为准确预测太阳能热发电站并网发电量,提出一种改进后的麻雀搜索算法与长短期记忆网络相结合的模型（ISSA-LSTM模型）。首先,基于传统LSTM模型引入麻雀搜索算法构建SSA-LSTM预测模型,以突破局部最优陷阱,提升全局搜索能力。其次,运用精英反向学习策略生成反向解并获取精英个体动态边界,对SSA-LSTM预测模型进行改进,进一步提升算法全局搜索能力与搜索精度。最后,运用太阳能热发电站真实数据对所构建模型与其他模型进行训练分析,并对比各模型预测结果。经过多次训练后结果显示：ISSA-LSTM模型预测结果精度显著高于其他模型,对比SSA-LSTM模型预测精度提升14%;同时该模型训练结果基本与实际数值相吻合。该文基于ISSA-LSTM模型,对光热发电站并网发电量进行预测,为全面提高发电量预测精度、合理布局太阳能热发电站提供一定理论借鉴。
Abstract
To accurately forecast the grid connected power generation of solar thermal power stations, an improved sparrow search algorithm combined with long short-term memory networks （ISSA-LSTM model） is proposed. Firstly, based on the traditional LSTM model, the sparrow search algorithm is introduced to construct the SSA-LSTM forecast model, in order to break through the local optimal trap and enhance the global search capability. Secondly, using the elite opposition-based learning strategy to generate reverse solutions and obtain dynamic boundaries of elite individuals, the SSA-LSTM forecast model is improved to further enhance the algorithm's global search capability and search accuracy. Finally, the constructed model is trained and analyzed using real data from the solar thermal power station, and the forecast results of each model are compared with those of other models. After multiple training sessions, the results show that the ISSA-LSTM model has significantly higher forecast accuracy than other models, with a 14% improvement in forecast accuracy compared to the SSA-LSTM model. At the same time, the training results of the model are basically consistent with the actual values. Based on the ISSA-LSTM model, this article predicts the grid connected power generation of solar thermal power plants, providing a theoretical reference for comprehensively improving the accuracy of power generation pre and rational layout of solar thermal power stations.
关键词
太阳能热发电站 /
发电量预测 /
学习算法 /
麻雀搜索算法 /
神经网络
Key words
solar thermal power stations /
power generation forecast /
learning algorithms /
sparrow search algorithm /
neural network
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] ZHANG M J, ANABA O A, MA Z Q, et al.En route to attaining a clean sustainable ecosystem: a nexus between solar energy technology, economic expansion and carbon emissions in China[J]. Environmental science and pollution research, 2020, 27(15): 18602-18614.
[2] 方宇晨, 杜尔顺, 余扬昊, 等. 太阳能光热发电并网的综合效益量化评估方法[J]. 中国电机工程学报, 2024, 44(13): 5135-5146.
FANG Y C, DU E S, YU Y H, et al.Quantitative evaluation method of comprehensive benefits of solar photothermal power generation connected to grid[J]. Proceedings of the CSEE, 2024, 44(13): 5135-5146.
[3] 杜尔顺, 张宁, 康重庆, 等. 太阳能光热发电并网运行及优化规划研究综述与展望[J]. 中国电机工程学报, 2016, 36(21): 5765-5775, 6019.
DU E S, ZHANG N, KANG C Q, et al.Reviews and prospects of the operation and planning optimization for grid integrated concentrating solar power[J]. Proceedings of the CSEE, 2016, 36(21): 5765-5775, 6019.
[4] 曾光, 纪阳, 符津铭, 等. 热储能技术研究现状、热点趋势与应用进展[J]. 中国电机工程学报, 2023, 43(S1): 127-142.
ZENG G, JI Y, FU J M, et al.Research status, hot trends and application progress of thermal energy storage technology[J]. Proceedings of the CSEE, 2023, 43(S1): 127-142.
[5] ZJAVKA L.Photovoltaic power one-day and multistep-hourly AI predictions using node-by-node evolved binomial tree structures to form L-transformed PDE modules[J]. Soft computing, 2025, 29(5): 2483-2495.
[6] 余洋, 陈庚, 余佳磊, 等. 基于聚类和长短期记忆神经网络的光热电站并网电力预测[J]. 热力发电, 2021, 50(9): 128-136.
YU Y, CHEN G, YU J L, et al.Grid-connected power forecasting of concentrating solar power plants based on clustering and long short-term memory neural network[J]. Thermal power generation, 2021, 50(9): 128-136.
[7] 刘振路, 郭军红, 李薇, 等. 基于FCM-LSTM的光热发电出力短期预测[J]. 工程科学学报, 2024, 46(1): 178-186.
LIU Z L, GUO J H, LI W, et al.Short-term prediction of concentrating solar power based on FCM-LSTM[J]. Chinese journal of engineering, 2024, 46(1): 178-186.
[8] 路小娟, 董海鹰. 太阳能热发电集热系统终端受限非线性模型预测控制[J]. 热力发电, 2015, 44(10): 63-67.
LU X J, DONG H Y.Predictive control of nonlinear model for heat collecting system with terminal limit in solar thermal power generation system[J]. Thermal power generation, 2015, 44(10): 63-67.
[9] 彭曙蓉, 陈慧霞, 孙万通, 等. 基于改进LSTM的光伏发电功率预测方法研究[J]. 太阳能学报, 2024, 45(11): 296-302.
PENG S R, CHEN H X, SUN W T, et al.Research on photovoitaic power prediction method based on improved LSTM[J]. Acta energiae solaris sinica, 2024, 45(11): 296-302.
[10] 王东风, 刘婧, 黄宇, 等. 结合太阳辐射量计算与CNN-LSTM组合的光伏功率预测方法研究[J]. 太阳能学报, 2024, 45(2): 443-450.
WANG D F, LIU J, HUANG Y, et al.Photovoltaic power prediction method combinating solar radiation calculation and CNN-LSTM[J]. Acta energiae solaris sinica, 2024, 45(2): 443-450.
[11] 杨轶航, 韩璐, 史华勃, 等. 基于相似日与ISC-BiLSTM的短期光伏功率预测方法[J]. 太阳能学报, 2025, 46(1): 676-685.
YANG Y H, HAN L, SHI H B, et al.Short-term photovoltaic power forecast method based on similar days and ISC-BiLSTM[J]. Acta energiae solaris sinica, 2025, 46(1): 676-685.
[12] 王晓霞, 俞敏, 冀明, 等. 基于气候相似性与SSA-CNN-LSTM的光伏功率组合预测[J]. 太阳能学报, 2023, 44(6): 275-283.
WANG X X, YU M, JI M, et al.Photovoltaic power combination forecasting based on climate similarity and SSA-CNN-LSTM[J]. Acta energiae solaris sinica, 2023, 44(6): 275-283.
[13] 薛建凯. 一种新型的群智能优化技术的研究与应用[D]. 上海: 东华大学, 2020.
XUE J K, Research and application of a novel swarm intelligence optimization technique[D]. Shanghai: Donghua University, 2020.
[14] 陈立万, 赵尚飞, 曾蝶, 等. 基于混合策略麻雀搜索算法的WSN覆盖优化[J]. 电子测量技术, 2022, 45(23): 174-180.
CHEN L W, ZHAO S F, ZENG D, et al.WSN coverage optimization based on hybrid strategy sparrow search algorithm[J]. Electronic measurement technology, 2022, 45(23): 174-180.
[15] 王瑞, 闫方, 逯静, 等. 运用相似日和LSTM的短期负荷双向组合预测[J]. 电力系统及其自动化学报, 2022, 34(1): 93-99.
WANG R, YAN F, LU J, et al.Bidirectional combined short-term load forecasting by using similar days and LSTM[J]. Proceedings of the CSU-EPSA, 2022, 34(1): 93-99.
[16] 姚玉璧, 郑绍忠, 杨扬, 等. 中国太阳能资源评估及其利用效率研究进展与展望[J]. 太阳能学报, 2022, 43(10): 524-535.
YAO Y B, ZHENG S Z, YANG Y, et al.Progress and prospects on solar energy resource evaluation and utilization efficiency in China[J]. Acta energiae solaris sinica, 2022, 43(10): 524-535.
[17] 纪文波, 徐建新, 王华, 等. 基于三态测试的生物柴油喷射火焰混沌识别及燃烧性能研究[J]. 太阳能学报, 2021, 42(11): 403-409.
JI W B, XU J X, WANG H, et al.Chaos identification and combustion performance of biodiesel injection flame based on three state test[J]. Acta energiae solaris sinica, 2021, 42(11): 403-409.
[18] 李青. 基于注意力时间卷积神经网络的光伏功率概率预测[J]. 太阳能学报, 2025, 46(2): 326-332.
LI Q.Photovoltaic power probability prediction based on attention time convolutional neural network[J]. Acta giae solaris sinica, 2025, 46(2): 326-332.
[19] 蒲晓云, 杨靖, 杨兴, 等. 基于分解技术的IZOA-Transformer-BiGRU短期风电功率预测[J]. 电子测量技术, 2025, 48(2): 39-48.
PU X Y, YANG J, YANG X, et al.IZOA-Transformer-BiGRU short-term wind power prediction based on decomposition technique[J]. Electronic measurement technology, 2025, 48(2): 39-48.
基金
内蒙古自然科学基金（2023LHMS05043）; 国家自然科学基金项目（51965052）; 内蒙古自治区直属高校基本科研业务费项目; 包头职业技术学院科研创新团队建设项目（TD202206）
PDF(1077 KB)
