FLoRa: Flight-Assisted Data Collection from Duty Cycling LoRa Nodes under Energy Constraints

Naresh Babu Kakarla; V. Mahendran

cs.NIOct 6, 2026

FLoRa: Flight-Assisted Data Collection from Duty Cycling LoRa Nodes under Energy Constraints

Authors: Naresh Babu Kakarla, V. Mahendran

Organizations: Department of Computer Science and Engineering, Indian Institute of Technology Tirupati, Andhra Pradesh, 517619, India

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.

Figures & tables

Ref	Problem	Path	Positioning	Type	Probing
[ TSP_2 ]	TSP	All	Above IoTDs	Push	Deterministic
[ CE_TSP ]	CE-TSP	All	IoTD neighborhood	Push	Deterministic
[ OP_DC ]	OP	Subset	Above IoTDs	Push	Deterministic
[ CEOP ]	CEOP	Subset	IoTD neighborhood	Push	Deterministic
FLoRa	PTCOP	Subset	IoTD neighborhood	Pull	Probabilistic

TABLE I : Types of UAV path-planning problems

Fig. 1 : SNR success probability over different SF regions

Fig. 2 : Hierarchical layout of the proposed FLoRa framework

Work	Energy Constraint	Freshness	Duty cycling	Optimization	Method
[ LoRa_UAV_AoI ]	✓	AoI	Scheduled	Path and hover	Algorithm
[ TC_UAV_DC_4 ]	×	×	×	Trajectory	Exact methods
[ UAV_Hover_Flight_Heur ]	×	×	×	Trajectory and hover	Meta heuristics
[ UAV_OP_Traj_Opt ]	✓	×	×	Trajectory	Meta heuristics
[ UAV_Subset_Visit_AoI ]	✓	AoI	×	Trajectory and hover	Exact methods
[ UAV_Traj_Opt_DC ]	×	×	Scheduled	Trajectory	Exact methods

TABLE II : Comparison with related works

Fig. 3 : UAV-assisted LoRa IoT data-collection architecture with a sample trajectory over

N=3

sensing regions,

[N]=\{1,2,3\}

. The UAV visits IoTDs

1

and

3

and returns home, giving the tour

\mathbf{z}=\{z_{1}=1,\,z_{2}=3\}

Fig. 4 : Timing components associated with the UAV flight and hover for each of the IoTDs visited sequentially in a given tour

Fig. 5 : Conceptual block diagram of the proposed FLoRa framework

Category	Parameter	3 km	12 km
Network	Deployment area	$78.75\times 55$	$315\times 220$
		km 2	km 2
	Number of IoTDs ( $N$ )	20, 40
	IoTD radius ( $d_{\max}$ )	3 km	12 km
	Device availability ( $a_{i}$ )	$[0,\,1]$
Channel / Radio	Bandwidth ( $BW$ )	125 kHz

TABLE III : Simulation parameters

Panel of Figure 9 — Fig. 6 : Total expected VIP vs UAV battery ( $b_{\max}$ ) at 3 km scenario for (a) $N=20$ and (b) $N=40$ IoTDs.

Panel of Figure 10 — Fig. 7 : Total expected VIP vs UAV battery ( $b_{\max}$ ) at 12 km scenario for (a) $N=20$ and (b) $N=40$ IoTDs.

Panel of Figure 11 — Fig. 8 : Node Coverage vs UAV battery ( $b_{\max}$ ) at 3 km scenario for (a) $N=20$ and (b) $N=40$ IoTDs.

Panel of Figure 12 — Fig. 9 : Node Coverage vs UAV battery ( $b_{\max}$ ) at 12 km scenario for (a) $N=20$ and (b) $N=40$ IoTDs.

Panel of Figure 13 — Fig. 10 : Expected successful collections vs UAV battery ( $b_{\max}$ ) at 3 km scenario for (a) $N=20$ and (b) $N=40$ IoTDs.

Panel of Figure 14 — Fig. 11 : Expected successful collections vs UAV battery ( $b_{\max}$ ) at 12 km scenario for (a) $N=20$ and (b) $N=40$ IoTDs.

	Total Expected VIP			Coverage			successful collections
Baseline	20 $N$	40 $N$	Avg	20 $N$	40 $N$	Avg	20 $N$	40 $N$	Avg
GUHO	+27.3	+22.1	+24.7	+43.8	+26.9	+35.3	+21.6	+18.6	+20.1
ACO	+19.2	+22.3	+20.8	+18.6	+16.6	+17.6	+16.6	+12.7	+14.6
PPO	+17.1	+14.6	+15.8	+14.2	+8.9	+11.6	+17.7	+10.4	+14.0
SSA	+15.8	+15.9	+15.9	+15.0	+14.2	+14.6	+14.3	+10.0	+12.1
GU	+21.4	+22.0	+21.7	+27.8	+17.9	+22.8	+15.2	+26.1	+20.7

TABLE IV : Percentage improvement of FLoRa over baselines, averaged over all UAV battery levels (

3

km scenario).

	Total Expected VIP			Coverage			successful collections
Baseline	20 $N$	40 $N$	Avg	20 $N$	40 $N$	Avg	20 $N$	40 $N$	Avg
GUHO	+20.5	+16.1	+18.3	+19.3	+16.1	+17.7	+29.1	+14.3	+21.7
ACO	+44.3	+49.2	+46.8	+34.2	+38.2	+36.2	+39.5	+37.0	+38.2
PPO	+16.1	+12.9	+14.5	+6.4	+5.5	+6.0	+23.6	+9.1	+16.3
SSA	+38.7	+39.1	+38.9	+30.8	+28.5	+29.7	+36.7	+27.7	+32.2
GU	+41.1	+52.1	+46.6	+30.8	+51.2	+41.0	+36.7	+43.3	+40.0

TABLE V : Percentage improvement of FLoRa over baselines, averaged over all UAV battery levels (

12

km scenario).

	3 km			12 km			Overall
Category	VIP	Cov.	Succ.	VIP	Cov.	Succ.	VIP	Cov.	Succ.
Metaheuristic	+18.4	+16.1	+13.3	+42.8	+33.0	+35.2	+30.6	+24.5	+24.3
Greedy	+23.2	+29.0	+20.4	+32.5	+29.4	+30.9	+27.8	+29.2	+25.6
DRL	+15.8	+11.6	+14.0	+14.5	+6.0	+16.3	+15.2	+8.8	+15.2

TABLE VI : Percentage improvement of FLoRa over baseline categories.

Method	Path Planning	Hover Opt.	Mean Time
GU	Greedy	None (hover-on-node)	$\sim$ 2 s
SSA	SA	None (hover-on-node)	$\sim$ 6.2 s
GUHO	Greedy	CMA-ES	$\sim$ 112 s
PPO	Learned (DRL)	Learned (DRL)	$\sim$ 308 s (5.1 min)
FLoRa	SA	CMA-ES (+ nested POMDP)	$\sim$ 724 s (12.1 min)

TABLE VII : Offline planning time comparison across methods (mean, single problem instance,

N{=}40

, 12 km scenario).

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Symbol	Description
$a_{k}$	Data-availability probability of IoTD in region $k$
$\mathbf{a}$	Availability probability vector $(a_{i})_{i=1}^{\|\mathbf{z}\|}$
$A_{k}$	Bernoulli random variable representing IoTD $k$ ’s availability state, $A_{k}\!\sim\!\text{Bernoulli}(a_{k})$
$b_{\max}$	UAV battery budget
$b_{f}$	Battery consumed during flight
$b$	Probing energy budget, $b=b_{\max}-b_{f}$

Appendix

TABLE VIII : Summary of notations.

Explore similar work

Partially-Observable Transmission Control for UAV-Enabled Federated Learning in IoT Networks
Aug 1, 2026Masoud Ghazikor, Zhou Ni, Morteza HashemiFederated Learning Aggregation Wireless Resource Allocation
Department of Electrical Engineering and Computer Science, University of Kansas
Learning to Optimize UAV Path Planning for Data Sensing in Wireless Sensor Networks
Sep 15, 2026Sijie Ma, Zeyuan Ma, Weijia Cao +4Robotic Data Collection Metaheuristic Optimization
South China University of Technology · South China Normal University · Information Research Institute, CAS +2
Joint Optimization of Trajectory Control, Resource Allocation, and Task Offloading for Multi-UAV-Assisted IoV
May 6, 2026Maoxin Ji, Qiong Wu, Pingyi Fan +4Trajectory Optimization Intelligent Transportation Systems
School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China · School of Information Engineering, Jiangxi Provincial Key Laboratory of Advanced Signal Processing and Intelligent Communications, Nanchang University, Nanchang 330031, China · Department of Electronic Engineering, State Key laboratory of Space Network and Communications, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China +4

Aug 1, 2026, cs.ITJ/K move · Enter open · S save

Partially-Observable Transmission Control for UAV-Enabled Federated Learning in IoT Networks

Masoud Ghazikor, Zhou Ni, Morteza Hashemi

Department of Electrical Engineering and Computer Science, University of Kansas

Federated Learning Aggregation Wireless Resource Allocation Federated Learning

Open paper AskPDF arXiv

Uncrewed aerial vehicle (UAV)-enabled federated learning (FL) can provide flexible, on-demand edge intelligence for large-scale IoT deployments, but operating in shared unlicensed bands makes uplink update delivery interference-coupled and unreliable. In this paper, we develop a packet-level transmission framework that captures buffer overflow, delay violations, and transmission errors, and uses the resulting packet delivery ratio (PDR) to represent partial-update reception through a packetized, Bernoulli-masked FL aggregation process. We then formulate a fairness-consensus bilevel (FCB) optimization that jointly controls (i) transmission thresholds to maximize the average PDR while reaching consensus under partial observability and (ii) transmission powers to improve the worst PDR and enforce fairness across IoT learners. To solve this problem, we propose an alternating FCB optimizer composed of a consensus-based threshold controller (CTC), which drives the IoT learners toward a PDR-efficient consensus on transmission thresholds, and a fairness-based power controller (FPC), which updates transmission powers to improve the worst PDR and ensure fairness under the resulting consensus thresholds. Numerical results on CNN-based FL tasks show that the FCB optimizer improves FL aggregation and training performance by enhancing packet-level update delivery, consistently outperforming baseline transmission policies.

Abstract

Explore similar work

Partially-Observable Transmission Control for UAV-Enabled Federated Learning in IoT Networks

Learning to Optimize UAV Path Planning for Data Sensing in Wireless Sensor Networks

Joint Optimization of Trajectory Control, Resource Allocation, and Task Offloading for Multi-UAV-Assisted IoV