What question did this study set out to answer?

March 19, 2026Open Access

Energy-efficient neuromorphic computing for ultra-low latency cognitive radio: a hardware-software co-design framework for 6 G spectrum intelligence

Puntos clave

The goal is to create a co-design framework integrating neuromorphic computing with cognitive radio systems for improved efficiency and reduced latency.
Analyzed five neuromorphic platforms using benchmarks from the Intel Neuromorphic Deep Noise Suppression Challenge.
Developed a unified methodology for joint optimization of spike encoding, network topology, and hardware mapping.
Formulated design rules for selecting the appropriate encoding based on specific signal requirements.
Conducted experimental validations using real-world spectrum data from industrial IoT deployments.
Achieved sub-millisecond latency with 50-170 µs for spectrum decisions.
Reduced energy consumption significantly, achieving 31 pJ per spike compared to 2.5−12.5 µJ per operation with GPUs.
Demonstrated 97.6% classification accuracy on real-world spectrum data.
Provided evidence of practical deployment success across diverse sectors including industrial automation and smart cities.

Resumen

Sixth-generation (6 G) wireless networks demand cognitive radio systems that simultaneously achieve sub-millisecond latency and sustainable energy consumption – requirements conventional artificial intelligence approaches cannot meet. This paper presents a hardware-software co-design framework integrating neuromorphic computing with cognitive radio to address both constraints through brain-inspired spiking neural networks (SNNs). We systematically analyze five neuromorphic platforms – Intel Loihi 2, IBM TrueNorth, SpiNNaker, SpiNNaker 2, and Intel Hala Point – using standardized benchmarks from the Intel Neuromorphic Deep Noise Suppression (N-DNS) Challenge, demonstrating sub-millisecond spectrum decisions (50-170 s end-to-end latency) with energy consumption reduced by 100-1000 (31 pJ per spike) compared to conventional GPU-based approaches (2. 5−12. 5 J per operation). Our framework provides three novel contributions: (1) a unified co-design methodology optimizing spike encoding, network topology, and hardware mapping jointly to achieve 3 efficiency gains over independent optimization; (2) quantitative design rules for encoding selection – rate coding for signal-to-noise ratios below -10 dB, temporal coding for latency requirements below 100 s, and population coding for reliability exceeding 99. 9%; and (3) experimental validation achieving 97. 6% classification accuracy on real-world spectrum data from industrial IoT deployments consuming only 31 mW average power. Through five detailed case studies spanning industrial automation (99. 9% uptime over 6 months), vehicle-to-everything communications (98. 7% collision avoidance), defense applications (95% reliability under 40 dB jamming), smart cities (100, 000 sensors), and healthcare (15-year implant lifetime), we demonstrate neuromorphic cognitive radio’s practical viability. The framework addresses critical deployment barriers including device variability mitigation (±20% threshold compensation), cross-platform algorithm portability, and RF-to-spike conversion interfaces. These results establish neuromorphic computing as a foundational technology for energy-constrained, latency-critical 6 G wireless systems, with implications extending to radar processing, electronic warfare, and satellite communications.

Me gusta

Guardar

Ver artículo completo