Intelligent Scheduling Methodology for UAV Swarm Remote Sensing in Distributed Photovoltaic Array Maintenance.

Area of Science:

• Engineering
• Computer Science
• Renewable Energy

Background:

• Unmanned aerial vehicle (UAV) remote sensing is crucial for urban distributed photovoltaic array (UDPA) planning, design, and maintenance.
• Existing research has not sufficiently addressed UAV swarm scheduling for UDPA maintenance tasks.

Purpose of the Study:

• To develop a novel scheduling model and algorithm for UAV swarm remote sensing specifically for UDPA maintenance.
• To address the large-scale global optimization (LSGO) challenges inherent in coordinating UAV swarms for this application.

Main Methods:

• UAV swarm scheduling tasks for UDPA maintenance were formulated as a large-scale global optimization (LSGO) problem with penalty functions for constraints.
• An adaptive multiple variable-grouping optimization strategy was developed, incorporating adaptive random grouping, UAV grouping, and task grouping.
• A novel evolutionary algorithm, cooperatively coevolving particle swarm optimization with adaptive multiple variable-grouping and context vector crossover/mutation strategies (CCPSO-mg-cvcm), was created.

Main Results:

• The developed CCPSO-mg-cvcm algorithm demonstrated superior performance compared to existing algorithms in case studies.
• The methodology effectively optimizes UAV swarm remote sensing for large-scale UDPA maintenance.

Conclusions:

• The proposed CCPSO-mg-cvcm algorithm provides an effective solution for optimizing UAV swarm scheduling in UDPA maintenance.
• This research advances the application of UAV technology in the renewable energy sector, particularly for maintaining distributed photovoltaic systems.