基于IFA-BP神经网络模型的变电站碳排放预测

doi:10.16088/j.issn.1001-6600.2025022101

摘要/Abstract

摘要： 针对现有变电站碳排放量预测模型存在考虑指标较少、数据更新慢等问题,本文提出一种基于改进萤火虫算法(improved firefly algorithm,IFA)优化反向传播(back propagation, BP)神经网络的变电站碳排放预测模型。首先,针对萤火虫算法(firefly algorithm,FA)收敛速度过慢以及易陷入局部最优等问题,引入教与学因子,修改萤火虫位置更新过程,以提高群体适应度。其次,引入IFA算法对BP神经网络模型进行超参数寻优,并构建IFA-BP神经网络预测模型。然后,基于CRITIC法筛选预测模型输入层的关键碳排放指标。最后,利用训练集数据训练预测模型,基于训练好的模型对变电站的碳排放量进行预测。仿真结果表明,相较于3种对比方案,本文IFA-BP神经网络预测模型分别在均方根误差(root mean square error,RMSE)上降低59.61%、15.77%和26.65%,在决定系数(coefficient of determination,R²)上提高5.66%、1.46%和1.15%,充分验证了本文所提变电站碳排放预测模型的可行性与优越性。

关键词: 碳排放, 变电站, 改进萤火虫算法, BP神经网络, 教与学因子

Abstract: To solve the problems of existing carbon emission prediction models such as a limited number of indicators and slow data updates, this article proposes a substation carbon emission prediction model based on the improved firefly algorithm (IFA) optimized BP neural network. Firstly, in response to the slow convergence speed and tendency to fall into local optima in the firefly algorithm (FA), teaching and learning factors are introduced to modify the firefly position update process to improve population fitness. Secondly, IFA is introduced to perform hyper-parameter optimization on the BP neural network model, and an IFA-BP neural network prediction model is constructed. Then, based on the CRITIC method, select key carbon emission indicators for the input layer of the prediction model. Finally, the prediction model is trained using the training set data to predict the carbon emissions of the substation based on the trained model. The simulation results show that compared with the three comparison schemes, the root mean square error (RMSE) of the proposed IFA-BP neural network prediction model decreases by 59.61%, 15.77% and 26.65%, respectively. The coefficient of determination (R²) increases by 5.66%, 1.46% and 1.15%. The feasibility and superiority of the substation carbon emission prediction model proposed in this paper are fully verified.

Key words: carbon emissions, substation, IFA optimization algorithm, BP neural network, teaching and learning factors

中图分类号: X773; TP183; TM63

王巍, 李智威, 张赵阳, 张洪, 周蠡, 王振, 黄放, 王灿. 基于IFA-BP神经网络模型的变电站碳排放预测[J]. 广西师范大学学报（自然科学版）, 2026, 44(2): 103-114.

WANG Wei, LI Zhiwei, ZHANG Zhaoyang, ZHANG Hong, ZHOU Li, WANG Zhen, HUANG Fang, WANG Can. Carbon Emission Prediction of Substation Based on IFA-BP Neural Network Model[J]. Journal of Guangxi Normal University(Natural Science Edition), 2026, 44(2): 103-114.

参考文献

[1] 倪志,文中,王灿,等.含光热MRH和燃气掺氢的综合能源系统优化运行[J].广西师范大学学报(自然科学版),2024,42(1):54-66.DOI:10.16088/j.issn.1001-6600.2023042407.
[2] 许伦辉, 王晴, 朱群强, 等.基于碳足迹的城市客运交通优化研究[J].广西师范大学学报(自然科学版), 2015, 33(4):1-5.DOI:10.16088/j.issn.1001-6600.2015.04.001.
[3] 赵迪, 文中, 吴倩, 等.5G基站与光热电站电-热耦合下的综合能源系统低碳优化调度[J].广西师范大学学报(自然科学版), 2023, 41(4):47-60.DOI:10.16088/j.issn.1001-6600.2023021503.
[4] 闫文文, 文中, 王爽, 等.基于AA-CAES电站和综合需求响应的供暖期弃风消纳策略[J].广西师范大学学报(自然科学版), 2024, 42(2):55-68.DOI:10.16088/j.issn.1001-6600.2023050805.
[5] 王灿, 李欣然, 赵积红, 等.基于P2G与富氧燃烧联合运行的多能源低碳调度[J].电力工程技术, 2023, 42(3):139-148.DOI:10.12158/j.2096-3203.2023.03.016.
[6] 王灿, 张雪菲, 凌凯, 等.基于区间概率不确定集的微电网两阶段自适应鲁棒优化调度[J].中国电机工程学报, 2024, 44(5):1750-1764.DOI:10.13334/j.0258-8013.pcsee.221968.
[7] 冯健冰, 任洲洋, 姜云鹏, 等.电力系统定碳排运行域:概念与方法[J].中国电机工程学报, 2024, 44(22):8846-8860.DOI:10.13334/j.0258-8013.pcsee.231021.
[8] 田福银, 马骏, 王灿, 等.基于双层主从博弈的综合能源系统多主体低碳经济运行策略[J].中国电力, 2022, 55(11):184-193.DOI:10.11930/j.issn.1004-9649.202206090.
[9] 贺旭辉, 王灿, 李欣然, 等.计及CLHG-SOFC碳捕集的多能源系统低碳优化调度[J].智慧电力, 2023, 51(5):57-64.
[10] 刘天蔚, 边晓燕, 吴珊, 等.电力系统碳排放核算综述与展望[J].电力系统保护与控制, 2024, 52(4):176-187.DOI:10.19783/j.cnki.pspc.230735.
[11] 陈巳阳, 韩利, 方济中, 等.基于不确定参数的变电站碳储量预估方法[J].中国电力, 2024, 57(4):200-210.DOI:10.11930/j.issn.1004-9649.202311078.
[12] 曾一鸣, 曹姗姗, 孔繁涛, 等.基于小波包去噪和深度学习的电力行业碳排放预测模型研究[J].河南科学, 2024, 42(8):1102-1110.DOI:10.3969/j.issn.1004-3918.2024.08.002.
[13] HUANG S Y, XIAO X P, GUO H.A novel method for carbon emission forecasting based on EKC hypothesis and nonlinear multivariate grey model:evidence from transportation sector[J].Environmental Science and Pollution Research, 2022, 29(40):60687-60711.DOI:10.1007/s11356-022-20120-5.
[14] REZA S, FERREIRA M C, MACHADO J J M, et al.An actor-critic-based adapted deep reinforcement learning model for multi-step traffic state prediction[J].Applied Soft Computing, 2025, 184:113783.DOI:10.1016/j.asoc.2025.113783.
[15] ZHANG L F, LU G, YAN X Q, et al.A differential evolution optimized hybrid XGBoost for accurate carbon emission prediction[J].Environmental Modelling & Software, 2025, 193:106627.DOI:10.1016/j.envsoft.2025.106627.
[16] SAPNKEN F E, HONG K R, CHOPKAP NOUME H, et al.A grey prediction model optimized by meta-heuristic algorithms and its application in forecasting carbon emissions from road fuel combustion[J].Energy, 2024, 302:131922.DOI:10.1016/j.energy.2024.131922.
[17] 沙爱敏, 陈婷, 吕凡任, 等.基于组合预测模型的交通碳排放量预测研究[J].节能, 2023, 42(1):72-75.DOI:10.3969/j.issn.1004-7948.2023.01.019.
[18] WANG Z L, WANG S H, LI Y.Design of substation carbon emission prediction model based on cloud model[J].E3S Web of Conferences, 2023, 393:03002.DOI:10.1051/e3sconf/202339303002.
[19] 陈远东, 孟辉, 李猛克, 等.基于支持向量机的变压器碳排放预测模型[J].包装工程, 2024, 45(1):254-261.DOI:10.19554/j.cnki.1001-3563.2024.01.030.
[20] 祁升龙, 芦翔, 刘海涛, 等.基于遗传算法优化的BP神经网络在配电网故障诊断中的应用[J].电力科学与技术学报, 2023, 38(3):182-187, 196.DOI:10.19781/j.issn.1673-9140.2023.03.020.
[21] JIA M S, WANG X W, ZHANG W, et al.Prediction of CO/NO_x emissions and the smoldering characteristic of sewage sludge based on back propagation neural network[J].Environmental Pollution, 2024, 342:123049.DOI:10.1016/j.envpol.2023.123049.
[22] 胡振, 龚薛, 刘华.基于BP模型的西部城市家庭消费碳排放预测研究:以西安市为例[J].干旱区资源与环境, 2020, 34(7):82-89.DOI:10.13448/j.cnki.jalre.2020.187.
[23] 范德成, 张修凡.基于PSO-BP神经网络模型的中国碳排放情景预测及低碳发展路径研究[J].中外能源, 2021, 26(8):11-19.
[24] 文华, 吴敏, 杨兆山.基于GA-BP神经网络的柴油机NO_x瞬态排放预测[J].南昌大学学报(工科版), 2012, 34(1):62-65.DOI:10.3969/j.issn.1006-0456.2012.01.014.
[25] 张迪, 王彤彤, 支金虎.基于IPSO-BP神经网络模型的山东省碳排放预测及生态经济分析[J].生态科学, 2022, 41(1):149-158.DOI:10.14108/j.cnki.1008-8873.2022.01.017.
[26] JIE P F, ZHOU Y, ZHANG Z J, et al.Heating energy consumption prediction based on improved GA-BP neural network model[J].Energy, 2025, 328:136392.DOI:10.1016/j.energy.2025.136392.
[27] LI S Y, YAO L L, ZHANG Y C, et al.China’s provincial carbon emission driving factors analysis and scenario forecasting[J].Environmental and Sustainability Indicators, 2024, 22:100390.DOI:10.1016/j.indic.2024.100390.
[28] 王一蓉, 陈浩林, 林立身, 等.考虑电力行业碳排放的全国碳价预测[J].中国电力, 2024, 57(5):79-87.
[29] 刘含笑, 单思珂, 魏书洲, 等.基于生命周期法的煤电碳足迹评估[J].中国电力, 2024, 57(7):227-237.DOI:10.11930/j.issn.1004-9649.202404039.
[30] 叶远波, 李端超, 汪胜和, 等.基于广义S变换和皮尔逊相关系数的新能源接入电网纵联保护[J].电力科学与技术学报, 2024, 39(6):194-202.DOI:10.19781/j.issn.1673-9140.2024.06.020.
[31] 邹港, 赵斌, 罗强, 等.基于PCA-VMD-MVO-SVM的短期光伏输出功率预测方法[J].电力科学与技术学报, 2024, 39(5):163-171.DOI:10.19781/j.issn.1673-9140.2024.05.017.
[32] 李娟, 汪家铭, 许苏迪, 等.基于量子萤火虫算法的配电网故障恢复策略[J].中国电力, 2023, 56(12):191-198.
[33] 从帆平, 周建萍, 茅大钧, 等.基于改进教与学算法的含电能路由器的电力系统无功优化[J].电力建设, 2022, 43(6):110-118.DOI:10.12204/j.issn.1000-7229.2022.06.012.
[34] 吴青峰, 杨艺涛, 刘立群, 等.基于GA-SA-BP神经网络的锂电池健康状态估算方法[J].电力系统保护与控制, 2024, 52(19):74-84.DOI:10.19783/j.cnki.pspc.240248.
[35] 彭威龙, 曾松梧, 张宝庆, 等.基于GA-BP模型的大型接地网腐蚀速率预测方法[J].电力科学与技术学报, 2024, 39(3):264-270.DOI:10.19781/j.issn.1673-9140.2024.03.028.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed