为提高光伏发电系统短期出力预测的精度,提出了一种和声搜索(Harmony Search,HS)算法与回声状态网络(Echo State Network,ESN)算法相结合的预测模型。该模型以光伏电站的历史发电量数据和气象数据为基础。首先通过相似日选择算法挑选出...为提高光伏发电系统短期出力预测的精度,提出了一种和声搜索(Harmony Search,HS)算法与回声状态网络(Echo State Network,ESN)算法相结合的预测模型。该模型以光伏电站的历史发电量数据和气象数据为基础。首先通过相似日选择算法挑选出预测日的相似日,将相似日的气象特征向量和预测日的气象特征向量的差值作为预测模型的输入变量;然后选择训练样本,并用和声搜索算法优化后的回声状态网络模型(HS-ESN)对样本进行训练和预测;最后以甘肃某光伏电站为例进行实例验证。实证分析表明,利用和声搜索算法优化回声状态网络预测模型的储备池参数可有效提高回声状态网络的预测精度,因此该模型具有较好的实用价值。展开更多
Riverbed modeled rockfill material from Noa Dehing dam project, Arunachal Pradesh, India and blasted quarried modeled rockfill material from Kol dam project, Himachal Pradesh, India were considered for this research. ...Riverbed modeled rockfill material from Noa Dehing dam project, Arunachal Pradesh, India and blasted quarried modeled rockfill material from Kol dam project, Himachal Pradesh, India were considered for this research. Riverbed rockfill material is rounded to sub-rounded and quarried rockfill material is angular to sub-angular in shape. Prototype rockfill materials were modeled into maximum particle size （dmax） of 4.75 mm, 10 mm, 19 mm, 25 mm, 5O mm and 80 mm for testing in the laboratory. Consolidated drained triaxial tests were conducted on modeled rockfill materials with a specimen size of 381 mm in diameter and 813 mm in height to study the stress-strain-volume change behavior for both rockfill materials. Index properties, i.e. uncompacted void content （UVC） and uniaxial compressive strength （UCS）, were determined for both rockfill materials in association with material parameters. An elasto- plastic hardening soil （HS） constitutive model was used to predict the behavior of modeled rockfill materials. Comparing the predicted and observed stress-strain-volume change behavior, it is found that both observed and predicted behaviors match closely. The procedures were developed to predict the shear strength and elastic parameters of rockfill materials using the index properties, i.e. UCS, UVC and relative density （RD）, and predictions were made satisfactorily. Comparing the predicted and experi- mentally determined shear strengths and elastic parameters, it is observed that both values match closely. Then these procedures were used to predict the elastic and shear strength parameters of large- size prototype rockfill materials. Correlations were also developed between index properties and ma- terial strength parameters （dilatancy angle, ~, and initial void ratio, einit, required for HS model） of modeled rockfill materials and the same correlations were used to predict the strength parameters for the prototype rockfill materials. Using the predicted material parameters, the stress-strain-volume change behavior of prototype rockfill material was predicted using elastoplastic HS constitutive model. The advantage of the proposed methods is that only index properties, i.e. UCS, UVC, RD, modulus of elasticity of intact rock, Eir, and Poisson＇s ratio of intact rock, Vir, are required to determine the angle of shearing resistance, Ф, modulus of elasticity, E50^ref and Poisson＇s ratio, , of rockfill materials, and there is E50＆ref no need of triaxial testing. It is believed that the proposed methods are more realistic, economical, and can be used where large-size triaxial testing facilities are not available.展开更多
文摘为提高光伏发电系统短期出力预测的精度,提出了一种和声搜索(Harmony Search,HS)算法与回声状态网络(Echo State Network,ESN)算法相结合的预测模型。该模型以光伏电站的历史发电量数据和气象数据为基础。首先通过相似日选择算法挑选出预测日的相似日,将相似日的气象特征向量和预测日的气象特征向量的差值作为预测模型的输入变量;然后选择训练样本,并用和声搜索算法优化后的回声状态网络模型(HS-ESN)对样本进行训练和预测;最后以甘肃某光伏电站为例进行实例验证。实证分析表明,利用和声搜索算法优化回声状态网络预测模型的储备池参数可有效提高回声状态网络的预测精度,因此该模型具有较好的实用价值。
文摘Riverbed modeled rockfill material from Noa Dehing dam project, Arunachal Pradesh, India and blasted quarried modeled rockfill material from Kol dam project, Himachal Pradesh, India were considered for this research. Riverbed rockfill material is rounded to sub-rounded and quarried rockfill material is angular to sub-angular in shape. Prototype rockfill materials were modeled into maximum particle size （dmax） of 4.75 mm, 10 mm, 19 mm, 25 mm, 5O mm and 80 mm for testing in the laboratory. Consolidated drained triaxial tests were conducted on modeled rockfill materials with a specimen size of 381 mm in diameter and 813 mm in height to study the stress-strain-volume change behavior for both rockfill materials. Index properties, i.e. uncompacted void content （UVC） and uniaxial compressive strength （UCS）, were determined for both rockfill materials in association with material parameters. An elasto- plastic hardening soil （HS） constitutive model was used to predict the behavior of modeled rockfill materials. Comparing the predicted and observed stress-strain-volume change behavior, it is found that both observed and predicted behaviors match closely. The procedures were developed to predict the shear strength and elastic parameters of rockfill materials using the index properties, i.e. UCS, UVC and relative density （RD）, and predictions were made satisfactorily. Comparing the predicted and experi- mentally determined shear strengths and elastic parameters, it is observed that both values match closely. Then these procedures were used to predict the elastic and shear strength parameters of large- size prototype rockfill materials. Correlations were also developed between index properties and ma- terial strength parameters （dilatancy angle, ~, and initial void ratio, einit, required for HS model） of modeled rockfill materials and the same correlations were used to predict the strength parameters for the prototype rockfill materials. Using the predicted material parameters, the stress-strain-volume change behavior of prototype rockfill material was predicted using elastoplastic HS constitutive model. The advantage of the proposed methods is that only index properties, i.e. UCS, UVC, RD, modulus of elasticity of intact rock, Eir, and Poisson＇s ratio of intact rock, Vir, are required to determine the angle of shearing resistance, Ф, modulus of elasticity, E50^ref and Poisson＇s ratio, , of rockfill materials, and there is E50＆ref no need of triaxial testing. It is believed that the proposed methods are more realistic, economical, and can be used where large-size triaxial testing facilities are not available.
