Algorithmes, Technologies de l’information et des communications (TIC), Technologies disponibles, Télécommunications


Algorithmes efficaces pour la prise de décision et le déploiement de couverture de drones à basse altitude

– Description en anglais seulement –

The need and the challenge in the unmanned aerial vehicles market

  • Unmanned Aerial Vehicles (UAVs) or drones are increasingly used in numerous military and civil expeditions that could be dull, dirty or dangerous.
  • The UAVs market is estimated at USD 19.3 billion in 2019 and is projected to reach USD 45.8 billion by 2025, at a CAGR of 15.5% from 2019 to 2025 (Market&Markets).
  • UAVs have gained a lot of popularity and together with the emergence of the Internet-of-things, 5G and mobile edge computing, their application domains will be further widened.
  • The selection of appropriate UAVs (their number, operational altitude, etc.) to satisfy end-user QoS requirements and their deployment over an area of interest to maximize its coverage are challenging. Trade-offs must be made: for example, higher altitudes lead to better communication links and wider coverage but also affect imaging resolution and cause signal attenuation. Sensitive applications may require maximized zone coverage, while the number of drones may need to be minimized due high costs, and their movements minimized to preserve energy.
  • To cope with such trade-offs and challenges, an efficient selection and deployment strategy is necessary.

Efficient algorithms for decision-making and coverage deployment of multi-low-altitude platforms

  • The proposed invention emphasizes two goals: first, selecting a minimal number of adequate UAVs and deciding their operational altitude. These UAVs will be deployed across a given area of interest for certain coverage missions. The second goal is obtaining the optimal placement coordinates to maximize coverage.
  • A multi-objective and constraints-handling decision-making algorithm called SAGA is designed to pick the most fitting option amongst a large set of possible candidates according to conflicting criteria and based on QoS conditions or user requirements.
  • These criteria depend on the application. For example, wildlife/crop monitoring may demand good imaging resolution, long hovering duration and lower costs.
  • A comparative analysis between the proposed algorithm (SAGA) and existing MCDM methods showed that SAGA has a lower computational complexity, a good level of consistency and most importantly a higher selection accuracy (Fig. 1).
  • An improved and fast multi-objective genetic algorithm called NSPGGA and a camera orientation algorithm are used to get the best UAV hovering coordinates.
  • These algorithms provide a nearly complete view of the area of interest and maximize the coverage by re-orienting the UAVs or by rotating their cameras in specific directions.
  • Comparative analyses with some existing state-of-the-art techniques showed that the proposed approach achieves better efficiency and higher accuracy in almost all simulated scenarios and has lesser computational complexity (Fig. 2).
  • The approach efficiently specifies which and how many UAVs to choose, and in which cardinal direction to aim (tilt and azimuth angles) to further increase coverage level in an energy-efficient manner without the necessity to move the UAVs from their hovering positions (Fig. 3).
  • Technology developed by Prof. Nadjia Kara, (Department of Software Engineering and IT, École de technologie supérieure (ÉTS)).

Competitive advantages

  • High accuracy for selecting appropriate UAVs according to user requirements and the application QoS conditions.
  • Fast, optimal and collision free deployment.
  • Better performance outcomes: high coverage levels, energy-efficiency, connectivity and coverage lifetime.
  • Application-agnostic (wildlife monitoring, video reconnaissance, 5G applications, crop monitoring, search and rescue, etc.).
  • Fewer UAVs needed (i.e. lower purchase and maintenance costs).

Market applications

  • Aerospace equipment manufacturers.
  • Unmanned Aerial Vehicle (UAV) and an Unmanned Ground Vehicle (UGV) equipment manufacturers.
  • Drone deployment solutions.

Business opportunity 

  • Technology available for licensing.
  • Co-development, partnering.
  • Provisional patent application filed.


If you are interested by this technology, please contact :
Jean-Philippe Valois, Director Business Development, Engineering, (514) 575-0425


École de Technologie supérieure (ÉTS)

Main inventors


Houssem E. Mohamadi, Researcher, Department of Software Engineering and IT

Houssem E. Mohamadi is currently a Ph.D. student in the field of UAVs and Internet-of-Things, at the Institute of Aeronautics and Spatial Studies, University of SAAD DAHLAB, Blida, Algeria and in collaboration the School of Superior Technology (ÉTS), Montreal, Canada. He received his M. Sc. degree in Avionics Engineering from the Institute of Aeronautics and Spatial Studies, University of SAAD DAHLAB, Blida, Algeria, in 2016. His current research activities include Aeronautical Ad-hoc Networks and security mechanisms, UAVs deployment, optimization, guidance and control.


Nadjia Kara, Professor, Department of Software Engineering and IT

Prof. Kara holds a Ph.D. in Electrical and Computer Engineering from Ecole Polytechnique of Montreal (Canada), a Master’s degree in Electrical and Computer Engineering from Ecole Polytechnique of Algiers (Algeria). She has several years of experience in research and development. She worked in industry for more than ten years. From 2005 to 2015, she held adjunct professor positions at INRS-EMT (Canada), University of Sherbrooke (Canada), and Concordia University (Canada). Since 2009, she is a full professor at the department of software engineering and IT, School of Superior Technology (E´ TS), University of Quebec (Canada). Her research interests include service and network engineering for communication networks, resource management in next-generation networks, ambient intelligence, autonomous networks, multimedia applications and services, and machine learning. The application areas are: network virtualization cloud, grids and autonomic computing, and Internet of Things.