Dynamic prediction method of power carbon emission intensity based on ISSA-CNN-BiLSTM

LI Hongwei; WANG Laijun; LI Shuaibing; YUN Yunyun; YANG Lixia; KANG Yongqiang

doi:10.11930/j.issn.1004-9649.202509020

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Dynamic prediction method of power carbon emission intensity based on ISSA-CNN-BiLSTM

更新时间：2026-07-31

- Dynamic prediction method of power carbon emission intensity based on ISSA-CNN-BiLSTM
- Vol. 59, Issue 7, Pages: 66-77(2026)
- 作者机构：
  
  1. 兰州交通大学自动化与电气工程学院
  2. 兰州交通大学新能源与动力工程学院
- 作者简介：
- 基金信息：
- DOI：10.11930/j.issn.1004-9649.202509020
  CLC：
- Published：2026
- 稿件说明：
移动端阅览
李宏伟, 王来君, 李帅兵, 等. 基于ISSA-CNN-BiLSTM的电力碳排放强度动态预测方法[J]. 中国电力, 2026, 59(7): 66−77.

LI Hongwei, WANG Laijun, LI Shuaibing, et al. Dynamic prediction method of power carbon emission intensity based on ISSA-CNN-BiLSTM[J]. 2026, 59(7): 66-77.
李宏伟, 王来君, 李帅兵, 等. 基于ISSA-CNN-BiLSTM的电力碳排放强度动态预测方法[J]. 中国电力, 2026, 59(7): 66−77. DOI： 10.11930/j.issn.1004-9649.202509020

LI Hongwei, WANG Laijun, LI Shuaibing, et al. Dynamic prediction method of power carbon emission intensity based on ISSA-CNN-BiLSTM[J]. 2026, 59(7): 66-77. DOI： 10.11930/j.issn.1004-9649.202509020.

摘要

电力碳排放强度是衡量电力系统碳排放水平的重要指标，精确计算并预测电力碳排放强度对于有效实施碳排放管理策略、科学制定减排方案具有重要意义。为此，提出一种动态碳排放强度计算及预测方法。基于燃煤机组运行煤耗与负荷的函数关系，构建燃煤机组动态碳排放强度模型。融合发电机组出力特性和动态碳排放强度，形成电网级碳排放强度实时计算模型。通过卷积神经网络（convolutional neural network，CNN）提取动态碳排放强度数据特征，输入到双向长短期记忆网络（bidirectional long short-term memory，BiLSTM），引入改进麻雀优化算法（improved sparrow search algorithm，ISSA），集成Circle初始化种群、自适应因子、柯西变异和Sine映射扰动策略，优化BiLSTM超参数配置，最终构建ISSA-CNN-BiLSTM混合模型，实现短期碳排放强度高精度预测。仿真计算与测试结果表明，与长短期记忆网络（long short-term memory，LSTM）等模型相比，提出的ISSA-CNN-BiLSTM模型在碳排放强度预测中展现出了更高的预测精度和更强的泛化能力。

Abstract

Power carbon emission intensity is an important indicator for measuring the carbon emission level of the power system. Accurate calculation and prediction of power carbon emission intensity are of great significance for effectively implementing carbon emission management strategies and scientifically formulating emission reduction plans. To this end

a dynamic calculation and prediction method for carbon emission intensity is proposed. Firstly

based on the functional relationship between coal consumption and load of coal-fired units

a dynamic carbon emission intensity model for coal-fired units is constructed. Then

by integrating the output characteristics of power generation units and the dynamic carbon emission intensity

a real-time calculation model for grid-level carbon emission intensity is established. On this basis

convolutional neural networks (CNN) are used to extract data features of dynamic carbon emission intensity

which are then input into a bidirectional long short-term memory network (BiLSTM). Additionally

an improved sparrow optimization algorithm (ISSA) is introduced

integrating strategies including circle population initialization

adaptive factors

Cauchy mutation

and Sine mapping perturbation to optimize the hyperparameter configuration of BiLSTM. Finally

a hybrid model of ISSA-CNN-BiLSTM is constructed to achieve high-precision short-term prediction of carbon emission intensity. Simulation and test results show that compared with models such as long short-term memory networks (LSTM)

the proposed ISSA-CNN-BiLSTM model exhibits higher prediction accuracy and stronger generalization capabilities in carbon emission intensity prediction.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Electricity Carbon Coupled Market Modeling Method and Market Optimization Mechanism Based on Dynamic Carbon Emission Intensity

State Estimation Method for Distribution Network Based on Incomplete Measurement Data

Short-Term Load Forecasting Based on Complementary Ensemble Empirical Mode Decomposition and Long Short-Term Memory

Study on Carbon Emission Characteristics and Suggestions on Carbon Emission Management of Coal-fired Power Plant

Fault location method for distribution networks based on traveling wave transfer function difference matrix

Related Author

Xuesong LI

Hao ZHOU

Yu DING

Bin YANG

Wentao WANG

Peng WANG

Tong ZHAO

Huixuan LI

Related Institution

State Grid Jiangsu Electric Power Co., Ltd.

School of Electrical and Electronic Engineering, North China Electric Power University

State Grid Henan Electric Power Company Economic and Technological Research Institute

School of Electrical and Information Engineering, Tianjin University

State Grid Henan Electric Power Company

AI问答

⁰