• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.4
• /
• pp.87-92
• /
• 2019

This paper describes the pattern analysis for data of the factory energy consumption by using machine learning method. While usual statistical methods or approaches require specific equations to represent the physical characteristics of the plant, machine learning based approach uses historical data and calculate the result effectively. Although rule-based approach calculates energy usage with the physical equations, it is hard to identify the exact equations that represent the factory's characteristics and hidden variables affecting the results. Whereas the machine learning approach is relatively useful to find the relations quickly between the data. The factory has several components directly affecting to the electricity consumption which are machines, light, computers and indoor systems like HVAC (heating, ventilation and air conditioning). The energy loads from those components are generated in real-time and these data can be shown in time-series. The various sensors were installed in the factory to construct the database by collecting the energy usage data from the components. After preliminary statistical analysis for data mining, time-series clustering techniques are applied to extract the energy load pattern. This research can attributes to develop Factory Energy Management System (FEMS).

• Spatial Information Research
• /
• v.19 no.1
• /
• pp.61-72
• /
• 2011

Greenhouses gas emission due to usage of fossil fuel has been known as one of the main causes of global warming. Fundamentally, greenhouse gas is a by-product of economic activity. Since majority of economic activity happens in an urban setting, a countermeasure in an urban setting is needed. Therefore, an analysis of relationship between carbon dioxide emission and urban form will be investigated for urban planning and management in the future. The purpose of this study is to analyze the relationship between carbon dioxide emission and urban spatial patterns, and suggesting an urban form with low carbon dioxide emission. In order to achieve this, first theoretical analysis was carried out on urban spatial patterns related to physical size, usage rate, and activity level. Secondly, Seoul's dam on electricity, natural gas, local heating, petroleum, and water usage and mapping a carbon dioxide emission map. Thirdly, relationship between carbon dioxide emission and urban spatial patterns are analyzed and urban spatial patterns that affects energy usage in urban setting was elucidated, and elicited implications on future directions on urban planning based on our analyses above.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.23 no.12
• /
• pp.176-183
• /
• 2009

Distributed generation(DG) of combined cooling, heat, and power(CCHP)has been gaining momentum in recent year as efficient, secure alternative for meeting increasing energy demands. This paper presents the energy performance of microturbine CCHP system equipped with an absorption chiller by modelling it in hospital building. The orders of study were as following. 1)The list and schedule of energy consumption equipment in hospital were examined such as heating and cooling machine, light etc. 2) Annual report of energy usage and monitoring data were examined as heating, cooling, DHW, lighting, etc. 3) The weather data in 2007 was used for simulation and was arranged by meteorological office data in Daejeon. 4) Reference simulation model was built by comparison of real energy consumption and simulation result by TRNSYS and ESP-r. The energy consumption pattern of building were analyzed by simulation model and energy reduction rate were calculated over the cogeneration. As a result of this study, power generation efficiency of turbine was about 30[%] after installing micro gas turbine and lighting energy as well as total electricity consumption can be reduced by 40[%]. If electricity energy and waste heat in turbine are used, 56[%] of heating energy and 67[%] of cooling energy can be reduced respectively, and total system efficiency can be increased up to 70[%].

• Proceedings of the SAREK Conference
• /
• 2009.06a
• /
• pp.1185-1190
• /
• 2009

Korea is an industrial country that overspends energy and has a policy that is more focused on a supply side. When an urban developmental program is to set up, surveys are carried out only with the respect to electricity, telecommunication, gas, and heating sources. Based on the existing survey results, the problems related to the supply side are being dealt with more importantly and the quantities of those supplies are estimated only by each energy source. The aim of this study is to provide basic information on energy consumption patterns of a diverse comsumer groups including industry, transportation, commerce, public and household to plan diverse energy policies. Through this basic information, it may be possible to analyze the energy consumption pattern by each consumer group and provide data for setting up efficient energy policies by the government. The energy consumption map that are analyzed and developed by the data obtained from Busan municipal area will be deposited and used as a part of the national energy statistics.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.39 no.5
• /
• pp.637-645
• /
• 2019

Global warming and a new energy policy request the energy saving and pollutant emission control in municipal level. Previous studies focus on transportation in the Seoul metropolitan area which can easily meet the policy goal by reducing it. This study expands the area of urban energy planning to the industries and land use which takes up most of energy use of the city. We empirically study the Busan metropolitan area's 5 years natural gas and electricity consumption data by the industries and land use. Results show that energy usage significantly depends on not only population but also urbanizing intensity and industrial category. This paper address that the policy maker need to pay attention on energy usage pattern of each sectors during the planning.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.120-126
• /
• 2019

Recently, accurate prediction of power consumption based on machine learning techniques in Internet of Energy (IoE) has been actively studied using the large amount of electricity data acquired from advanced metering infrastructure (AMI). In this paper, we propose a deep learning model based on Gated Recurrent Unit (GRU) as an artificial intelligence (AI) network that can effectively perform pattern recognition of time series data such as the power consumption, and analyze performance of the prediction based on real household power usage data. In the performance analysis, performance comparison between the proposed GRU-based learning model and the conventional learning model of Long Short Term Memory (LSTM) is described. In the simulation results, mean squared error (MSE), mean absolute error (MAE), forecast skill score, normalized root mean square error (RMSE), and normalized mean bias error (NMBE) are used as performance evaluation indexes, and we confirm that the performance of the prediction of the proposed GRU-based learning model is greatly improved.

• Journal of Bio-Environment Control
• /
• v.31 no.4
• /
• pp.366-375
• /
• 2022

The monitoring of electricity consumption using Internet of Things (IoT) technology is attracting attention as a technology to reduce operation costs of smart farms. In this study, we propose a method to apply a real-time electrical consumption monitoring system (the e-Gauge system) and utilization of the collected data real-time while a melon-producing smart farm is in operation. For this purpose, the electrical consumption data for the individual smart-farm facilities such as boilers, nutrient distribution systems, automatic controllers, circulation fans, boiler controllers, and other IoT-related utilities were collected during three months of melon cultivation period. By using the monitoring results, the electrical energy consumption pattern was analyzed as an example, and necessary considerations needed to optimally utilize the measurement data were suggested. This paper will be useful in lowering the technological implementation barriers for new researchers to build a electrical consumption monitoring system and reducing trial and errors in the usage of the generated data.