A Correlated Data-Driven Collaborative Beamforming Approach for Energy-efficient IoT Data Transmission

TL;DR

This work tackles energy efficiency and data redundancy in IoT networks by integrating collaborative beamforming with a data-aware routing and deep RL-based node selection. The proposed framework combines an overlap-based multi-hop routing protocol (OMRP) for data fusion and routing with SoftPPO-LSTM to intelligently select CB nodes, forming a virtual antenna array for uplink to a remote BS. Empirical results show that OMRP extends network lifetime and reduces energy consumption, while SoftPPO-LSTM improves data throughput and provides robust CB node selection under long horizons and large action spaces. Together, these components yield a scalable, data-driven solution that mitigates hot spots and enhances the practicality of energy-efficient IoT data transmission in large deployments.

Abstract

An expansion of Internet of Things (IoTs) has led to significant challenges in wireless data harvesting, dissemination, and energy management due to the massive volumes of data generated by IoT devices. These challenges are exacerbated by data redundancy arising from spatial and temporal correlations. To address these issues, this paper proposes a novel data-driven collaborative beamforming (CB)-based communication framework for IoT networks. Specifically, the framework integrates CB with an overlap-based multi-hop routing protocol (OMRP) to enhance data transmission efficiency while mitigating energy consumption and addressing hot spot issues in remotely deployed IoT networks. Based on the data aggregation to a specific node by OMRP, we formulate a node selection problem for the CB stage, with the objective of optimizing uplink transmission energy consumption. Given the complexity of the problem, we introduce a softmax-based proximal policy optimization with long short-term memory (SoftPPO-LSTM) algorithm to intelligently select CB nodes for improving transmission efficiency. Simulation results validate the effectiveness of the proposed OMRP and SoftPPO-LSTM methods, demonstrating significant improvements over existing routing protocols and node selection strategies. The results also reveal that the combined OMRP with the SoftPPO-LSTM method effectively mitigates hot spot problems and offers superior performance compared to traditional strategies.

Figures (17)

• Figure 1: The CB-based data harvesting and dissemination system overview. (a) The routing process is activated by a query from the BS. (b) Sketch map and geometrical configuration of CB process after aggregating the data to the sink node.
• Figure 2: Network model and operating mechanisms. Each round of data harvesting consists of six steps. Routing and fusion are configured and performed in steps 3 and 4, while synchronization and CB are performed in steps 5 and 6.
• Figure 3: Overlapping area of node $i$ with its neighbors $j$, $k$ and $q$. Note that each node has a monitor radius of $r$.
• Figure 4: Direct or relay communication method in inter-cluster routing.
• Figure 5: Framework of SoftPPO-LSTM model in the training phrase.