Energy-Predictive Planning for Optimizing Drone Service Delivery

2025-08-03

AI Summary

This paper addresses the joint path planning and charging scheduling problem in UAV-based aerial delivery, where high energy consumption and poor timeliness hinder operational efficiency. To tackle this, we propose an energy-aware predictive planning framework. Methodologically, we design an adaptive bidirectional LSTM model to jointly predict multi-UAV energy consumption and arrival times; subsequently, we develop a heuristic bi-objective optimization algorithm that simultaneously optimizes flight trajectories and charging schedules within a formal mathematical programming formulation. Unlike conventional single-objective or static planning approaches, our framework tightly integrates machine learning–driven prediction with operations research–based decision-making. Extensive experiments on real-world flight data demonstrate that our method reduces average delivery time by 18.7% and improves energy utilization efficiency by 23.4% over baseline approaches, significantly enhancing both service efficiency and sustainability in large-scale UAV networks.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We propose a novel Energy-Predictive Drone Service (EPDS) framework for efficient package delivery within a skyway network. The EPDS framework incorporates a formal modeling of an EPDS and an adaptive bidirectional Long Short-Term Memory (Bi-LSTM) machine learning model. This model predicts the energy status and stochastic arrival times of other drones operating in the same skyway network. Leveraging these predictions, we develop a heuristic optimization approach for composite drone services. This approach identifies the most time-efficient and energy-efficient skyway path and recharging schedule for each drone in the network. We conduct extensive experiments using a real-world drone flight dataset to evaluate the performance of the proposed framework.

Problem

• Optimize drone delivery paths for energy efficiency
• Predict energy status and arrival times of drones
• Develop heuristic approach for time-energy efficient scheduling

Innovation

• Energy-Predictive Drone Service (EPDS) framework
• Adaptive bidirectional LSTM energy prediction
• Heuristic optimization for skyway path planning