

50-200 km coverage | RTT to Aggregation 15-30 msUse cases: smart city, cloud gaming, content deliveryComponents: SMF/AMF/PCF (control plane) + Regional UPF

10-50 km coverage | RTT to Local: 10-20 msUse cases: campus control, local CDN

OKD (3 master nodes)Components: SMF/AMF/PCF (control plane) + optional Aggregation UPF

TODO Local MEC

Components: Local UPFDeploy two OKD SNOs or MicroShift clusters (MEC-1: Campus South; MEC-2: Campus North)

N3 (gNB to UPF @ MEC): VLAN/VRF local to the site, low jitterN6 (UPF to campus/ISP): routed toward the PoP

Digital Twin

Must implement N2, N3, and optionally Xn. Focus on mmWave.

Focus on multi-agent workflow design and LLM fine-tuning.

ETSI = European Telecommunications Standards Institute

Famous work includes ETSI MEC (edge computing) and the original ETSI NFV effort.

Deploy Three LLMs to Regional MEC or Aggregation MEC:

Mobility Predictor Agent (MPA) Aggregation MEC / Local MEC (Near-RT RIC/O-RAN Layer) Context Generation: Provides real-time prediction of UE handover and mobility patterns to anticipate service relocation. Real-time Radio KPIs (RSRP, RSRQ), Handover/Xn/N2 events, UE location/velocity. Proactive Migration: Essential for timely initiation of migration at the lowest latency tiers, ensuring QoE under high mobility.

MEC Resource Agent (RCA) All Managed MEC Sites (Local, Aggregation, Regional) Local State Reporting: Monitors the instantaneous resource utilization and available capacity of its local compute cluster (OKD/MicroShift) CPU/Memory/GPU load, Available network bandwidth, K8s/OKD/MicroShift node metrics. Survivability and Autonomy: Guarantees that every control-plane instance has local resource awareness, upholding isolation and independence

Migration Planner Agent (PLA) Regional MEC and Aggregation MEC (Control Plane) Decision-Making: Determines the optimal migration target, timing, and method based on its scope (Local -> Local vs. Regional -> Regional). Aggregated Predictions (MPA data), Resource Availability (RCA reports), Service SLOs, Migration Cost Model. Hierarchical/Decentralized Decision: Enables ultra-low-latency decision-making for local PoP movements and wide-area optimization, avoiding high Central Cloud RTT

State/Traffic Steering Agent (TSA) Co-located with SMF/UPF Execution & Cutover: Executes the migration by coordinating state transfer and updating the 5G Core traffic rules PLA’s Decision (Target MEC ID), State Transfer Status, 5G Core N4/N11 APIs (for UPF/SMF control plane updates) Critical Service Continuity: Directly implements the necessary 5G Core control procedures (PSA Relocation/UL-CL) at all anchor points to shift traffic seamlessly

Policy Enforcement Agent (PEA) Central Cloud (Azure) Global Policy Management: Distributes high-level, long-term policies, cost objectives, and optimization models across all PLA instances Long-term historical data, Global business objectives, Failure tolerance settings, Regulatory/Tenancy policies. Global Governance: Provides the top-level goals and learning feedback to the decentralized PLA instances, ensuring consistency and alignment with global business objectives.