Quantum Learning Enabled Green Communication for Next Generation Wireless Systems
ABSTARCT :
Next generation wireless systems have witnessed significant R&D attention from academia and industries to enable wide range of applications for connected environment around us. The technical design of next generation wireless systems in terms of relay and transmit power control is very critical due to the ever-reducing size of these sensor enabled systems. The growing demand of computation capability in these systems for smart decision making further diversified the significance of relay and transmit power control. Towards harnessing the benefits of Quantum Reinforcement Leaning (QRL) in the design of next generation wireless systems, this paper presents a framework for joint optimal Relay and transmit Power Selection (QRL-RPS). In QRL-RPS, each sensor node learns using its present and past local state’s knowledge to take optimal decision in relay and transmit power selection. Firstly, RPS problem is modelled as a Markov Decision Process (MDP), and then QRL optimization aspect of the MDP problem is formulated focusing on joint optimization of energy consumption and throughput as network utility. Secondly, a QRL-RPS algorithm is developed based on Grover’s iteration to solve the MDP problem. The comparative performance evaluation attests the benefit of the proposed framework as compared to the state-of-the-art techniques.
EXISTING SYSTEM :
? In the communications and computing domains, the existing protocols can be enhanced with more efficient algorithms by exploiting the physical phenomena available in the quantum world with the utilization of quantum principles and tools.
? To this end, one of the objectives of this paper is to provide a detailed classification of existing ML techniques along with their applications in B5G communications networks.
? To address this, Quantum Decision Theory (QDT) seems to be a promising approach and has been already investigated in some existing literature.
? The performance enhancement of MIMO-OFDM system with the joint channel estimation and MUD has been depicted in several existing works.
DISADVANTAGE :
? To solve the aforementioned problem, reinforcement learning (RL) approach has been used for optimal decision making .
? However, the above suggested schemes use a Q-table to save state-value and can only solve the problems with small states because the storage capacity of Qtable is limited.
? To sort out the Q-learning problem, a Deep RL in WSN was presented, named as DQ-RSS.
? The direct communication link between source and sink is assumed to be weak because of pathloss and fading problem.
? Thus, local solutions for joint optimal relay and transmit power selection problem at each point-to-point communication leads to globally optimal solution for network.
PROPOSED SYSTEM :
• A novel QC-assisted ML and QML-based framework for 6G communication networks is proposed.
• In the proposed framework context, various potential enabling technologies for 6G at network-infrastructure, networkedge, air interface, and user-side are also discussed thoroughly.
• The proposed learning method is shown to enhance the network sum effective capacity by about 30% compared to the baseline random caching approaches.
• In this regard, a model-free distributed reinforcement learning method for power allocation is proposed, in which Channel State Information (CSI) and QoS indicators are exploited to adapt the transmit power.
ADVANTAGE :
? The RL based relay selection has been improved using Q-learning for better network performance in terms of reliability, outage probability, bit-error rate and network adaptivity.
? However, the classical RL technique is not suitable because of its slower learning performance, unexpected exploration and exploitation strategy and limited data analytics .
? The performance of the proposed algorithm is evaluated using Pyquil programming on Rigetti’s Forest quantum virtual machine, and the results of the framework is compared with state-of-the-art techniques.
? The QRL-RPS technique achieves such good performance by taking the advantage of the quantum property such as quantum superposition and quantum parallelisms used for selection of joint optimal relay and transmit power at each network state.
|