Learning Autonomy in Management of Wireless Random Networks
ABSTARCT :
This paper presents a machine learning strategy that tackles a distributed optimization task in a wireless network with an arbitrary number of randomly interconnected nodes. Individual nodes decide their optimal states with distributed coordination among other nodes through randomly varying backhaul links. This poses a technical challenge in distributed universal optimization policy robust to a random topology of the wireless network, which has not been properly addressed by conventional deep neural networks (DNNs) with rigid structural configurations. We develop a flexible DNN formalism termed distributed message-passing neural network (DMPNN) with forward and backward computations independent of the network topology. A key enabler of this approach is an iterative message-sharing strategy through arbitrarily connected backhaul links. The DMPNN provides a convergent solution for iterative coordination by learning numerous random backhaul interactions. The DMPNN is investigated for various configurations of the power control in wireless networks, and intensive numerical results prove its universality and viability over conventional optimization and DNN approaches.
EXISTING SYSTEM :
? It is possible to accurately sense the entire space by using a low-cost micro sensor compared to the existing sensor.
? However, the existing LEACH method is only based on the model with a static topology, but a case for a disposable sensor is included in an autonomous thing’s environment.
? We compared the results of the dynamic and static topology model with existing LEACH on the aspects of energy loss, number of alive nodes, and throughput.
? Existing IoT sensors have limitations in price, size, and weight, so it is difficult to precisely monitor a wide range of physical spaces.
? The Q-value function is calculated using the existing estimate, not the final return.
DISADVANTAGE :
? Wireless resource management problems with uniform node and resource types are considered in a class of the permutation-invariant problems.
? We address applications in the resource management of interference channels (IFCs) where N transmitter-receiver pairs communicate with the same radio resources.
? Transmitters are designated as nodes in (P) responsible for solving distributed power control problems.
? We test the performance of the DMPNN for tackling two power control problems of (P1) and (P2).
? The node population corresponding to the number of the transmitter-receiver pairs in the wireless network is chosen at random within the range of N ?.
PROPOSED SYSTEM :
• A Q-learning-based cooperative sensing plan is proposed to enhance the performance of spectrum in a wireless network environment.
• In addition, it is proposed I-LEACH to save energy, while communicating within the network.
• In order to increase the stability of the network, we proposed Optimized-LEACH(O-LEACH), which optimizes CH selection.
• Therefore, the proposed F-LEACH in this paper provides more effective distributed clustering compared to the D-LEACH protocol.
• The proposed algorithm sets SINR as state and chooses to use transmit power as action.
• The basic LEACH protocol and implementation of the proposed algorithm are used in the statistic and dynamic topology models.
ADVANTAGE :
? Supervised learning techniques save significant computational complexity at the cost of the performance, while unsupervised learning algorithms to optimize network utilities have also been developed in network applications.
? The FNN baseline provides the state-of-the-art performance of unsupervised learning methods.
? One can see that the DMPNN, when tested in an edgeless setup of no node interaction, still shows a good performance that outperforms naive peak power and random power allocation schemes.
? Although the choice of a small value for M simplifies the system design, it generally degrades the learning performance.
? Nodes exchange high-dimensional messages for an improved performance with limited coordination.
|