Research On Oil Depot Information System Technology Based On Quantum Particle Swarm Algorithm

With the rapid development of the Internet of Things technology,its application in the industrial field can effectively improve the work efficiency in the production process.Domestic oil depot enterprises are actively introducing new technologies and some oil depots have built and put into use wireless transmission platforms.However,the application of the Internet of Things will rapidly increase the number of network edge devices.In addition,the original information system equipment will generate a large amount of data.Improper processing may easily increase the energy consumption of the terminal equipment and the data calculation is slow which cannot achieve intelligent prediction.In the research of improving oil depot information system technology,this paper introduces edge computing for the intensive tasks to be carried out in the oil depot information system and designs a multi-platform task offload algorithm.The three platforms are local computing,mobile edge computing and cloud computing.Mathematically model the problem define the total energy consumption as the transmission energy consumption and value performance during the offloading of the calculation task.Restrictions.Because it is a non-convex problem after modeling,the quantum particle swarm optimization algorithm is used to optimize the solution,so as to determine the intelligent offload strategy for multi-platform tasks.Using MATLAB software simulation,the multi-platform offload algorithm can reduce energy consumption by up to 38.3%.Through the analysis of the results,after using the offload algorithm,multi-task processing can be achieved and the energy consumption can be reduced without a major upgrade of the terminal device hardware.It can solv the problems of insufficient computing power of the terminal device,limited battery capacity and increased network delay.In terms of data processing,the fire fighting information system of the oil depot was improved and a fire intelligent early warning algorithm based on the quantum particle swarm optimization optimized neural network was constructed.The temperature,smoke and CO data were used as the input of the neural network.Fire as the output of the neural network.The quantum particle swarm optimization algorithm is used to optimize therandomly generated weights and thresholds during the operation of the BP neural network,accelerate the speed of the neural network converging to the expected error and increase the global search capability.The intelligent fire warning model is simulated by MATLAB software and the fire probability output by the model is basically consistent with the actual value.In order to further verify the effectiveness of the algorithm,a multi-sensor data collection device was designed.The experimental data was input into the network model,proving that the algorithm can effectively identify open flames,smoldering fires and non-fire conditions,so as to achieve the purpose of improving the accuracy of the oil tank fire warning system.