青海高原光伏适宜性评价的不同决策树算法的比较研究

张玉冰; 申彦波; 姚鑫; 周雅文; 俞文政

doi:10.19912/j.0254-0096.tynxb.2023-2078

PDF(2659 KB)

太阳能学报 ›› 2024, Vol. 45 ›› Issue (12) : 30-39. DOI: 10.19912/j.0254-0096.tynxb.2023-2078

青海高原光伏适宜性评价的不同决策树算法的比较研究

张玉冰¹, 申彦波^2,3, 姚鑫¹, 周雅文¹, 俞文政¹

作者信息 +

COMPARATIVE STUDY OF DIFFERENT DECISION TREE ALGORITHMS FOR PV SUITABILITY EVALUATION IN QINGHAI PLATEAU

Zhang Yubing¹, Shen Yanbo^2,3, Yao Xin¹, Zhou Yawen¹, Yu Wenzheng¹

Author information +

文章历史 +

摘要

以青海高原为例,通过野外调查和整合谷歌图像的方式,收集185个光伏站点位置信息。在此基础上,对比分类与回归树（CART）、随机森林（RF）和极端梯度提升（XGBoost）这3种机器学习算法,采用受试者工作特征（ROC）曲线和统计指标对模型质量进行检验。结果表明：XGBoost具有较高的预测性能,对噪声数据具有较强的适应性,总体表现优于其他模型。太阳总辐射、与电网的距离和与道路的距离是影响光伏电站选址的主要影响因子。3个模型生成的光伏适宜性图显示,非常适宜区域主要分布在柴达木盆地和共和盆地,非常适宜和较适宜区占研究区总面积的15.31%和16.33%。

Abstract

Taking the Qinghai Plateau as an example,a total of 185 photovoltaic sites positional information are collected through field investigation and integration of Google Images. Based on this dataset,three machine learning algorithms,namely Classification and Regression Tree （CART）,Random Forest （RF）,and Extreme Gradient Boosting （XGBoost）,are compared and evaluated for their predictive performance is assesed using ROC curves and statistical indicators. The results reveal that XGBoost demonstrates superior predictive performance and robust adaptability to noisy data, overall outperforms the other models. Factors such as total solar radiation,distance from the power grid, and distance to roads are identified as the key factors influencing the location of photovoltaic power stations. The PV suitability maps generated by the three models indicate that the highly suitable areas are primarily distributed in the Qaidam Basin and Gonghe Basin. The highly suitable and relatively suitable areas account for 15. 31% and 16. 33% of the total area of the study area, respectively.

导出引用

张玉冰, 申彦波, 姚鑫, 周雅文, 俞文政. 青海高原光伏适宜性评价的不同决策树算法的比较研究[J]. 太阳能学报. 2024, 45(12): 30-39 https://doi.org/10.19912/j.0254-0096.tynxb.2023-2078

Zhang Yubing, Shen Yanbo, Yao Xin, Zhou Yawen, Yu Wenzheng. COMPARATIVE STUDY OF DIFFERENT DECISION TREE ALGORITHMS FOR PV SUITABILITY EVALUATION IN QINGHAI PLATEAU[J]. Acta Energiae Solaris Sinica. 2024, 45(12): 30-39 https://doi.org/10.19912/j.0254-0096.tynxb.2023-2078

中图分类号： TK519

参考文献

[1] SUN Y W, ZHU D F, LI Y, et al.Spatial modelling the location choice of large-scale solar photovoltaic power plants: application of interpretable machine learning techniques and the national inventory[J]. Energy conversion and management, 2023, 289: 117198.
[2] 刘立程, 孙中孝, 吴锋, 等. 京津冀地区光伏开发空间适宜性及减排效益评估[J]. 地理学报, 2022, 77(3): 665-678.
LIU L C, SUN Z X, WU F, et al.Evaluation of suitability and emission reduction benefits of photovoltaic development in Beijing-Tianjin-Hebei region[J]. Acta geographica sinica, 2022, 77(3): 665-678.
[3] CHANG R, YAN Y P, WU J, et al.Projected PV plants in China's gobi deserts would result in lower evaporation and wind[J]. Solar energy, 2023, 256: 140-150.
[4] HOU W J, LI X J, YANG L S, et al.Carrying capacity of water resources for renewable energy development in arid regions in Northwest China: a case study of Golmud, Qinghai[J]. Frontiers in environmental science, 2022, 10: 892414.
[5] 田政卿, 张勇, 刘向, 等. 光伏电站建设对陆地生态环境的影响: 研究进展与展望[J]. 环境科学, 2024, 45(1): 239-247.
TIAN Z Q, ZHANG Y, LIU X, et al.Effects of photovoltaic power station construction on terrestrial environment: retrospect and prospect[J]. Environmental science, 2024, 45(1): 239-247.
[6] QIU L H, HE L, LU H W, et al.Systematic potential analysis on renewable energy centralized co-development at high altitude: a case study in Qinghai-Tibet Plateau[J]. Energy conversion and management, 2022, 267: 115879.
[7] GIAMALAKI M, TSOUTSOS T.Sustainable siting of solar power installations in Mediterranean using a GIS/AHP approach[J]. Renewable energy, 2019, 141: 64-75.
[8] SUH J, BROWNSON J.Solar farm suitability using geographic information system fuzzy sets and analytic hierarchy processes: case study of ulleung island, Korea[J]. Energies, 2016, 9(8): 648.
[9] 张乾, 辛晓洲, 张海龙, 等. 基于遥感数据和多因子评价的中国地区建设光伏电站的适宜性分析[J]. 地球信息科学学报, 2018, 20(1): 119-127.
ZHANG Q, XIN X Z, ZHANG H L, et al.Suitability analysis of photovoltaic power plants in China using remote sensing data and multicriteria evaluation[J]. Journal of geo-information science, 2018, 20(1): 119-127.
[10] YANG Q, HUANG T Y, WANG S G, et al.A GIS-based high spatial resolution assessment of large-scale PV generation potential in China[J]. Applied energy, 2019, 247: 254-269.
[11] LIU J C, XU F Q, LIN S S.Site selection of photovoltaic power plants in a value chain based on grey cumulative prospect theory for sustainability: a case study in Northwest China[J]. Journal of cleaner production, 2017, 148: 386-397.
[12] XIAO J H, YAO Z Y, QU J J, et al.Research on an optimal site selection model for desert photovoltaic power plants based on analytic hierarchy process and geographic information system[J]. Journal of renewable and sustainable energy, 2013, 5(2): 023132.
[13] ARABAMERI A, SAHA S, ROY J, et al.Landslide susceptibility evaluation and management using different machine learning methods in the gallicash river watershed, Iran[J]. Remote sensing, 2020, 12(3): 475.
[14] WIMHURST J J, GREENE J S, KOCH J.Predicting commercial wind farm site suitability in the conterminous United States using a logistic regression model[J]. Applied energy, 2023, 352: 121880.
[15] RIOS R, DUARTE S.Selection of ideal sites for the development of large-scale solar photovoltaic projects through analytical hierarchical process-geographic information systems (AHP-GIS) in Peru[J]. Renewable and sustainable energy reviews, 2021, 149: 111310.
[16] 苏淑兰, 姬海娟, 张东, 等. 青海草地生态系统水分利用效率特征及其影响因素分析[J]. 草地学报, 2023, 31(9): 2814-2825.
SU S L, JI H J, ZHANG D, et al.Characteristics of water use efficiency and its influencing factors of grassland ecosystem in Qinghai Province[J]. Acta agrestia sinica, 2023, 31(9): 2814-2825.
[17] 杜志勇, 丛楠. 植被与土壤特征对青藏高原不同程度退化草地的响应[J]. 生态学报, 2024, 44(6): 2504-2516.
DU Z Y, CONG N.Responses of vegetation and soil characterisitics to degraded grassland under different degrees on the Qinghai-Tibet Plateau[J]. Acta ecologica sinica, 2024, 44(6): 2504-2516.
[18] QIU L H, HE L, LU H W, et al.Spatial-temporal evolution of pumped hydro energy storage potential on the Qinghai-Tibet Plateau and its future trend under global warming[J]. Science of the total environment, 2023, 857: 159332.
[19] TANG W J, QI J W, WANG Y, et al.Dense station-based potential assessment for solar photovoltaic generation in China[J]. Journal of cleaner production, 2023, 414: 137607.
[20] HUANG T Y, WANG S G, YANG Q, et al.A GIS-based assessment of large-scale PV potential in China[J]. Energy procedia, 2018, 152: 1079-1084.
[21] COLAK H E, MEMISOGLU T, GERCEK Y.Optimal site selection for solar photovoltaic (PV) power plants using GIS and AHP: a case study of Malatya Province, Turkey[J]. Renewable energy, 2020, 149: 565-576.
[22] ELBOSHY B, ALWETAISHI M, ALY R M H, et al. A suitability mapping for the PV solar farms in Egypt based on GIS-AHP to optimize multi-criteria feasibility[J]. Ain shams engineering journal, 2022, 13(3): 101618.
[23] SUN L J, JIANG Y C, GUO Q S, et al.A GIS-based multi-criteria decision making method for the potential assessment and suitable sites selection of PV and CSP plants[J]. Resources, conservation and recycling, 2021, 168: 105306.
[24] 王海金, 唐若笠, 周雨诗, 等. 基于ArcGIS与多因子模型的光伏电站选址评估[J]. 太阳能学报, 2023, 44(11): 120-130.
WANG H J, TANG R L, ZHOU Y S, et al.Location evaluation of photovoltaic power stations based on ArcGIS and multi-criteria model[J]. Acta energiae solaris sinica, 2023, 44(11): 120-130.
[25] YE L C, RODRIGUES J F D, LIN H X. Analysis of feed-in tariff policies for solar photovoltaic in China 2011-2016[J]. Applied energy, 2017, 203: 496-505.
[26] ZHANG A H, SIRIN S M, FAN C L, et al.An analysis of the factors driving utility-scale solar PV investments in China: how effective was the feed-in tariff policy?[J]. Energy policy, 2022, 167: 113044.
[27] CHE X J, ZHOU P, WANG M.The policy effect on photovoltaic technology innovation with regional heterogeneity in China[J]. Energy economics, 2022, 115: 106385.
[28] SHRIKI N, RABINOVICI R, YAHAV K, et al.Prioritizing suitable locations for national-scale solar PV installations: Israel's site suitability analysis as a case study[J]. Renewable energy, 2023, 205: 105-124.
[29] CHARABI Y, GASTLI A.PV site suitability analysis using GIS-based spatial fuzzy multi-criteria evaluation[J]. Renewable energy, 2011, 36(9): 2554-2561.
[30] GUPTA V, SHARMA M, PACHAURI R K, et al.Comprehensive review on effect of dust on solar photovoltaic system and mitigation techniques[J]. Solar energy, 2019, 191: 596-622.
[31] 袁红, 易桂花, 张廷斌, 等. 基于遥感数据川西高原光伏开发适宜性研究[J]. 自然资源遥感, 2023, 35(4): 301-311.
YUAN H, YI G H, ZHANG T B, et al.Suitability of photovoltaic development in the Western Sichuan Plateau based on remote sensing data[J]. Remote sensing for natural resources, 2023, 35(4): 301-311.
[32] 孟丹, 陈正洪, 严国刚, 等. 光伏电站气象灾害风险评估研究: 以湖北省为例[J]. 太阳能学报, 2020, 41(5): 359-364.
MENG D, CHEN Z H, YAN G G, et al.Study on risk assessment of meteorological disaster in photovoltaic power stations: a case study of Hubei Province[J]. Acta energiae solaris sinica, 2020, 41(5): 359-364.
[33] LEE D S, LEE T G, BAE Y S, et al.Occurrence prediction of western conifer seed bug (leptoglossus occidentalis: Coreidae) and evaluation of the effects of climate change on its distribution in South Korea using machine learning methods[J]. Forests, 2023, 14(1): 117.
[34] 曹炯玮, 魏加华, 李想, 等. 青海省太阳能-风能发电潜力评估及时空格局[J]. 太阳能学报, 2023, 44(10): 255-265.
CAO J W, WEI J H, LI X, et al.Potential assesssment and spatio-temporal pattern of solar-wind power in Qinghai province[J]. Acta energiae solaris sinica, 2023, 44(10): 255-265.
[35] LI X Y, DONG X Y, CHEN S, et al.The promising future of developing large-scale PV solar farms in China: a three-stage framework for site selection[J]. Renewable energy, 2024, 220: 119638.
[36] Global Solar Atlas.World - Photovoltaic Power Potential (PVOUT) GIS Data[EB/OL]. https://globalsolaratlas.info/map.
[37] 冯婉玲, 何立恒, 杨强. 基于CART决策树分类的江苏省湿地提取[J]. 水生态学杂志, 2022, 43(3): 35-43.
FENG W L, HE L H, YANG Q.Extraction of remotely sensed wetland information for Jiangsu Province based on CART decision tree classification[J]. Journal of hydroecology, 2022, 43(3): 35-43.
[38] MA M H, ZHAO G, HE B S, et al.XGBoost-based method for flash flood risk assessment[J]. Journal of hydrology, 2021, 598: 126382.
[39] 管家琳, 黄炎和, 林金石, 等. 基于信息量模型与随机森林模型的崩岗风险对比评估[J]. 山地学报, 2021, 39(4): 539-551.
GUAN J L, HUANG Y H, LIN J S, et al.Comparisons between Benggang risk assessments based on information model and random forest model[J]. Mountain research, 2021, 39(4): 539-551.
[40] 范天程, 汪珍亮, 李云飞, 等. 基于机器学习的沟谷地貌识别模型对比: 以黄土高原典型流域为例[J]. 水土保持学报, 2023, 37(4): 205-213.
FAN T C, WANG Z L, LI Y F, et al.Comparing the performance of machine learning models for identifying gully landforms—a case study of a typical watershed on the Chinese Loess Plateau[J]. Journal of soil and water conservation, 2023, 37(4): 205-213.
[41] QIU T Z, WANG L C, LU Y B, et al.Potential assessment of photovoltaic power generation in China[J]. Renewable and sustainable energy reviews, 2022, 154: 111900.
[42] ROGAN J, FRANKLIN J, STOW D, et al.Mapping land-cover modifications over large areas: a comparison of machine learning algorithms[J]. Remote sensing of environment, 2008, 112(5): 2272-2283.
[43] HUANG F M, TENG Z K, GUO Z Z, et al.Uncertainties of landslide susceptibility prediction: influences of different spatial resolutions, machine learning models and proportions of training and testing dataset[J]. Rock mechanics bulletin, 2023, 2(1): 100028.
[44] YIN X Z, FALLAH-SHORSHANI M, MCCONNELL R, et al.Predicting fine spatial scale traffic noise using mobile measurements and machine learning[J]. Environmental science & technology, 2020, 54(20): 12860-12869.
[45] HOU Y L, WANG Q W, TAN T.Regional suitability assessment for straw-based power generation: a machine learning approach[J]. Energy strategy reviews, 2023, 49: 101173.
[46] HOU Y L, WANG Q W, ZHOU K, et al.Integrated machine learning methods with oversampling technique for regional suitability prediction of waste-to-energy incineration projects[J]. Waste management, 2024, 174: 251-262.
[47] TAO X M, LI Q, REN C, et al.Real-value negative selection over-sampling for imbalanced data set learning[J]. Expert systems with applications, 2019, 129: 118-134.
[48] HASTI F, MAMKHEZRI J, MCFERRIN R, et al.Optimal solar photovoltaic site selection using geographic information system-based modeling techniques and assessing environmental and economic impacts: the case of Kurdistan[J]. Solar energy, 2023, 262: 111807.
[49] YU S W, HAN R L, ZHANG J J.Reassessment of the potential for centralized and distributed photovoltaic power generation in China: on a prefecture-level city scale[J]. Energy, 2023, 262: 125436.
[50] DOLJAK D, STANOJEVIĆ G.Evaluation of natural conditions for site selection of ground-mounted photovoltaic power plants in Serbia[J]. Energy, 2017, 127: 291-300.
[51] ALMASAD A, PAVLAK G, ALQUTHAMI T, et al.Site suitability analysis for implementing solar PV power plants using GIS and fuzzy MCDM based approach[J]. Solar energy, 2023, 249: 642-650.
[52] YANG Z, GAO S M.On selecting the locations of 60MW grid-connected photovoltaic power plant[C]//2010 Symposium on Photonics and Optoelectronics. Chengdu, China, 2010: 1-4.
[53] VRÎNCEANU A, GRIGORESCU I, DUMITRAȘCU M, et al. Impacts of photovoltaic farms on the environment in the Romanian Plain[J]. Energies, 2019, 12(13): 2533.
[54] WATSON J J W, HUDSON M D. Regional Scale wind farm and solar farm suitability assessment using GIS-assisted multi-criteria evaluation[J]. Landscape and urban planning, 2015, 138: 20-31.