论文检索
期刊
全部知识仓储预印本开放期刊机构
高级检索

基于EABC算法优化RFR模型的电力行业碳排放量预测OA

Forecast of Electricity Industry Carbon Emission Based on EABC Algorithm Optimized RFR Model

中文摘要英文摘要

针对电力行业碳排放量预测问题,在传统人工蜂群算法中引入遗传学习策略进行改进,提出一种基于进化人工蜂群算法优化的随机森林回归预测模型.首先在可拓展随机性环境影响评估模型(stochastic imacts by regression on population affluence and technlogy,STIRPAT)模型基础上确定电力行业碳排放量影响因素,将其作为预测模型的输入自变量,继而利用进化人工蜂群算法优化随机森林回归模型,从而避免模型参数主观设置不合理对预测精度的不利影响,最后运用参数优化后的模型对电力行业碳排放量进行预测.实际测算数据验证结果表明,该模型可以准确反映电力行业未来碳排放趋势,并且与其他预测模型相比,预测精度更高、优势更加明显,能够为节能减排政策制定提供参考借鉴.

In order to solve the forecast problem of electricity industry carbon emissions,the forecast model based on evolve artificial bee colony(EABC)algorithm optimized random forest regression(RFR)was proposed.Firstly,the influence factors of electricity industry carbon emission were determined based on the STIRPAT model,which were considered as the input independent variables of forecast model.Then,the RFR model was optimized by EABC algorithm,and the adverse influence on prediction accuracy due to unreasonable subjective setting of model parameters can be avoid.Finally,the parameter optimized model was used to forecast the electricity industry carbon emission.The verification result of actual measured data shows that the proposed model can accurately reflect the future carbon emission trend of electricity industry,and the model has higher forecast accuracy and more obvious advantage compared with the other forecast models,which can provide a certain reference for policy formulation of energy conservation and emission reduction.

赵中华;张绪辉;王太;刘科;张利孟

国网山东省电力公司电力科学研究院,山东 济南 250003华北电力大学能源动力与机械工程学院,河北 保定 071003

环境科学

碳排放;STIRPAT模型;进化人工蜂群算法;随机森林回归模型

carbon emission;STIRPAT model;EABC algorithm;RFR model

《山东电力技术》 2024 (001)

77-84 / 8

国网山东省电力公司电力科学研究院自主研发项目"碳电协同背景下电力系统碳评价与低碳调度技术研究"(520626220067).Independent Research and Development Project of State Grid Shandong Electric Power Research Institute"Research on electric system carbon assessment and low carbon dispatch technology under carbon electric synergy background"(520626220067).

10.20097/j.cnki.issn1007-9904.2024.01.009

评论

下载量:0
点击量:2