Browsing by Author "Chen, Linnan"

Now showing 1 - 2 of 2

Concept Drift Detection and Adaption in Big Imbalance Industrial IoT Data Using an Ensemble Learning Method of Offline Classifiers
(2019-01-01)
Lin, Chun-Cheng
;
Deng, Der-Jiunn
;
Kuo, Chin-Hung
;
Chen, Linnan
;
工業工程與管理學系
In a smart factory, thousands of industrial Internet of Things (IIoT) devices or sensors are installed in production machines to collect big data on machine conditions and transmit it to a cyber-physical system in the cloud center of the factory. Then, the system employs a variety of condition-based maintenance (CBM) methods to predict the time point when machines start to be operated abnormally and to maintain them or replace their components in advance so as to avoid manufacturing enormous detective products. CBM suffers from problems of concept drifts (i.e., the distribution of fault patterns may change over time) and imbalance data (i.e., the data with faults accounts for a minority of all data). Ensemble learning that integrates the diversity of multiple classifiers provides a high-performance solution to address these problems. In practice, most companies may not have a sufficient budget to establish a sound infrastructure to support real-time online classifiers, but may have off-the-shelf offline classifiers in their existing systems. However, most previous works on ensemble learning only focused on supporting online classifiers. Consequently, this work proposes an ensemble learning algorithm that supports offline classifiers to cope with three-stage CBM with concept drifts and imbalance data, in which Stages 1 (training an ensemble classifier) and 3 (creating a new ensemble) employ an improved Dynamic AdaBoost.NC classifier and the SMO method to address imbalance data; and Stage 2 (detecting concept drifts in imbalance data) employs an improved LFR (Linear Four Rates) method. The experimental results on datasets with different degrees of imbalance show that the proposed method can successfully detect all concept drifts, and has a high accuracy rate in detecting minority-class data, which is over 94%.
Peak Load Shifting in the Internet of Energy With Energy Trading Among End-Users
(2017-01-01)
Lin, Chun-Cheng
;
Deng, Der-Jiunn
;
Liu, Wan-Yu
;
Chen, Linnan
;
工業工程與管理學系
Recent advances in renewable energy generation and the Internet of things (IoT) has urged energy management to enter the era of the Internet of energy (IoE). The IoE adopts a huge number of distributed energy -generating facilities, distributed energy storage facilities, and IoT technologies to implement energy sharing, promote utilization of electrical grids, and maintain safety of electrical grids. Rapid economic and social development makes energy shortage tend to be increasingly serious. Most cases of energy shortage occur during the peak energy load, and hence the previous works focused on shifting peak load to address energy shortage. However, few of these works took the IoE framework into account. Consequently, this work aims to consider the IoE framework to investigate the peak load shifting problem in which end-users in the energy market can adopt their respective energy storage facilities to charge and discharge energy to minimize the total operating costs. In such a problem setting, each end-user can not only be a demander, but also be a supplier in the energy market, so that operating costs are concerned; the energies from both conventional electrical grids and distributed renewable energy sources can be stored in energy storage facilities; real-time price of energy will be applied adequately to affect energy distribution of supply and demand. Simulation results of a case study show that the proposed model can obtain the optimal result and achieve peak load shifting.