Slice Management in Radio Access Network via Deep Reinforcement Learning
| Autor: | Behnam Khodapanah, Ingo Viering, Meryem Simsek, Ahmad Awada, Gerhard Fettweis, Andre Noll Barreto |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Radio access network
Computer science business.industry 05 social sciences Pooling 050801 communication & media studies 020206 networking & telecommunications 02 engineering and technology 0508 media and communications 0202 electrical engineering electronic engineering information engineering Reinforcement learning Radio resource management business 5G Computer network |
| Zdroj: | VTC Spring |
| DOI: | 10.1109/vtc2020-spring48590.2020.9128982 |
| Popis: | In future 5G systems, it is envisioned that the physical resources of a single network will be dynamically shared between the virtual end-to-end networks called “slices” and the network is “sliced”. The dynamic sharing of resources can bring about pooling gains, but different slices can easily influence each other. Focusing on slicing the radio access network, a slice management entity is required to steer the radio resource management (RRM) so that all of the slices are satisfied and negative inter-slice influences are minimized. The steering of RRM can be done by adjusting slice-specific control parameters in scheduler and admission controller mechanisms. We use a model-free reinforcement learning (RL) framework and train an agent as a slice manager. Simulation results show that such agents are capable of relatively quickly learning how to steer the RRM. Furthermore, a hybrid method of Jacobian-matrix approximation with RL approach has been devised and shown to be a practical and efficient solution. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|