Search

Photovoltaic (PV) power prediction is an effective way to ensure the safe operation of the grid connected photovoltaic power station, and the prediction accuracy is very important as well as difficult. In order to improve the prediction accuracy, a combination prediction model based on entropy weight and traditional prediction methods is demonstrated. The combination prediction model used entropy weight to combine three traditional prediction methods which are persistence method, support vector machine (SVM) and prediction method based on similar data. And the entropy weight of each single prediction method is got by evaluating the amount of information of each method objectively. The prediction accuracy of entropy weight combination prediction model and these three single prediction methods are compared by simulation. Case study results show that the combination model based on entropy weight can get proper combination weights for these traditional methods. As a result, the prediction accuracy of entropy weight combination prediction model is much higher than that of single traditional prediction method for all weather types.

Even though recent hybrid methods have helped to avoid certain limitations of Content-based (CB) filtering and collaborative filtering (CF), scalability and sparsity are still major problems in large-scale recommendation systems. This paper presents a novel collaborative recommendation method based on ontology for personalized TV program application. In the proposed method, we give a new formula to calculate user ratings explicitly according to four TV-watching related behaviors' preferences. More specifically, in order to overcome sparsity problems of CF, we build the TV programs ontology to take semantic relationship to estimate contents' concept similarity. Experiments show that Ontology can explicitly reveal the similarity of programs. In our WEB-TV prototype system, Ontology-based collaborative recommendation method illustrate the ability improving the precision and recall in a large degree.