针对广域分布式新能源普遍缺乏新能源资源监测装置,而导致功率预测精度不足的问题,提出一种基于气象资源插值与迁移学习的广域分布式光伏功率预测方法。首先,基于地理信息和粗颗粒气象数据,对广域范围下的气象资源数据进行网格化插值;其...针对广域分布式新能源普遍缺乏新能源资源监测装置,而导致功率预测精度不足的问题,提出一种基于气象资源插值与迁移学习的广域分布式光伏功率预测方法。首先,基于地理信息和粗颗粒气象数据,对广域范围下的气象资源数据进行网格化插值;其次,依据插值结果对具有相同气象特征的光伏电站进行自组织映射(self-organizing maps,SOM)网络聚类,并对每一类中的光伏电站进行迁移学习的源域和目标域的划分,以保证预测精度;然后,结合长短期记忆(long short term memory,LSTM)网络,引入误差修正环节,建立源域至目标域的双迁移模型;最后,以浙江省绍兴市的分布式光伏电站为实例验证该方法的有效性。相比于对各个光伏电站单独建模,所提方法能将目标域光伏电站的训练速度提高10倍以上,且在预测精度方面也有显著提升,具有一定的推广应用价值。展开更多
Varieties of approaches and algorithms have been presented to identify the distribution of elements. Previous researches based on the type of problem, categorized their data in proper clusters or classes. This means t...Varieties of approaches and algorithms have been presented to identify the distribution of elements. Previous researches based on the type of problem, categorized their data in proper clusters or classes. This means that the process of solution could be supervised or unsupervised. In cases, where there is no idea about dependency of samples to specific groups, clustering methods (unsupervised) are applied. About geochemistry data, since various elements are involved, in addition to the complex nature of geochemical data, clustering algorithms would be useful for recognition of elements distribution. In this paper, Self-Organizing Map (SOM) algorithm, as an unsupervised method, is applied for clustering samples based on REEs contents. For this reason the Choghart Fe-REE deposit (Bafq district, central Iran), was selected as study area and dataset was a collection of 112 lithology samples that were assayed with laboratory tests such as ICP-MS and XRF analysis. In this study, input vectors include 19 features which are coordinates x, y, z and concentrations of REEs as well as the concentration of Phosphate (P<sub>2</sub>O<sub>5</sub>) since the apatite is the main source of REEs in this particular research. Four clusters were determined as an optimal number of clusters using silhouette criterion as well as k-means clustering method and SOM. Therefore, using self-organizing map, study area was subdivided in four zones. These four zones can be described as phosphate type, albitofyre type, metasomatic and phosphorus iron ore, and Iron Ore type. Phosphate type is the most prone to rare earth elements. Eventually, results were validated with laboratory analysis.展开更多
The convergence analysis of MaxMin-SOMO algorithm is presented. The SOM-based optimization (SOMO) is an optimization algorithm based on the self-organizing map (SOM) in order to find a winner in the network. Generally...The convergence analysis of MaxMin-SOMO algorithm is presented. The SOM-based optimization (SOMO) is an optimization algorithm based on the self-organizing map (SOM) in order to find a winner in the network. Generally, through a competitive learning process, the SOMO algorithm searches for the minimum of an objective function. The MaxMin-SOMO algorithm is the generalization of SOMO with two winners for simultaneously finding two winning neurons i.e., first winner stands for minimum and second one for maximum of the objective function. In this paper, the convergence analysis of the MaxMin-SOMO is presented. More specifically, we prove that the distance between neurons decreases at each iteration and finally converge to zero. The work is verified with the experimental results.展开更多
An improved clustering method based on artificial immune is proposed. To obtain the better initial solution, the initial antibody network is introduced by self organizing map （SOM） method. In the process of the clus...An improved clustering method based on artificial immune is proposed. To obtain the better initial solution, the initial antibody network is introduced by self organizing map （SOM） method. In the process of the clustering iteration, a series of optimization and evolution strategies are designed, such as clustering satisfaction, the threshold design of scale compression, the learning rate, the clustering monitoring points and the clustering evaluations indexes. These strategies can make the clustering thresholds be quantified and reduce the operator’s subjective factors. Thus, the local optimal and the global optimal clustering simultaneously are proposed by the synthesized function of these strategies. Finally, the experiment and the comparisons demonstrate the proposed method effectiveness.展开更多
文摘针对广域分布式新能源普遍缺乏新能源资源监测装置,而导致功率预测精度不足的问题,提出一种基于气象资源插值与迁移学习的广域分布式光伏功率预测方法。首先,基于地理信息和粗颗粒气象数据,对广域范围下的气象资源数据进行网格化插值;其次,依据插值结果对具有相同气象特征的光伏电站进行自组织映射(self-organizing maps,SOM)网络聚类,并对每一类中的光伏电站进行迁移学习的源域和目标域的划分,以保证预测精度;然后,结合长短期记忆(long short term memory,LSTM)网络,引入误差修正环节,建立源域至目标域的双迁移模型;最后,以浙江省绍兴市的分布式光伏电站为实例验证该方法的有效性。相比于对各个光伏电站单独建模,所提方法能将目标域光伏电站的训练速度提高10倍以上,且在预测精度方面也有显著提升,具有一定的推广应用价值。
文摘Varieties of approaches and algorithms have been presented to identify the distribution of elements. Previous researches based on the type of problem, categorized their data in proper clusters or classes. This means that the process of solution could be supervised or unsupervised. In cases, where there is no idea about dependency of samples to specific groups, clustering methods (unsupervised) are applied. About geochemistry data, since various elements are involved, in addition to the complex nature of geochemical data, clustering algorithms would be useful for recognition of elements distribution. In this paper, Self-Organizing Map (SOM) algorithm, as an unsupervised method, is applied for clustering samples based on REEs contents. For this reason the Choghart Fe-REE deposit (Bafq district, central Iran), was selected as study area and dataset was a collection of 112 lithology samples that were assayed with laboratory tests such as ICP-MS and XRF analysis. In this study, input vectors include 19 features which are coordinates x, y, z and concentrations of REEs as well as the concentration of Phosphate (P<sub>2</sub>O<sub>5</sub>) since the apatite is the main source of REEs in this particular research. Four clusters were determined as an optimal number of clusters using silhouette criterion as well as k-means clustering method and SOM. Therefore, using self-organizing map, study area was subdivided in four zones. These four zones can be described as phosphate type, albitofyre type, metasomatic and phosphorus iron ore, and Iron Ore type. Phosphate type is the most prone to rare earth elements. Eventually, results were validated with laboratory analysis.
基金supported by National Natural Science Foundation of China(Nos.11171367 and 61502068)the Fundamental Research Funds for the Central Universities of China(No.3132014094)+1 种基金the China Postdoctoral Science Foundation(Nos.2013M541213 and 2015T80239)Fundacao da Amaro a Pesquisa do Estado de Sao Paulo(FAPESP)Brazil(No.2012/23329-5)
文摘The convergence analysis of MaxMin-SOMO algorithm is presented. The SOM-based optimization (SOMO) is an optimization algorithm based on the self-organizing map (SOM) in order to find a winner in the network. Generally, through a competitive learning process, the SOMO algorithm searches for the minimum of an objective function. The MaxMin-SOMO algorithm is the generalization of SOMO with two winners for simultaneously finding two winning neurons i.e., first winner stands for minimum and second one for maximum of the objective function. In this paper, the convergence analysis of the MaxMin-SOMO is presented. More specifically, we prove that the distance between neurons decreases at each iteration and finally converge to zero. The work is verified with the experimental results.
基金supported by the Program for New Century Excellent Talents in University (NCET-06-0236)
文摘An improved clustering method based on artificial immune is proposed. To obtain the better initial solution, the initial antibody network is introduced by self organizing map （SOM） method. In the process of the clustering iteration, a series of optimization and evolution strategies are designed, such as clustering satisfaction, the threshold design of scale compression, the learning rate, the clustering monitoring points and the clustering evaluations indexes. These strategies can make the clustering thresholds be quantified and reduce the operator’s subjective factors. Thus, the local optimal and the global optimal clustering simultaneously are proposed by the synthesized function of these strategies. Finally, the experiment and the comparisons demonstrate the proposed method effectiveness.
