arXiv：cs.LG· Naresh Babu Kakarla, V. Mahendran·· 4 小时前AI 评分25
FLoRa：能量受限下无人机辅助占空比 LoRa 节点的数据采集架构
FLoRa: Flight-Assisted Data Collection from Duty Cycling LoRa Nodes under Energy Constraints
AI 导读
针对 LoRa 物联网设备为省电而占空比运行、无人机难以高效采集数据的问题，研究者提出 FLoRa 架构，用模拟退火做路径规划、CMA-ES 做悬停定位、POMDP 做探测决策，并提出 VIP 指标衡量采集价值。FLoRa 总期望 VIP 较元启发式、贪心与深度强化学习基线分别提升 30.6%、27.8%、15.2%，节点覆盖率提升 24.5%、29.2%、8.8%。
正文
Abstract:Data collection using Unmanned Aerial Vehicles (UAVs) is challenging when LoRa IoT Devices (IoTDs) duty-cycle to conserve battery. Under energy constraints, a UAV must decide which IoTDs to visit, in what order, where to hover, and how many times to probe each node, while time-based data freshness decays. Tractably solving this problem requires a multi-level optimization architecture: discrete combinatorial optimization for routing, continuous global optimization for spatial positioning, and sequential decision-making under uncertainty. We propose FLoRa, a Flight-assisted LoRa data collection architecture using Simulated Annealing (SA) for path planning, Covariance Matrix Adaptation Evolution Strategy (CMA-ES) for hover positioning, and Partially Observable Markov Decision Processes (POMDPs) for probing IoTDs. To quantify collection utility from duty-cycling nodes, we introduce the Value of Information for Pull-based systems (VIP), a metric that rewards fresh data and penalizes failed probes, imposing well-posedness and preventing indefinite probing when an IoTD is off. Tracking hard battery constraints on every POMDP sample path requires state augmentation, worsening the curse of dimensionality. For tractability, SA and CMA-ES work on the hard battery constraints, while at the POMDP layer we relax them into soft average constraints via Lagrangian relaxation. Since solving the network-wide POMDP is computationally complex, we decompose it into node-level POMDPs by approximating inter-node time dependency using a forward-decomposition technique. Evaluation shows FLoRa outperforms metaheuristic, greedy, and deep reinforcement learning baselines by 30.6%, 27.8%, and 15.2% in total expected VIP, while increasing node coverage by 24.5%, 29.2%, and 8.8%, and successful collections by 24.3%, 25.6%, and 15.2%, respectively.
| Comments: | 20 pages |
| Subjects: | Networking and Internet Architecture (cs.NI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.09226 [cs.NI] |
| (or arXiv:2610.09226v1 [cs.NI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09226 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mahendran Veeramani [view email]
[v1]
Tue, 6 Oct 2026 23:43:55 UTC (454 KB)
来源：arXiv：cs.LG · arxiv.org