École de technologie supérieure
Efficient mobile edge computing development with drone integration
Abstract
dc:descriptionMobile Edge Computing (MEC) has revolutionized mobile networks by bringing computation and storage closer to users. The integration of drones enhances this approach by introducing dynamic mobility and flexibility, thereby expanding the capabilities of edge computing. Drones and Software-Defined Networking (SDN) technology integrate intricately to form an innovative MEC system development method. Drones within MEC present both unique challenges and opportunities, acting as mobile edge servers in remote or densely populated areas where conventional infrastructure is lacking, dynamically deploying to areas with sudden demand spikes, optimizing resource allocation, and enhancing quality of service (QoS). SDN is a key part of making drones, MEC servers, and traditional network infrastructure work together. It does this by separating the control and data planes, which allows for centralized management and dynamic resource allocation. This increases scalability, flexibility, and efficiency while facilitating seamless integration with existing networks and enabling efficient routing and traffic management in dynamic MEC environments. This master’s thesis delves into a comprehensive framework for developing efficient MEC systems with drone integration and SDN. Drone-Enabled MEC Architecture This innovative design leverages unmanned aerial vehicles (UAVs) as mobile edge servers to enhance the capacity and reach of MEC infrastructure. SDN-Based Using real-time network circumstances and application needs, a centralized SDN controller dynamically orchestrates the deployment and operation of MEC servers and drones. Advanced deep learning algorithms are utilized for the prediction and optimization of Quality of Service (QoS). Firstly, enhance the effectiveness of deep learning models by training them to accurately forecast QoS measures, including latency, throughput, and packet loss. Such models can utilize intricate patterns in input characteristics to offer more precise predictions and enhance QoS optimization. Secondly, Apply deep learning methods to enhance quality of service (QoS) by dynamically optimizing resource allocation and routing decisions using projected QoS metrics. Implementing these strategies can guarantee the consistent fulfillment of service level agreements (SLAs), hence improving the user experience in dynamic multi-access edge computing (MEC) environments. By integrating deep learning into the model, we can improve the effectiveness, scalability, and robustness of mobile edge computing (MEC) systems by incorporating drone integration, software-defined networking (SDN), and machine learning approaches. Deep learning techniques improve prediction accuracy, enable adaptive decision-making, and facilitate proactive security measures, thereby optimizing performance and advancing the development of edge computing infrastructures.
Degree
thesis:*- Name thesis:degree_name
- Mémoire de maîtrise électronique
- Level thesis:degree_level
- masters
- Grantor dc:publisher
- École de technologie supérieure
- Year dc:date
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Sanatkar, Talaye
Subjects
dc:subject × 1Rights
- Language dc:language
- en
Identifiers
dc:identifier.*- Identifier
- INSERT-YOUR-LIBRARY-ID-HERE3553