Written for
RAN engineering and network planning at a mobile operator; security architecture for QKD-ready links.
Industry 5
Telecom
RAN engineering and network planning at a mobile operator; security architecture for QKD-ready links.
The decision
How to get more capacity from spectrum already owned; where to place QKD hardware; which traffic is anomalous.
How it is done today
Vendor SON features and manual parameter tuning.
When it goes wrong New spectrum is expensive; a mis-tuned cluster loses throughput every day it stays mis-tuned.
Applications
| Application | You give | You get | Status |
|---|---|---|---|
| Carrier-aggregation optimisation Proof: +10% average downlink on a live network, no new radio hardware | A cluster of cells and its parameters | The settings and the downlink comparison | Deployed through the platform network |
| Optical network routing and wavelength assignment Proof: A 156-qubit run published in the platform network | The optical topology and demands | The routing and assignment | Deployed through the platform network |
| QKD hardware placement | The fibre network and the candidate sites | Where to place the QKD nodes | Deployed through the platform network |
| Network traffic anomaly detection | Traffic records | The anomalous flows | Deployed through the platform network |
| Where throughput is lost across the whole network | The network as an edge list | The response of the whole network, not cell by cell | Mapped |
| Customer segmentation from CRM data | CRM records | The segments | Deployed through the platform network |
What changes for you
- Measured on the live network, not in a simulator.
- No radio hardware added.
- The whole-network response is simulated the way the grid response is, past where the reference stops.
First engagement
You send One cluster of cells with its current parameters.
You get back The settings and the downlink comparison. Two weeks.
Proof · Carrier aggregation optimisation
Customer proof of concept · platform network
+10%
average downlink speed on a live network, against the network operator's existing carrier-aggregation settings; no added hardware
Platform networkPlatform quantum-inspired solver, on the network operator's live networkDecision
How to raise capacity on spectrum already owned
What is modelled
Carrier-aggregation settings across the cells of a live network, as a combinatorial optimisation.
Operational outcome
- +10% average downlink speed
- No new radio hardware
- Measured on the live network, not in simulation
- Problem size
- Live network · cell-level settings · one operator
- Scope
- A proof of concept on one network; the +50% figure is an upper bound on secondary-cell volume.
Results, each with its baseline
- About +10% average downlink speed on a live network from carrier-aggregation optimisation, no added hardware; secondary-cell data volume up to +50% (upper bound). Baseline: the network operator's existing settings.Platform networkWhere live-network proof of concept, quantum-inspired
Benchmark
TelecomCarrier aggregation optimisation
Published reference
Published telecom figures in the field state a percentage with no baseline and no date.
Sources: public vendor and operator announcements, undated
Merlin
+10% average downlink on a live network, no added hardware (quantum-inspired, platform network)
Platform networkBaseline
The network operator's existing carrier-aggregation settings
Through our platform network
Client anonymised to its sector; partner not named; metric quoted with its published baseline, compute type and status. Not our own measurement.
Telecom
5G carrier-aggregation tuning
Average downlink throughput about +10%
- Condition
- Field pilot on a live network in a limited trial area, with no added hardware. Secondary-cell data volume up to +50% is an upper bound.
- Compute
- Quantum-inspired (Ising machine)
- Status
- Pilot
Does not show that quantum beats classical.
Through our platform network · partner and client not named
Your industry, next
Bring us the decision your industry has to make next.
A resist, a grid plan, a controller, a cipher: you get the answer, the method it was checked against, and its status. The free check runs in your browser.
No keyNo cardAn answer in about a second