文章摘要
李鹏,戚凯,张培强,张世旭,闫志兴,庞柯成,朱晓辉,张宁.计及用户低碳需求响应行为的动态碳排放因子预测方法[J].电力需求侧管理,2026,28(2):77-85
计及用户低碳需求响应行为的动态碳排放因子预测方法
Dynamic carbon emission factor prediction method considering user low-carbon demand response behavior
投稿时间：2025-09-26  修订日期：2025-12-17
DOI：10.3969/j.issn.1009-1831.2026.02.012
中文关键词: 碳排放因子  低碳需求响应  长短期记忆神经网络  动态碳排放因子预测
英文关键词: carbon emission factor  low carbon demand response  long short-term memory neural networks  dynamic carbon emission factor prediction
基金项目:许继电气重大科技攻关项目(2024G307)；国家自然科学基金项目(52477103)
作者单位
李鹏 河南许继仪表有限公司,河南 许昌 461000 
戚凯 河南许继仪表有限公司,河南 许昌 461000 
张培强 河南许继仪表有限公司,河南 许昌 461000 
张世旭 清华四川能源互联网研究院,成都 610042 
闫志兴 河南许继仪表有限公司,河南 许昌 461000 
庞柯成 河南许继仪表有限公司,河南 许昌 461000 
朱晓辉 河南许继仪表有限公司,河南 许昌 461000 
张宁 清华四川能源互联网研究院,成都 610042 ；清华大学 电机工程与应用电子技术系,北京 100084 
摘要点击次数: 0
全文下载次数: 0
中文摘要:
      针对当前用户侧低碳用能缺乏关键引导信号的问题,提出一种计及用户侧低碳需求响应行为的动态碳排放因子预测方法。首先,基于碳排放流理论构建用户动态用电碳排放因子计算模型,结合系统运行模拟构建碳排放因子数据池;其次,构建电力用户面向动态碳排放因子的低碳用能响应行为模型,并提出计及用户侧低碳需求响应行为的动态碳排放因子预测方法;然后,基于长短期记忆神经网络开展碳排放因子预测,实现基于任意源荷输入对给定系统的节点级动态碳排放因子有效预测;最后,基于PJM-5节点电力系统与某高比例可再生能源36节点电力系统开展了算例分析,验证了所提方法在预测计及用户低碳需求响应的节点级用电碳排放因子方面的有效性。
英文摘要:
      In view of the current problem of lack of key guiding signals for low-carbon energy consumption on the user side, a dynamic carbon emission factor prediction method taking into account the low-carbon demand response behavior on the user side is proposed. First, a user dynamic electricity carbon emission factor calculation model is constructed based on the carbon emission flow theory, and a carbon emission factor data pool is constructed in combination with system operation simulation. Second, a low-carbon energy consumption response behavior model for power users facing dynamic carbon emission factors is constructed, and a dynamic carbon emission factor prediction method taking into account the low-carbon demand response behavior on the user side is proposed. Carbon emission factor prediction is carried out based on LSTM neural network, and effective prediction of node-level dynamic carbon emission factors for a given system based on arbitrary source and load input is achieved. Finally, a case analysis is carried out based on a PJM-5 node power system and a 36-node power system with a high proportion of renewable energy, which verifies the effectiveness of the proposed method in predicting node-level electricity carbon emission factors taking into account the user's low-carbon demand response.
查看全文   查看/发表评论  下载PDF阅读器
关闭