A short-term power prediction method for photovoltaic cluster based on transformation of multi-source spatiotemporal feature is proposed to overcome the problem of insufficient mining spatiotemporal feature by traditi...
详细信息
A short-term power prediction method for photovoltaic cluster based on transformation of multi-source spatiotemporal feature is proposed to overcome the problem of insufficient mining spatiotemporal feature by traditional short-term power prediction methods for photovoltaic cluster. Firstly, the random forest algorithm is used to analyze the importance of every feature of numerical weather prediction, and a topology graph is generated based on the geographical coordinates of the photovoltaic power station to guide the most important feature of numerical weather prediction to divide the photovoltaic cluster into several sub-clusters by improving deep attention embedded graphclustering. Then, the photovoltaic power and numerical weather prediction are decomposed by Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise, and the decomposed components are reconstructed based on permutation entropy. Finally, the short-term power prediction result for photovoltaic cluster is obtained by time transformation network. Through simulation verification, the experimental results show that the root mean square error and the mean absolute error of the proposed method, respectively, reduces 0.0165 and 0.0170 in average, and the accuracy rate improves 1.63% compared with the other method. It can make greater contributions to large-scale photovoltaic grid connection and regional power supply.
In this paper, we present a novel graph Wavelet Convolutional Network (GWCN) approach with a graph clustering algorithm such as METIS. GWCN is a graph wavelet transform-based method. It has better locality than graph ...
详细信息
ISBN:
(数字)9781665485593
ISBN:
(纸本)9781665485593
In this paper, we present a novel graph Wavelet Convolutional Network (GWCN) approach with a graph clustering algorithm such as METIS. GWCN is a graph wavelet transform-based method. It has better locality than graph Convolutional Network (GCN) using the graph Fourier transform, and results higher classification accuracy. In this work, the graph clustering algorithm is applied to GWCN for providing a mechanism to the mini-batch selection in deep learning, which has an effective impact on learning.
Clearly visualized networks provide a great help in understanding complex systems, which require designing efficient layout algorithm to draw the network diagrams. Compared with force-directed algorithm, the algorithm...
详细信息
Clearly visualized networks provide a great help in understanding complex systems, which require designing efficient layout algorithm to draw the network diagrams. Compared with force-directed algorithm, the algorithms of grid-optimization series have the advantage of avoiding node overlap through positioning nodes on square grid points of twodimensional. However, for networks of several thousand nodes, the computation costs of extant grid layouts are too high to meet the visualization requirements. In order to improve computation performance, this article proposes a new grid point matching based algorithm named grid-based layout (GBL) with three procedures to draw complex networks. Firstly, graph clustering algorithm is applied to divide network into several modules constituted of closely connected nodes, then all modules are placed on separated two-dimensional space as global layout, and finally, the grid layout algorithm is applied to position the child nodes within these modules as local optimization. With GBL help, users can gain insights of global topological structure of network as well as detailed connectivity within these modules. In particular, an improved weight strategy is designed to speed up optimization process. Compared with latest available grid layout algorithm, GBL shows relatively better performances in computing time, edge-edge crossings, node-edge crossings, relative edge lengths and connectivity F-measures.
This article starts with the comparison of an algorithm for identifying various protein complexes interacting on the networks, has analyzed the shortages of the existing particle swarm optimization(PSO) and improved t...
详细信息
This article starts with the comparison of an algorithm for identifying various protein complexes interacting on the networks, has analyzed the shortages of the existing particle swarm optimization(PSO) and improved them so as to propose a modified PSO. From the comparison of the experimental results, it can be seen that the modified PSO mentioned in this paper can increase the identifying precision, which provides a novel idea for studying the algorithm of the protein complexes identification.
Protein complexes are essential entities that perform the major cellular processes and biological functions in live organisms. The identification of component proteins in a complex from protein-protein interaction (PP...
详细信息
ISBN:
(纸本)9780769545745
Protein complexes are essential entities that perform the major cellular processes and biological functions in live organisms. The identification of component proteins in a complex from protein-protein interaction (PPI) networks is an important step to understand the organization and interaction of gene products. In existing literature, methods for identifying protein complexes typically start from a selected seed, commonly a vertex (a single protein), in a PPI network. However, in many circumstances, a single protein seed is not enough to generate a meaningful complex, or more than one protein is known in a complex. In this paper, we present an improved seed-growth style algorithm to identify protein complexes from PPI networks based on the concept of graph entropy. Different from existing methods, the seed is assumed to be a clique (e.g., a vertex, an edge, a triangle) in a PPI network. The computational experiments have been conducted on PPI network of S. cerevisiae. The results have shown that the larger cliques are considered as seeds, the better the presented method performs in terms of f-score. In particular, up to K-3-cliques are included as seeds, the average f-score is 57.32%, which is better than that of existing methods.
暂无评论