Idea
A DNN-powered precoding platform for RIS-aided mmWave MIMO systems enabling faster, efficient wireless throughput optimization for telecom operators.
Research Paper
Core Innovation
This paper introduces a deep neural network model to replace exhaustive search in selecting phase shifts for RIS-aided mmWave MIMO precoding. It significantly reduces computational complexity while maintaining near-optimal spectral efficiency under practical phase shift constraints and varying user-RIS distances. This approach advances prior work by enabling real-time, scalable precoding in challenging wireless environments.
Market Size (TAM)
$10–20B TAM, $2–5B SAM; assumption: growing 5G/6G infrastructure and RIS adoption in telecom networks.
Potential Customers & Pain Points
- Telecom Operators Needing Efficient mmWave Network Optimization
- Wireless Infrastructure Providers Facing Obstructed Signal Paths
- IoT and 5G Service Providers Requiring Adaptive Beamforming
Business Model
Licensing the DNN precoding software to telecom equipment manufacturers and network operators as a subscription or per-deployment fee.
Competitive Landscape
- Nokia Bell Labs
- Huawei Wireless Research
- Samsung Networks
Implementation Challenges
- Integration with existing telecom hardware
- Real-time adaptation to dynamic environments
- Scalability of DNN models in large networks
Validation Strategy
- Develop prototype integrating DNN with RIS hardware
- Conduct field tests in obstructed mmWave environments
- Benchmark throughput gains against traditional methods
Research Paper Overview
DNN-Based Precoding in RIS-Aided mmWave MIMO Systems With Practical Phase Shift
Summary
This paper proposes a deep neural network to efficiently select phase shift codewords for precoding in mmWave MIMO systems aided by reconfigurable intelligent surfaces, improving throughput despite obstructed direct paths and varying user-RIS distances.