Browsing by Author "Liang, Yu-Lin"

Now showing 1 - 2 of 2

A Hybrid Memetic Algorithm for Simultaneously Selecting Features and Instances in Big Industrial IoT Data for Predictive Maintenance
(2019-01-01)
Liang, Yu-Lin
;
Kuo, Chih-Chi
;
Lin, Chun-Cheng
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
In Industry 4.0, various types of IoT sensors which are installed on machines to collect data for predictive maintenance. As the collected data increases, there are more missing values and noisy data. Related studies have already proposed various methods to solve the problems in big data. Among them, most studies focused on either feature selection or instance selection for data preprocessing before training forecast models. Metaheuristic algorithm is one of the mainstream methods in data preprocessing. However, most of these studies rarely considered feature and instance selection simultaneously. In addition, they seldom focused on noisy data. Therefore, this work combines the UCI datasets with noisy data to simulate the real situation. Memetic algorithm (MA) has excellent performance in machine learning of data selection, and variable neighborhood search (VNS) was also proved to be widely applied to the systematic change of local search algorithms. This work proposes a hybrid MA and VNS to find a new subset that maximizes the accuracy of the classifier while preserving the minimum amount of data by feature and instance selection simultaneously. Experimental results show that the proposed method can efficiently reduce the amount of data and the ratio of noisy data. By comparison with other metaheuristic algorithms, the proposed method has good performance by an excellent balance between exploration and exploitation.
Optimal Charging Control of Energy Storage and Electric Vehicle of an Individual in the Internet of Energy With Energy Trading
(2018-06-01)
Lin, Chun-Cheng
;
Deng, Der-Jiunn
;
Kuo, Chih-Chi
;
Liang, Yu-Lin
;
工業工程與管理學系
Developing green energy to be applied in green cities has received much attention. The Internet of energy (IoE) effectively improves networking of distributed green energies through extending smart grids with bidirectional transmission of energy and distributed renewable energy facilities. Previous works on the IoE focused on decisions of IoE operators or optimization of the whole system. However, few considered optimal decisions of a single end user in the IoE. Therefore, this work creates a mixed-integer linear programming (MILP) model for a single end user that considers green energy generation, an energy storage, an electric vehicle, and an IoE-based energy trading platform to reduce energy waste. This model considers a complete system of charging control of multiple facilities of a single end user in the IoE, and allows the end user to purchase energy and sell green energy through the IoE, in which the energy prices of the electrical grid and the IoE platform are set by the power company and the energy market, respectively. Because MILP is NP complete and the proposed model involves a large number of variables and constraints, this paper further proposes a genetic algorithm for this problem, in which a repairing scheme is proposed to handle solution infeasibility of all constraints. By simulation, the proposed algorithm is verified to effectively reduce energy waste.