Simulation of information transmission of IoT communication nodes based on fuzzy hierarchical optical neural network

As a large and complex network with uneven spatial distribution, IoT is widely used in many optical network service industries. However, in the actual use process, it is easy to generate node congestion, resulting in more loaded nodes due to excessive energy consumption, resulting in information transmission link breakage, information loss and other situations. An optimization approach for information transmission of Internet of things nodes based on a fuzzy hierarchical neural network method was presented in order to address the issue of long laser transmission times caused by network congestion brought on by various types of IoT nodes. The key evaluation factors were screened out using the fuzzy analytic hierarchy method, and the comprehensive selection system of information transmission was constructed. Combining with the principle of fuzzy neural network, a comprehensive judgement model for the information transmission of IoT communication nodes based on fuzzy neural network was established, and its accuracy was tested. Based on the fuzzy hierarchical algorithm and the nonlinear mapping ability, this method develops an optimized mathematical model that complies with the requirements of information transmission optimization in the Internet of Things and enhances the global optimization capability and convergence efficiency. Through simulation and analysis of the findings, we found that the suggested method performs better than the particle swarm optimization (PSO) algorithm in terms of network energy consumption, transmission latency, packet loss rate, and other metrics. connectivity and reliability. In terms of network energy consumption, transmission delay and packet loss rate, the proposed algorithm is 35.8, 27.9 and 31.6% lower than PSO algorithm, respectively. The mathematical model realizes the comprehensive judgement and the optimal network path that routes the engineering requirements is obtained through multi-generation evolution. Simulation results show that this method can effectively reduce transmission probability error rate, network congestion and transmission time.