• KEPCO Journal on Electric Power and Energy
• /
• v.5 no.1
• /
• pp.25-32
• /
• 2019

K-BEMS System was introduced to reduce peak load and to save total energy of the 200 buildings that KEPCO headquarter and branch offices use. And K-BEMS system is composed of PV, battery, and hybrid PCS. KEPCO research institute has carried out this K-BEMS research project for 3 years since January 2016. In this paper, the results of the project are shown. 9 modes of test results of K-BEMS system and are operational problems were analyzed. And measures to cure the trouble are also suggested. Batteries are operated more than 20% of SOC, and less than 20% of SOC battery protection switches are automatically shutting down the system and the system no longer respond to EMS, ending the supply of PV, and so therefore to continue the PV power supply it was turn out to be necessary that the EMS should automatically change its policy to change PV only supply mode automatically when the Battery Switch automatically operated. To operate the system continuously and automatically, it is necessary to modify the minimum operational SOC value, and in addition to that the EMS computer must remember the last shut-down SOC and Voltage which interrupted the system and add some margin to reflect the measurement error in the system.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.454-464
• /
• 2023

This paper proposes a low-power 8-bit asynchronous SAR ADC with a sampling rate of 1 MS/s for sensor node applications. The ADC uses bootstrapped switches to improve linearity and applies a VCM-based CDAC switching technique to reduce the power consumption and area of the DAC. Conventional synchronous SAR ADCs that operate in synchronization with an external clock suffer from high power consumption due to the use of a clock faster than the sampling rate, which can be overcome by using an asynchronous SAR ADC structure that handles internal comparisons in an asynchronous manner. In addition, the SAR logic is designed using dynamic logic circuits to reduce the large digital power consumption that occurs in low resolution ADC designs. The proposed ADC was simulated in a 180-nm CMOS process, and at a 1.8 V supply voltage and a sampling rate of 1 MS/s, it consumed 46.06 𝜇W of power, achieved an SNDR of 49.76 dB and an ENOB of 7.9738 bits, and obtained a FoM of 183.2 fJ/conv-step. The simulated DNL and INL are +0.186/-0.157 LSB and +0.111/-0.169 LSB.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.253-266
• /
• 2018

This paper proposes a methodology applying sequence tagging methodology to improve the performance of NER(Named Entity Recognition) used in QA system. In order to retrieve the correct answers stored in the database, it is necessary to switch the user's query into a language of the database such as SQL(Structured Query Language). Then, the computer can recognize the language of the user. This is the process of identifying the class or data name contained in the database. The method of retrieving the words contained in the query in the existing database and recognizing the object does not identify the homophone and the word phrases because it does not consider the context of the user's query. If there are multiple search results, all of them are returned as a result, so there can be many interpretations on the query and the time complexity for the calculation becomes large. To overcome these, this study aims to solve this problem by reflecting the contextual meaning of the query using Bidirectional LSTM-CRF. Also we tried to solve the disadvantages of the neural network model which can't identify the untrained words by using ontology knowledge based feature. Experiments were conducted on the ontology knowledge base of music domain and the performance was evaluated. In order to accurately evaluate the performance of the L-Bidirectional LSTM-CRF proposed in this study, we experimented with converting the words included in the learned query into untrained words in order to test whether the words were included in the database but correctly identified the untrained words. As a result, it was possible to recognize objects considering the context and can recognize the untrained words without re-training the L-Bidirectional LSTM-CRF mode, and it is confirmed that the performance of the object recognition as a whole is improved.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.1-25
• /
• 2020

In this paper, we suggest an application system architecture which provides accurate, fast and efficient automatic gasometer reading function. The system captures gasometer image using mobile device camera, transmits the image to a cloud server on top of private LTE network, and analyzes the image to extract character information of device ID and gas usage amount by selective optical character recognition based on deep learning technology. In general, there are many types of character in an image and optical character recognition technology extracts all character information in an image. But some applications need to ignore non-of-interest types of character and only have to focus on some specific types of characters. For an example of the application, automatic gasometer reading system only need to extract device ID and gas usage amount character information from gasometer images to send bill to users. Non-of-interest character strings, such as device type, manufacturer, manufacturing date, specification and etc., are not valuable information to the application. Thus, the application have to analyze point of interest region and specific types of characters to extract valuable information only. We adopted CNN (Convolutional Neural Network) based object detection and CRNN (Convolutional Recurrent Neural Network) technology for selective optical character recognition which only analyze point of interest region for selective character information extraction. We build up 3 neural networks for the application system. The first is a convolutional neural network which detects point of interest region of gas usage amount and device ID information character strings, the second is another convolutional neural network which transforms spatial information of point of interest region to spatial sequential feature vectors, and the third is bi-directional long short term memory network which converts spatial sequential information to character strings using time-series analysis mapping from feature vectors to character strings. In this research, point of interest character strings are device ID and gas usage amount. Device ID consists of 12 arabic character strings and gas usage amount consists of 4 ~ 5 arabic character strings. All system components are implemented in Amazon Web Service Cloud with Intel Zeon E5-2686 v4 CPU and NVidia TESLA V100 GPU. The system architecture adopts master-lave processing structure for efficient and fast parallel processing coping with about 700,000 requests per day. Mobile device captures gasometer image and transmits to master process in AWS cloud. Master process runs on Intel Zeon CPU and pushes reading request from mobile device to an input queue with FIFO (First In First Out) structure. Slave process consists of 3 types of deep neural networks which conduct character recognition process and runs on NVidia GPU module. Slave process is always polling the input queue to get recognition request. If there are some requests from master process in the input queue, slave process converts the image in the input queue to device ID character string, gas usage amount character string and position information of the strings, returns the information to output queue, and switch to idle mode to poll the input queue. Master process gets final information form the output queue and delivers the information to the mobile device. We used total 27,120 gasometer images for training, validation and testing of 3 types of deep neural network. 22,985 images were used for training and validation, 4,135 images were used for testing. We randomly splitted 22,985 images with 8:2 ratio for training and validation respectively for each training epoch. 4,135 test image were categorized into 5 types (Normal, noise, reflex, scale and slant). Normal data is clean image data, noise means image with noise signal, relfex means image with light reflection in gasometer region, scale means images with small object size due to long-distance capturing and slant means images which is not horizontally flat. Final character string recognition accuracies for device ID and gas usage amount of normal data are 0.960 and 0.864 respectively.