考虑电力行业碳排放的全国碳价预测OA北大核心CSTPCD
National Carbon Price Prediction Considering Carbon Emissions from the Power Industry
为更好预测全国碳价走势,基于带有外生变量的自回归差分移动平均模型(autoregressive integrated moving average with exogenous variable model,ARIMAX),分履约期和非履约期使用不同的外生变量分别构建了全国碳价预测模型.首先,基于对全国碳市场制度规则研究和交易特征分析,识别出全国碳价在非履约期主要受参与者预期的影响,在履约期碳价主要受企业履约需求驱动;其次,在模型训练方面,采用一种自回归差分移动平均模型,在不同阶段引入不同的外生变量来提升碳价预测效果;最后,基于全国碳市场第一履约期真实价格数据验证结果表明,所提的全国碳价预测模型在准确性方面优于基准模型.
In order to better predict the trend of national carbon prices,a national carbon price prediction model is constructed based on the autoregressive integrated moving average with exogenous variable model(ARIMAX),using different exogenous variables during the fulfillment and non-fulfillment period.Firstly,based on research on the institutional rules of the national carbon market and analysis of trading characteristics,it is found that the national carbon price is mainly influenced by the expectations of participants during the non-fulfillment period,and is mainly driven by the fulfillment demand of enterprises during the fulfillment period.Secondly,in terms of model training,an autoregressive differential moving average model is adopted to introduce different exogenous variables at different stages to improve the effectiveness of carbon price prediction.Finally,the real price data of the first compliance period in the national carbon market are used for verification,and the results show that the proposed national carbon price prediction model in this article is superior to the benchmark model in terms of accuracy.
王一蓉;陈浩林;林立身;唐进
国家电网有限公司大数据中心,北京 100052北京中创碳投科技有限公司,北京 100007
电力行业碳排放碳配额价格预测全国碳市场ARIMAX模型
power industrycarbon emissioncarbon allowancesprice forecastnational carbon marketARIMAX model
《中国电力》 2024 (005)
79-87 / 9
国家电网有限公司大数据中心科技项目(SGSJ 0000KFJS2200034). This work is supported by Science and Technology Project of the Big Data Center of State Grid Corporation of China(No.SGSJ 0000KFJS2200034).
评论