• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.3
• /
• pp.153-162
• /
• 2016

This paper proposes an optimal dynamic resource allocation method in IoT (Internet of Things) parking guidance system using Q-learning resource allocation model. In the proposed method, a resource allocation using a forecasting model based on Q-learning is employed for optimal utilization of parking guidance system. To demonstrate efficiency and availability of the proposed method, it is verified by computer simulation and practical testbed. Through simulation results, this paper proves that the proposed method can enhance total throughput, decrease penalty fee issued by SLA (Service Level Agreement) and reduce response time with the dynamic number of users.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2017.11a
• /
• pp.191-192
• /
• 2017

In response to the economic depression, the demand for fixed rent income has increased according to the easing construction regulations. it caused indiscriminated investment to stakeholders. This leads to oversupply in the multi-family Housing market and increases unsold housing and vacancy rates except specific area such as Gangnam-gu.In order to solve this issue, although studies on the optimization price of apartment houses has been conducted, the study is insufficient regarding on residential officetel. Therefore, the objective is to suggest a basic study on optimal price estimation model development by using probabilistic forecasting method in planning phase. To achieve the objective, first, variables are defined such as expenses, financial costs, income, etc. Second, causal loop diagram is suggested. Third, basic optimization prices estimation model is developed. In the future, this study can be used as one of decision making tools in planning phase of officetel development projects.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.67 no.4
• /
• pp.183-190
• /
• 2018

Predicting accurate electricity prices is an important task in the electricity trading market. To address the electricity price forecasting problem, various approaches have been proposed so far and it is known that linear regression-based approaches are the best. However, the use of such linear regression-based methods is limited due to low accuracy and performance. In traditional linear regression methods, it is not practical to find a nonlinear regression model that explains the training data well. If the training data is complex (i.e., small-sized individual data and large-sized features), it is difficult to find the polynomial function with n terms as the model that fits to the training data. On the other hand, as a linear regression model approximating a nonlinear regression model is used, the accuracy of the model drops considerably because it does not accurately reflect the characteristics of the training data. To cope with this problem, we propose a new electricity price forecasting method that divides the entire dataset to multiple split datasets and find the best linear regression models, each of which is the optimal model in each dataset. Meanwhile, to improve the performance of the proposed method, we modify the proposed localized linear regression method in the map and reduce way that is a framework for parallel processing data stored in a Hadoop distributed file system. Our experimental results show that the proposed model outperforms the existing linear regression model. Specifically, the accuracy of the proposed method is improved by 45% and the performance is faster 5 times than the existing linear regression-based model.

• Proceedings of the KIEE Conference
• /
• 2000.11a
• /
• pp.92-94
• /
• 2000

This paper presents algorithm to plan construction and expanding of substation considering contingency accidents by proposing utilization factor according to configuration of substation bank system. In this paper, above all, proper sphere of supply area by each district which could be standardized with respect to its supply capacity is established under assumption of long term load forecasting which was made by district respectively, and then goal of utilization ratio based on configuration of substation bank was set to keep reliability by remaining sound bank when it happen to one bank accidents. Finally it is set up for optimal construction and expanding of substation considering economy and reliability simultaneously about substation to exceed these ratio.

• Journal of the Korean Data and Information Science Society
• /
• v.19 no.4
• /
• pp.1037-1046
• /
• 2008

Recently, the oil suppliers who supply the tax-exempt oil to the fishery are confronted with big trouble in their supply and demand system due to the unstable global oil prices. We applied the seasonal ARIMA(SARIMA) model to the low-sulfur and high-sulfur crude oil which are in great request and developed forecasting systems for them. Since there are many parameters in SARIMA, it is difficult to estimate the optimal parameters, but it is overcome by using simulation looping program. In conclusion, we found that the obvious seasonality in demand of low-sulfur and these demands are tending downwards gradually.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.835-837
• /
• 1996

In this paper, a method for the daily maximum load forecasting which uses a chaotic time series in power system and artificial neural network(Back-propagation) is proposed. We find the characteristics of chaos in power load curve and then determine a optimal embedding dimension and delay time. For the load forecast of one day ahead daily maximum power, we use the time series load data obtained in previous year. By using of embedding dimension and delay time, we construct a strange attractor in pseudo phase plane and the artificial neural network model trained with the attractor mentioned above. The one day ahead forecast errors are about 1.4% for absolute percentage average error.

• Proceedings of the KIEE Conference
• /
• 2003.11a
• /
• pp.438-440
• /
• 2003

This paper resents an application of an Artificial Neural Network(ANN) technique to forecast the short-term system marginal price(SMP). The forecasting of SMP is a very important factor in an electricity market for the optimal biddings of market participants as well as for the market stabilization of regulatory bodies. The proposed neural network scheme is composed of three layers. In this process, input data are set up to reflect market conditions. And the $\lambda$ that is the coefficient of activation function is modified in order to give a proper signal to each neuron and improve the adaptability for a neural network. The reposed techniques are trained validated and tested with the historical real-world data from korea Power Exchange(KPX).

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.50 no.7
• /
• pp.303-308
• /
• 2001

This paper presents algorithm to plan construction and expanding of substation considering contingency accidents by proposing utilization factor according to configuration of substation bank system. In this paper, firstly, proper sphere of supply area by each district which could be standardized with respect to its supply capacity is established under assumption of long term load forecasting. Secondly, goal of utilization ratio based on configuration of substation bank was set to keep reliability by remaining sound bank when it happen to one bank accidents. Finally, it is set up for optimal construction and expanding of substation considering economy and reliability simultaneously about substation to exceed these ratio. To verify proposed algorithm, at first, after adopting a part of Kangnam area in Seoul as area for testing, it is divided into several regions for this area according to power branches of power utility. Secondly, by deriving correlation factor between load demand and economic indicators in these region respectively, the regional load forecasting was performed with economic growth and city plan scenario. Finally, based on the predicted load demand by region and land use data which is identified from air-photographic, the load demand by district was predicted. Also, planning for substation considering contingency is formulated to expand taking into account computing utilization factor which is based on configuration of substation bank respectively.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.229-256
• /
• 2023

The increase in telecommuting and household electricity demand due to the pandemic has led to significant changes in electricity demand patterns. This has led to difficulties in identifying KEPCO's PPA (power purchase agreements) and residential solar power generation and has added to the challenges of electricity demand forecasting and grid operation for power exchanges. Unlike other energy resources, electricity is difficult to store, so it is essential to maintain a balance between energy production and consumption. A shortage or overproduction of electricity can cause significant instability in the energy system, so it is necessary to manage the supply and demand of electricity effectively. Especially in the Fourth Industrial Revolution, the importance of data has increased, and problems such as large-scale fires and power outages can have a severe impact. Therefore, in the field of electricity, it is crucial to accurately predict the amount of power generation, such as renewable energy, along with the exact demand for electricity, for proper power generation management, which helps to reduce unnecessary power production and efficiently utilize energy resources. In this study, we reviewed the renewable energy generation forecasting system, its objectives, and practical applications to construct optimal aggregated power resources using data from 169 power plants provided by the Ministry of Trade, Industry, and Energy, developed an aggregation algorithm considering the settlement of the forecasting system, and applied it to the analytical logic to synthesize and interpret the results. This study developed an optimal aggregation algorithm and derived an aggregation configuration (Result_Number 546) that reached 80.66% of the maximum settlement amount and identified plants that increase the settlement amount (B1783, B1729, N6002, S5044, B1782, N6006) and plants that decrease the settlement amount (S5034, S5023, S5031) when aggregating plants. This study is significant as the first study to develop an optimal aggregation algorithm using aggregated power resources as a research unit, and we expect that the results of this study can be used to improve the stability of the power system and efficiently utilize energy resources.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.34 no.6
• /
• pp.220-229
• /
• 1985

This paper proposes a new optimal unit commitment algorithm for the rational operation of electric power systems. Especially, the algorithm is improved by considering transmission line capacity limits and load forecasting uncertainty with the consideration of the participation factors of each units, so that the method becomes more reliable and flexible one. The transmission losses are considered by using updated penalty factors obtained from the constant matrixes of the fast decoupled load flow method, the system loads are distributed at each buses, and the several necessary operational constraints are also considered for the purpose of presenting a more practicable scheme. Finally, the effectiveness of the proposed algorithm has been demonstrated by applying to the 23-bus model system.