What is it about?
Resource allocation is an important subject in our daily life. The next generation of wireless communication systems and device to device (D2D) communications require efficient channel and power allocation. It is also important to consider the unknown and dynamic parameters in this resource allocation. In this paper, we use learning based method to solve the resource allocation problem in D2D communications.
Featured Image
Why is it important?
Learning methods usually solve the problem in sub optimal manner. These methods use some explorations (learning time) for exploitation (react and decide on the solution). The optimal trade off between exploration and exploitation is an important issue to be addressed. We introduce a more practical and complicated scenario in resource allocation. We introduce a learning method to solve the joint channel and power allocation by the same computational complexity level and better performance in terms of network sum rate and fairness criterion.
Perspectives
Nowadays, machine learning is emerging in a new age of applications. However, on the time we started this study, not many researches were published on efficient application of conventional learning methods on D2D resource allocation. We have still a long distance to solve the problem in real environment in an optimum manner. However, I hope that this study is a good start in the way.
Reza Shahbazian
Shahid Beheshti University
Read the Original
This page is a summary of: Learning-based resource allocation in D2D communications with QoS and fairness considerations, Transactions on Emerging Telecommunications Technologies, September 2017, Wiley,
DOI: 10.1002/ett.3249.
You can read the full text:
Contributors
The following have contributed to this page
