Optimal scheduling of integrated energy systems based on improved CNN-LSTM and multi-objective RIME algorithm

doi:10.3969/j.issn.2097-0706.2026.04.005

Abstract

Abstract:

To improve the forecast accuracy and operation economic efficiency of integrated energy systems under multi-energy coupling conditions， an electric-thermal load forecasting and optimal scheduling method was proposed based on an improved convolutional neural network and long short-term memory neural network（CNN-LSTM）. The method integrated CNN and LSTM， introduced an attention mechanism to enhance the capabilities of feature extraction and temporal response， and achieved the coordinated optimization of the forecasting model and operation strategy in combination with the multi-objective rime optimization algorithm（MORIME）. Simulation results based on typical summer and winter days of a park in Jinan showed that the improved CNN-LSTM model achieved a 32.6% reduction in the mean absolute percentage error of load forecasting compared to that of the traditional model. With MORIME， the total operation costs of the system in summer and winter reduced by 12.7% and 10.3% respectively， and the energy utilization efficiency of the system increased by 3.8% to 4.1%. The efficient coordination of the electric-thermal energy storage system and the time-shift utilization of energy significantly improve the operation economic efficiency and energy utilization efficiency of the system， thereby providing a new technical approach for the optimal scheduling of complex multi-energy systems.

Key words: integrated energy system, load forecasting, convolutional neural network, long short-term memory neural network, attention mechanism, multi-objective rime optimization algorithm

CLC Number:

TK01

ZHU Lijuan, LIU Jiying, YU Mingzhi, YANG Kaimin, MAO Yudong. Optimal scheduling of integrated energy systems based on improved CNN-LSTM and multi-objective RIME algorithm[J]. Integrated Intelligent Energy, 2026, 48(4): 35-46.

Figures/Tables 21

Fig.1

Fig.2

Fig.3

Fig.4

Fig5

Table 1

Table 2

Fig.6

Table 3

Fig.7

Fig.8

Fig.9

Fig.10

Fig.11

Fig.12

Fig.13

Fig.14

Fig.15

Fig.16

Fig.17

Table 4

References 29

[1]	LU T G, YI X N, LI J, et al. Collaborative planning of integrated hydrogen energy chain multi-energy systems: A review[J]. Applied Energy, 2025, 393: 126019. doi: 10.1016/j.apenergy.2025.126019
[2]	张沈习, 王丹阳, 程浩忠, 等. 双碳目标下低碳综合能源系统规划关键技术及挑战[J]. 电力系统自动化, 2022, 46(8): 189-207.
	ZHANG Shenxi, WANG Danyang, CHENG Haozhong, et al. Key technologies and challenges of low-carbon integrated energy system planning for carbon emission peak and carbon neutrality[J]. Automation of Electric Power Systems, 2022, 46(8): 189-207.
[3]	李亮, 袁至, 李骥. 考虑源荷多重不确定性的含氢综合能源系统三阶段随机鲁棒日前优化[J]. 电网技术, 2025, 49(8): 3199-3208.
	LI Liang, YUAN Zhi, LI Ji. Three-stage stochastic robust day-ahead optimization of hydrogen-containing integrated energy system considering source-load multiple uncertainties[J]. Power System Technology, 2025, 49(8): 3199-3208.
[4]	周丹, 蒋达, 朱嘉炜, 等. 综合能源系统不确定性分析综述与展望[J]. 高技术通讯, 2025, 35(5): 513-525.
	ZHOU Dan, JIANG Da, ZHU Jiawei, et al. Review and prospects of uncertainty analysis of integrated energy system[J]. Chinese High Technology Letters, 2025, 35(5): 513-525.
[5]	LI K, ZHANG Q, YU C M, et al. Transfer learning-based multi-energy load forecasting method for integrated energy system with zero-shot[J]. Applied Energy, 2025, 401: 126769. doi: 10.1016/j.apenergy.2025.126769
[6]	谭丹, 陈聪, 陶悦玥, 等. 基于多能互补的综合能源系统优化设计与应用研究[J]. 自动化应用, 2025, 66(15): 158-160, 164.
	TAN Dan, CHEN Cong, TAO Yueyue, et al. Research on optimal design and application of integrated energy systems based on multi-energy complementation[J]. Automation Application, 2025, 66(15): 158-160, 164.
[7]	张玉, 曾繁敏, 林意杰, 等. 考虑多不确定性和需求响应的综合能源系统鲁棒优化调度研究[J]. 太阳能学报, 2025, 46(9): 688-695.
	ZHANG Yu, ZENG Fanmin, LIN Yijie, et al. Research on robust optimal scheduling of integrated energy systems considering multiple uncertainties and demand response[J]. Acta Energiae Solaris Sinica, 2025, 46(9): 688-695.
[8]	包盛宝, 王文成. 考虑双层电转气与需求响应的综合能源系统低碳优化: 以南宁江南工业园区为例[J]. 科学技术与工程, 2025, 25(9): 3730-3738.
	BAO Shengbao, WANG Wencheng. Low-carbon optimization of integrated energy system considering double-layer power-to-gas and demand response: Taking Nanning Jiangnan industrial park as an example[J]. Science Technology and Engineering, 2025, 25(9): 3730-3738.
[9]	ZHAO Q N, MA Z J, WEI S F, et al. Development, modeling and optimization of a solar-hydrogen-electricity-thermal-based integrated energy system for remote cold regions[J]. Energy Conversion and Management, 2026, 347: 120582. doi: 10.1016/j.enconman.2025.120582
[10]	UMAIR H, WANG H Z, PENG J C, et al. Transformer-based renewable energy forecasting: A comprehensive review[J]. Renewable and Sustainable Energy Reviews, 2026, 226: 116356. doi: 10.1016/j.rser.2025.116356
[11]	李鑫伟, 陈彬剑, 于明志, 等. 基于多目标优化的多能互补冷热电联产系统运行优化研究[J]. 热力发电, 2024, 53(7): 73-81.
	LI Xinwei, CHEN Binjian, YU Mingzhi, et al. Research on operation optimization of multi-energy complementary cogeneration system based on multi-objective optimization[J]. Thermal Power Generation, 2024, 53(7): 73-81.
[12]	王帆, 邢志坤, 陈振华, 等. 基于深度学习的综合能源系统多元负荷预测[J]. 河北电力技术, 2025, 44(3):11-21.
	WANG Fan, XING Zhikun, CHEN Zhenhua, et al. Multi-energy load forecasting of integrated energy system based on deep learning[J]. Hebei Electric Power Technology, 2025, 44(3): 11-21.
[13]	罗林霖, 王霄, 何志琴, 等. 基于滚动模态分解和GCN-DABiLSTM的综合能源系统多元负荷预测模型[J]. 广东电力, 2025, 38(9): 130-144.
	LUO Linlin, WANG Xiao, HE Zhiqin, et al. Multi-load forecasting model for integrated energy system based on rolling mode decomposition and GCN-DABiLSTM[J]. Guangdong Electric Power, 2025, 38(9): 130-144.
[14]	WANG C, WANG Y, ENRICO Z, et al. Short-term load forecasting method for integrated energy systems based on graph neural network and multi-task balance[J]. International Journal of Electrical Power and Energy Systems, 2025, 172: 111195.
[15]	范见雪, 陈鑫. 基于CNN-LSTM-Attention的空调负荷预测[J]. 苏州科技大学学报(自然科学版), 2025, 42(3): 70-77.
	FAN Jianxue, CHEN Xin. Air conditioning load forecasting based on CNN-LSTM-Attention[J]. Journal of Suzhou University of Science and Technology (Natural Science), 2025, 42(3): 70-77.
[16]	CHANG C, MA G X, ZHANG J H, et al. Investigation on the CNN-LSTM-MHA-based model for the heating energy consumption prediction of residential buildings considering active and passive factors[J]. Energy, 2025, 333: 137508. doi: 10.1016/j.energy.2025.137508
[17]	张语珊, 曾德良. 基于特征选择与优化混合神经网络的长距离供热负荷预测[J]. 热能动力工程, 2025, 40(8): 100-110.
	ZHANG Yushan, ZENG Deliang. Long distance heating load prediction based on feature selection and improved hybrid neural network[J]. Journal of Engineering for Thermal Energy and Power, 2025, 40(8): 100-110.
[18]	万炜兴, 谢丽蓉, 张龙军, 等. 基于时间特征分析的NST-IRN组合模型短期负荷功率预测[J]. 太阳能学报, 2025, 46(7): 62-72.
	WAN Weixing, XIE Lirong, ZHANG Longjun, et al. Short-term load power forecasting using NST-IRN combined model based on temporal feature analysis[J]. Acta Energiae Solaris Sinica, 2025, 46(7): 62-72.
[19]	LI Y B, HU W K, ZHANG F, et al. Multi-objective collaborative operation optimization of park-level integrated energy system clusters considering green power forecasting and trading[J]. Energy, 2025, 319: 135055. doi: 10.1016/j.energy.2025.135055
[20]	LAN P H, CHEN S, WANG F. Carbon and electricity trading for the green hydrogen-based integrated energy system: A deep reinforcement learning-based scheduling optimization[J]. Renewable Energy, 2026, 256: 124176. doi: 10.1016/j.renene.2025.124176
[21]	MA Y Y, LI S T, ZHOU S L, et al. Performance degradation prediction of proton exchange membrane fuel cells based on CNN-LSTM network with squeeze-and-excitation attention mechanism[J]. Energy, 2025, 335: 138127. doi: 10.1016/j.energy.2025.138127
[22]	杨澜倩, 郭锦敏, 田慧丽, 等. 基于CNN-LSTM-Self attention的园区负荷多尺度预测研究[J]. 综合智慧能源, 2025, 47(2): 79-87. doi: 10.3969/j.issn.2097-0706.2025.02.008
	YANG Lanqian, GUO Jinmin, TIAN Huili, et al. Research on multi-scale load prediction in parks based on CNN-LSTM-Self attention[J]. Integrated Intelligent Energy, 2025, 47(2): 79-87. doi: 10.3969/j.issn.2097-0706.2025.02.008
[23]	DU R Y, CHEN H F, YU M, et al. 3DTCN-CBAM-LSTM short-term power multi-step prediction model for offshore wind power based on data space and multi-field cluster spatio-temporal correlation[J]. Applied Energy, 2024, 376: 124169. doi: 10.1016/j.apenergy.2024.124169
[24]	张元曦, 杨国华, 杨娜, 等. 基于K-means聚类的LSTM-SVR-DE光伏功率组合预测[J]. 综合智慧能源, 2025, 47(2): 71-78. doi: 10.3969/j.issn.2097-0706.2025.02.007
	ZHANG Yuanxi, YANG Guohua, YANG Na, et al. Photovoltaic power prediction based on K-means clustering and the LSTM-SVR-DE model[J]. Integrated Intelligent Energy, 2025, 47(2): 71-78. doi: 10.3969/j.issn.2097-0706.2025.02.007
[25]	MELALKIA L, BERREZZEK F, KHELIL K, et al. A hybrid error correction method based on EEMD and ConvLSTM for offshore wind power forecasting[J]. Ocean Engineering, 2025, 325: 120773. doi: 10.1016/j.oceaneng.2025.120773
[26]	PANDYA S B, KALITA K, JANGIR P, et al. Multi-objective RIME algorithm-based techno-economic analysis for security constraints load dispatch and power flow including uncertainties model of hybrid power systems[J]. Energy Reports, 2024, 11: 4423-4451. doi: 10.1016/j.egyr.2024.04.016
[27]	ZHONG X Y, YAO X J, QIAO K J, et al. A dynamic granularity-based multi-objective evolutionary algorithm for coal mine integrated energy system dispatch optimization[J]. Expert Systems with Applications, 2025, 296:129142. doi: 10.1016/j.eswa.2025.129142
[28]	刘涛, 麻德权. 基于CBAM-CNN的涡旋压缩机故障诊断[J]. 振动、测试与诊断, 2024, 44(5): 900-906.
	LIU Tao, MA Dequan. Fault diagnosis of scroll compressor based on improved CBAM-CNN[J]. Journal of Vibration,Measurement & Diagnosis, 2024, 44(5): 900-906.
[29]	赵飞, 王媛. 计及碳交易机制和耦合需求响应的综合能源系统优化调度[J]. 现代电子技术, 2025, 48(18): 91-98.
	ZHAO Fei, WANG Yuan. IES optimal scheduling with carbon trading mechanism and coupled demand response[J]. Modern Electronic Technique, 2025, 48(18): 91-98.

模块	主要结构/超参数	取值/设置
CNN-CBAM空间特征提取	卷积层数；卷积核；池化方式	4层；3×3；2×2最大池化
CBAM模块	通道注意力压缩比；空间卷积核	4；4×4
ConvLSTM时间特征提取	层数；卷积核；隐藏单元数	2层；3×3；64，128
注意力与全连接层	注意力头数；全连接层神经元数	8；32/64/32
训练设置	优化算法；最大训练轮数	MORIME；100

参数	数值	参数	数值
${P}_{\mathrm{m}\mathrm{t}}^{\mathrm{m}\mathrm{i}\mathrm{n}}$/MW	15	${P}_{\mathrm{m}\mathrm{t}}^{\mathrm{m}\mathrm{a}\mathrm{x}}$/MW	65
${P}_{\mathrm{e}\mathrm{b}}^{\mathrm{m}\mathrm{i}\mathrm{n}}$/MW	0	${P}_{\mathrm{e}\mathrm{b}}^{\mathrm{m}\mathrm{a}\mathrm{x}}$/MW	50
${P}_{\mathrm{f}\mathrm{c}}^{\mathrm{m}\mathrm{i}\mathrm{n}}$/MW	5	${P}_{\mathrm{f}\mathrm{c}}^{\mathrm{m}\mathrm{a}\mathrm{x}}$/MW	40
${E}_{\mathrm{b}}^{\mathrm{m}\mathrm{i}\mathrm{n}}$/（MW·h）	30	${E}_{\mathrm{b}}^{\mathrm{m}\mathrm{a}\mathrm{x}}$/（MW·h）	120
${\eta }_{\mathrm{b}\mathrm{a}\mathrm{t}}^{\mathrm{c}\mathrm{h}}$	0.9	${\eta }_{\mathrm{b}\mathrm{a}\mathrm{t}}^{\mathrm{d}\mathrm{i}\mathrm{s}}$	0.9
${E}_{\mathrm{h}}^{\mathrm{m}\mathrm{i}\mathrm{n}}$/（MW·h）	10	${E}_{\mathrm{h}}^{\mathrm{m}\mathrm{a}\mathrm{x}}$/（MW·h）	80
${\eta }_{\mathrm{T}\mathrm{E}\mathrm{S}}^{\mathrm{c}\mathrm{h}}$	0.9	${\eta }_{\mathrm{T}\mathrm{E}\mathrm{S}}^{\mathrm{d}\mathrm{i}\mathrm{s}}$	0.9

模型	MAPE%	RMSE/kW	R²
LSTM	2.65	3.15	0.72
CNN-LSTM	1.48	2.05	0.88
改进CNN-LSTM	1.12	1.75	0.93

费用类别	夏季费用	冬季费用
维护费用	165.89	342.69
燃料费用	665.97	1 327.20
环境成本	27.07	69.11
市场成本	281.80	7.85
合计	1 140.74	1 746.84