ESA SHINE Project Smart Handover for Integrated 5G Non-Terrestrial Networks

  • Status
    Ongoing
  • Status date
    2025-07-03
  • Activity Code
    3F.015
Objectives

The SHINE project is focused on developing a Machine Learning (ML) engine solution that aids handover decisions between non-terrestrial networks and terrestrial networks.
The SHINE project has the following main objectives:
• Define the reference operational scenario and specific use cases where ML solutions are expected to provide a handover success rate gain in integrated 5G-NTNs.
• Perform a comprehensive survey of relevant state-of-the-art from both technical literature as well as standardization and industrial-oriented developments related to ML-assisted handover procedures.
• Design and develop an ML engine able to optimize handover between two different 5G networks, with one being a satellite-based NTN.
• Develop a SW-based system-level testbed able to assess the handover procedure(s) within the reference operational scenario and capture the relevant Key Performance Indicators (KPIs).
• Test the developed solution in the SW-based system-level testbed and verify the achievable gain with respect to conventional solutions. The goal is to improve the handover success rate to reach at least 95%.
• Critical assessment of the potential of the developed ML-assisted handover procedure for commercial exploitation. Establish a development plan to further raise the Technology Readiness Level (TRL).


Example of NTN-TN handover use-case

Challenges

Integrating satellite non-terrestrial (NTN) and terrestrial (TN) networks enables ubiquitous network access, requiring 5G user equipment (UE), such as handheld devices or vehicle devices, to connect to both networks directly. In this scenario, UEs may need to perform handovers between TN and NTN networks. Optimizing the number of handovers and the success rate of switching between networks is critical to minimize service interruption. Conventionally, handover can be triggered by signal strength measurements, location information, and other parameters such as elevation angle, Timing Advance (TA) values or Doppler values exceeding a predefined threshold. However, the handover decision is also impacted by the high mobility of UEs and satellites, strict Quality of Service (QoS) requirements such as reliability and latency, and the Quality of Experience (QoE) in terms of UE service satisfaction. Additionally, the different architecture between the NTN and TN networks, the changing communication environment, and the end-user requirements may lead the conventional handover to make late/early decisions and switch to the wrong network/cell. For this, ML-aided handover decisions can be a solution for the TN-NTN integrated network to deal with the network's partial information, uncertainty, rapidly changing environment, and strict time constraints.

Benefits

Machine Learning (ML) solutions to aid the handover decision-making between NTN and TN 5G network can improve the handover success rate and decrease the handover signalling load and the service interruption time to a minimum. Hence, UEs, such as handheld and vehicle devices, can seamlessly connect to NTN and TN 5G networks.

Features

The following software products are the output of the SHINE project :
• SW-based HO Engine: That includes different handover engine options (ML-based and non-ML-based, for comparison purposes).
• SW-based System-Level Testbed: that simulates/emulates the end-to-end performance of multiple 5G networks (e.g. integrated TN-NTN system) and is used to test the newly developed handover engine.

System Architecture

The SHINE project focuses on 5G-based handover between different 5G-networks, from which at least one is a satellite-based NTN. Considering the simple case of two 5G-networks, the following scenarios are considered
Scenario 1: Handover occurs between a TN and an NTN network with certain overlapping coverage over the region of interest.
Scenario 2: Handover occurs between two different NTN networks (operated by different operators), both with complementary coverage.

Plan

ESA SHINE project started in February 2025 and concluded in March 2026.
The project is composed of the following main tasks:

  1.  System Scenario Definition
  2. Finalised Technical Specification
  3. Selected Technical Baseline
  4. Verified Detailed Design
  5. Implementation and Verification Plan
  6. Verified Deliverable Items and Compliance Statement
  7. Technology Assessment and Development Plan
Current status

Ongoing.

Prime Contractor

Subcontractors