Actor-Critic Learning Based QoS-Aware Scheduler for Reconfigurable Wireless Networks
ABSTARCT :
The flexibility offered by reconfigurable wireless networks, provide new opportunities for various applications such as online AR/VR gaming, high-quality video streaming and autonomous vehicles, that desire high-bandwidth, reliable and low-latency communications. These applications come with very stringent Quality of Service (QoS) requirements and increase the burden over mobile networks. Currently, there is a huge spectrum scarcity due to the massive data explosion and this problem can be solved by helps of Reconfigurable Wireless Networks (RWNs) where nodes have reconfiguration and perception capabilities. Therefore, a necessity of AI-assisted algorithms for resource block allocation is observed. To tackle this challenge, in this paper, we propose an actor-critic learning-based scheduler for allocating resource blocks in a RWN. Various traffic types with different QoS levels are assigned to our agents to provide more realistic results. We also include mobility in our simulations to increase the dynamicity of networks. The proposed model is compared with another actor-critic model and with other traditional schedulers; proportional fair (PF) and Channel and QoS Aware (CQA) techniques. The proposed models are evaluated by considering the delay experienced by user equipment (UEs), successful transmissions and head-of-the-line delays. The results show that the proposed model noticeably outperforms other techniques in different aspects.
EXISTING SYSTEM :
? Existing works reviewed above indicated AI-based methods may be applied to address the RAN slicing problem in various contexts.
? When the network performance degrades to a threshold, adjusting existing slices or creating new slices will be triggered, which incurs slice reconfiguration overhead.
? In addition, existing works mainly deal with services attached to relatively loose QoS requirements, and hence developing RAN slicing to support strict URLLC services requires further investigation.
? These limitations may undermine the practicality of the existing optimization-based methods.
DISADVANTAGE :
? In the proposed model, we formulate the choice of the number of resource blocks (RBs) and the location of them in the RBs’ map as a Markov Decision Process (MDP), and we solve this problem by using an actor-critic model.
? This problem is amplified in future 5G applications with strict QoS requirements.
? It is well-known that due to the scheduler’s multidimensional and continuous state space, we can not enumerate the scheduling problem exhaustively.
? Providing ubiquitous connectivity for various devices with different QoS requirements is one of the most challenging issues for mobile network operators.
PROPOSED SYSTEM :
• Cloud/Fog-radio access network (RAN) based architecture, which incorporates the paradigm of cloud and fog computing into wireless networks, has also been proposed.
• The authors in first modeled multi-tenant RAN slicing problem as a non-cooperative stochastic game and then proposed a stochastic learning algorithm for communication resource allocation.
• To adapt to non-stationary traffic and content popularity, content updating policies have been proposed.
• One potential solution to handle a changing content catalogue is adding or removing contents based on their lifetime, as proposed in, so that caching decisions can be made for an evolving catalogue of contents.
ADVANTAGE :
? We evaluate the performance of the proposed models using NS3 with fixed and mobile scenarios.
? Due to the better performance of CDPA-A2C, we omit the D-A2C from second scenario.
? Although CQA has a good performance in the delivery of Voice, Video, and IMS packets, CDPAA2C can considerably enhance the packet delivery ratio for delay-sensitive traffics such as V2X packets in comparison with CQA.
? RL techniques are widely used in cellular networks with various use cases such as video flow optimization, improving energy efficiency in mobile networks , and optimizing resource allocation.
|