基于PSO-LSTM网络模型的建筑碳排放峰值预测  

Forecast of Peak Carbon Emissions of Buildings Based on PSO-LSTM Model

作　　者：唐晓灵[1] 刘嘉敏 Tang Xiaoling;Liu Jiamin(School of Management,Xi'an University of Architecture and Technology,Xi'an 710055,China)

机构地区：[1]西安建筑科技大学管理学院,陕西西安710055

出　　处：《科技管理研究》2023年第1期191-198,共8页Science and Technology Management Research

基　　金：科技部国际科技合作项目-子项目“能源安全、低碳减排、环境保护、可持续发展的必由之路-可再生能源建筑研究”(004/2028901044)。

摘　　要：在对BP神经网络、LSTM网络和PSO-LSTM模型在碳排放预测方面进行对比选优的基础上,通过训练好的PSO-LSTM模型在低碳、基准、高碳3种情景下,分别对建筑碳排放峰值进行预测。结果表明,低碳、基准、高碳3种情景的建筑碳排放峰值分别为226 774.56万吨、239 738.11万吨和253 379.47万吨;达峰时间分别为2029年、2032年和2033年。可见,在当前社会发展状况下,仍难在2030年前实现建筑领域的碳达峰,还需采取相应的低碳措施来推进目标的实现。Based on the comparing and selecting of BP neural network, LSTM network and PSO-LSTM model in the prediction of carbon emissions, the trained PSO-LSTM model was used to predict the peak carbon emission of buildings under three scenarios of low carbon, baseline and high carbon, respectively. The results show that the peak building carbon emissions for the low-carbon, baseline and high-carbon scenarios are 226 774.56 million tons, 239738.11 million tons, and 253 379.47 million tons;and the peak time is 2029, 2032 and 2033. It can be seen that in the existing social development context, it is still difficult to achieve the carbon peak in the building sector by 2030, and corresponding low-carbon measures are needed to promote the achievement of the goal.

关 键 词：建筑碳排放 PSO-LSTM 碳达峰 情景分析法 

分 类 号：F062.2[经济管理—政治经济学] F113.3