Abstract:
With the maturity and popularity of Internet of Things (IoT), Social Internet of Things (SIoT) has been proposed to support novel IoT applications and networking services more effectively and efficiently. Many SIoT works design architectures and protocols for specific schemes. SIoT collaboration for complex tasks is unexplored. Thus, we propose a new problem family, Task-Optimized SIoT Selection (TOSS), to find the best IoT objects for a set of tasks in the task pool. TOSS selects the target SIoT group to maximize accuracy and communication. Bounded Communication-loss TOSS (BC-TOSS) and Robustness Guaranteed TOSS (RG-TOSS) for different scenarios are both NP-hard and inapproximable. We propose a performance-guaranteed polynomial-time algorithm for BC-TOSS and an efficient one for RG-TOSS. Structure-Aware Reinforcement Learning (SARL) can use Graph Convolutional Networks (GCN) and Deep Reinforcement Learning (DRL) to solve RG-TOSS, which is NP-hard and inapproximable within any factor. Since we use graph models to simulate DRL problem instances, which differ from real ones, we propose Structure-Aware Meta Reinforcement Learning (SAMRL) for fast domain adaptation. Our algorithms outperform deterministic and learning-based baseline approaches on multiple real datasets.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
