基于改进Tent映射的APSO-LSTM天然气需求量预测模型  

APSO-LSTM model based on improved Tent mapping for natural gas demand forecasting

作　　者：温泉 石小平[1] 张利分[1,2] 李蕾 WEN Quan;SHI Xiaoping;ZHANG Lifen;LI Lei(College of Logistics and Transport Management,Hubei Communications Technical College;School of Transportation and Logistics Engineering,Wuhan University of Technology;Changjiang Waterway Institute of Planning and Design)

机构地区：[1]湖北交通职业技术学院物流与交通管理学院 [2]武汉理工大学交通与物流工程学院 [3]长江航道规划设计研究院

出　　处：《油气储运》2023年第6期702-712,共11页Oil & Gas Storage and Transportation

基　　金：湖北能源集团科技攻关项目“湖北能源气化长江工程战略布局规划研究”,EN0T-ZX-F2018-100。

摘　　要：为了准确预测多维影响因素条件下天然气需求量的变化,引入自适应惯性权重因子改进粒子群优化算法(Particle Swarm Optimization,PSO),将构建的自适应粒子群优化算法(Adaptive Particle Swarm Optimization,APSO)与改进Tent映射相结合,对长短期记忆(Long Short-Time Memory,LSTM)神经网络模型中的隐含层节点数、学习轮数、初始学习速率进行超参寻优,改变传统LSTM模型凭经验设定超参数的不足。基于1999—2020年的10项强相关性影响因素细分数据进行算例验证,并对2021—2030年中国的天然气需求量进行预测。结果表明:改进Tent-APSOLSTM模型组合参数寻优效果最佳,可以更好地适用于中国天然气中短期需求量预测工作。(图5,表6,参34)In order to accurately forecast the change of natural gas demand under the condition of multi-dimensional influencing factors,the adaptive inertia weight factor was introduced to improve the Particle Swarm Optimization(PSO)algorithm.Then,by combining the constructed Adaptive Particle Swarm Optimization(APSO)algorithm with the improved Tent mapping,hyper-parameter optimization was performed to the hidden layer nodes,the learning rounds and the initial learning rate in the Long Short-Time Memory Network(LSTM)model,so as to change the deficiency of the traditional LSTM model of setting the hyper-parameters empirically.Moreover,the calculation example was verified based on the subdivided data of 10 highly correlated influencing factors from 1999 to 2020,and the natural gas demand from 2021 to 2030 was forecasted.The results show that the improved Tent-APSO-LSTM model has the best optimization effect on the parameters and could be better applied to the gas demand forecasting in short and medium term.(5 Figures,6 Tables,34 References)

关 键 词：天然气需求量 Tent混沌映射 APSO-LSTM PSO-LSTM LSTM BP神经网络 预测 

分 类 号：TE832[石油与天然气工程—油气储运工程]