DeepMIMO v1, DeepMIMO v2, and DeepMIMO 5G NR
What Are the Differences?
DeepMIMO v1
Generates the channels between selected BSs and UEs
Allows for multiple antennas only at the BSs (with single-antenna UEs)
Supports OFDM channels only
Available only in Matlab
DeepMIMO v2
Includes all features of DeepMIMO v1
Optimized memory requirements and generation speed
Generates the channels between BSs and UEs
Generates the channels between BSs and BSs (enabling integrated access-backhaul, RIS, etc.)
Allows for multiple antennas at both the BSs and UEs
Allows for changing panel orientations at the BS and UEs
Allows for applying receiver filtering for more accurate channel generation
Generates OFDM and time-domain channels
Outputs path parameters, path-loss, distances, among other possible outputs
Outputs transmitter/receiver locations
Available in Matlab, Octave, and Python
DeepMIMO 5G NR
- Generates datasets that are compatible with the 3GPP 5G NR CDL channel model
- Supports all FR1/FR2 5G NR numerologies in 3GPP release 15,16, and 17
- Generates the channels between BSs and UEs
- Generates the channels between BSs and BSs (enabling integrated access-backhaul, RIS, etc.)
- Allows for multiple antennas at both the BSs and UEs
- Allows for changing panel orientations at the BS and UEs
- Outputs path parameters, path-loss, distances, among other possible outputs
- Outputs transmitter/receiver locations
- Available in Matlab – Requires 5G Toolbox
Which DeepMIMO Version Should I Use?
- If you are interested in generating deterministic geometric channels that solely rely on 3D ray-tracing
- If you are interested in 5G NR compliant wireless channels
- This is a hybrid approach that merges geometric (ray-tracing) and stochastic models
