COMNETS: COst-sensitive decision trees approach to throughput optimization for Multi-radio IoT NETworkS

TL;DR

COMNETS addresses cost-sensitive radio selection for mesoscale IoT by integrating per-sample misclassification costs into a TAO-optimized oblique tree framework, thereby reducing high-cost errors while compressing the model for resource-constrained devices. The approach yields interpretable, sparse decision rules and demonstrates stability in tree structure when confronted with new data. Real-world deployments show substantial throughput gains over the prior MARS system (approximately 20–21% at two sites) with maintained latency within practical bounds. This work advances deployable AI-driven protocols for IoT networking by combining cost-sensitive learning, interpretability, and large-scale validation.

Abstract

Mesoscale IoT applications, such as P2P energy trade and real-time industrial control systems, demand high throughput and low latency, with a secondary emphasis on energy efficiency as they rely on grid power or large-capacity batteries. MARS, a multi-radio architecture, leverages ML to instantaneously select the optimal radio for transmission, outperforming the single-radio systems. However, MARS encounters a significant issue with cost sensitivity, where high-cost errors account for 40% throughput loss. Current cost-sensitive ML algorithms assign a misclassification cost for each class but not for each data sample. In MARS, each data sample has different costs, making it tedious to employ existing cost-sensitive ML algorithms. First, we address this issue by developing COMNETS, an ML-based radio selector using oblique trees optimized by Tree Alternating Optimization (TAO). TAO incorporates sample-specific misclassification costs to avert high-cost errors and achieves a 50% reduction in the decision tree size, making it more suitable for resource-constrained IoT devices. Second, we prove the stability property of TAO and leverage it to understand the critical factors affecting the radio-selection problem. Finally, our real-world evaluation of COMNETS at two different locations shows an average throughput gain of 20.83%, 17.39% than MARS.

Figures (8)

• Figure 1: Motivation for cost-sensitive learning
• Figure 2: Mesh topology set up at locations A and B
• Figure 3: Multi-radio hardware
• Figure 4: Tree structure provided by TAO for a tree model trained with 50%, 75% and 100% of the training data.
• Figure 5: Sparse oblique tree