1. The release data includes the original data of wind turbine X30 at 2018 and 2019, which are files “2019_x30.csv” and “2018_x30.csv” in directory “Original data”. For the turbine, the wind speed and direction are collected at each 30 seconds, then there are 2880 data at a day. In the experiment, we use the slide window with 120 data, which corresponding to an hours, and slide the window with 10 data step, which corresponding to 5 minutes. For the data in window, we select the data of final 10 minutes as the label.
The evaluations are modified with the feed back mechanism based on optimal model in Large Scale Group Decision Making (LSGDM) usually, the intelligent decision making cannot be achieved with end-to-end. The application of LSGDM is limited, such as the customer evaluation to sales factors, the most customers would not modify the provided evaluations. A novel method combining Conditional Variational Auto-Encoder (CVAE) and self attention mechanism is developed to conduct the intelligent decision making with end-to-end.
There are 3 data files in total for this data set, 1 for Experiment 1 and 2 for Experiment 2. The File Experiment 1.csv contains 12 matrices for Experiment 1, which are the opinions of the decision makers with the pairwise comparison of alternatives in the form of the linguistic preference relations. The File Experiment 2-1.csv contains 51 matrices, which denote the opinions of the decision makers with the pairwise comparison of alternatives in the form of the Linguistic Discrete Region.