• 전력전자학회논문지
• /
• 제26권3호
• /
• pp.183-191
• /
• 2021

A battery management system (BMS) provides some functions for ensuring safety and reliability that includes algorithms estimating battery states. Given the changes caused by various operating conditions, the state-of-health (SOH), which represents a figure of merit of the battery's ability to store and deliver energy, becomes challenging to estimate. Machine learning methods can be applied to perform accurate SOH estimation. In this study, we propose a Long-Term Recurrent Convolutional Network (LRCN) that combines the Convolutional Neural Network (CNN) and Long Short-term Memory (LSTM) to extract aging characteristics and learn temporal mechanisms. The dataset collected by the battery aging experiments of NASA PCoE is used to train models. The input dataset used part of the charging profile. The accuracy of the proposed model is compared with the CNN and LSTM models using the k-fold cross-validation technique. The proposed model achieves a low RMSE of 2.21%, which shows higher accuracy than others in SOH estimation.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.271-274
• /
• 2005

Under competitive power markets, various long-term and short-term contracts based on spot price are used by producers and consumers. So an accurate forecasting for spot price allow market participants to develop bidding strategies in order to maximize their benefit. Artificial Neural Network is a powerful method in forecasting problem. In this paper we used Radial Basis Function(RBF) network to forecast spot price. To learn ANN, in addition to price history, we used some other effective inputs such as load level, fuel price, generation and transmission facilities situation. Results indicate that this forecasting method is accurate and useful.

• Journal of Electrical Engineering and Technology
• /
• 제10권4호
• /
• pp.1480-1491
• /
• 2015

In new deregulated electricity market, short-term price forecasting is key information for all market players. A better forecast of market-clearing price (MCP) helps market participants to strategically set up their bidding strategies for energy markets in the short-term. This paper presents a new prediction strategy to improve the need for more accurate short-term price forecasting tool at spot market using an artificial neural networks (ANNs). To build the forecasting ANN model, a three-layered feedforward neural network trained by the improved Levenberg-marquardt (LM) algorithm is used to forecast the locational marginal prices (LMPs). To accurately predict LMPs, actual power generation and load are considered as the input sets, and then the difference is used to predict price differences in the spot market. The proposed ANN model generalizes the relationship between the LMP in each area and the unconstrained MCP during the same period of time. The LMP calculation is iterated so that the capacity between the areas is maximized and the mechanism itself helps to relieve grid congestion. The addition of flow between the areas gives the LMPs a new equilibrium point, which is balanced when taking the transfer capacity into account, LMP forecasting is then possible. The proposed forecasting strategy is tested on the spot market of the Nord Pool. The validity, the efficiency, and effectiveness of the proposed approach are shown by comparing with time-series models

• Journal of Positioning, Navigation, and Timing
• /
• 제8권4호
• /
• pp.209-214
• /
• 2019

Precise point positioning (PPP) requires precise orbit and clock products. International GNSS service (IGS) real-time service (RTS) data can be used in real-time for PPP, but it may not be possible to receive these corrections for a short time due to internet or hardware failure. In addition, the time required for IGS to combine RTS data from each analysis center results in a delay of about 30 seconds for the RTS data. Short-term orbit prediction can be possible because it includes the rate of correction, but the clock correction only provides bias. Thus, a short-term prediction model is needed to preidict RTS clock corrections. In this paper, we used a long short-term memory (LSTM) network to predict RTS clock correction for three minutes. The prediction accuracy of the LSTM was compared with that of the polynomial model. After applying the predicted clock corrections to the broadcast ephemeris, we performed PPP and analyzed the positioning accuracy. The LSTM network predicted the clock correction within 2 cm error, and the PPP accuracy is almost the same as received RTS data.

• 품질경영학회지
• /
• 제47권3호
• /
• pp.497-508
• /
• 2019

Purpose: The purpose of this study is to overcome limitations of conventional studies that to predict Baltic Dry Index (BDI). The study proposed applications of Artificial Neural Network (ANN) named Long Short-Term Memory (LSTM) to predict BDI. Methods: The BDI time-series prediction was carried out through eight variables related to the dry bulk market. The prediction was conducted in two steps. First, identifying the goodness of fitness for the BDI time-series of specific ANN models and determining the network structures to be used in the next step. While using ANN's generalization capability, the structures determined in the previous steps were used in the empirical prediction step, and the sliding-window method was applied to make a daily (one-day ahead) prediction. Results: At the empirical prediction step, it was possible to predict variable y(BDI time series) at point of time t by 8 variables (related to the dry bulk market) of x at point of time (t-1). LSTM, known to be good at learning over a long period of time, showed the best performance with higher predictive accuracy compared to Multi-Layer Perceptron (MLP) and Recurrent Neural Network (RNN). Conclusion: Applying this study to real business would require long-term predictions by applying more detailed forecasting techniques. I hope that the research can provide a point of reference in the dry bulk market, and furthermore in the decision-making and investment in the future of the shipping business as a whole.

• Nuclear Engineering and Technology
• /
• 제53권8호
• /
• pp.2534-2546
• /
• 2021

Nuclear emergency preparedness and response is an essential part to ensure the safety of nuclear power plant (NPP). Key support technologies of nuclear emergency decision-making usually consist of accident diagnosis, source term estimation, accident consequence assessment, and protective action recommendation. Source term estimation is almost the most difficult part among them. For example, bad communication, incomplete information, as well as complicated accident scenario make it hard to determine the reactor status and estimate the source term timely in the Fukushima accident. Subsequently, it leads to the hard decision on how to take appropriate emergency response actions. Hence, this paper aims to develop a method for rapid source term estimation to support nuclear emergency decision making in pressurized water reactor NPP. The method aims to make our knowledge on NPP provide better support nuclear emergency. Firstly, this paper studies how to build a Bayesian network model for the NPP based on professional knowledge and engineering knowledge. This paper presents a method transforming the PRA model (event trees and fault trees) into a corresponding Bayesian network model. To solve the problem that some physical phenomena which are modeled as pivotal events in level 2 PRA, cannot find sensors associated directly with their occurrence, a weighted assignment approach based on expert assessment is proposed in this paper. Secondly, the monitoring data of NPP are provided to the Bayesian network model, the real-time status of pivotal events and initiating events can be determined based on the junction tree algorithm. Thirdly, since PRA knowledge can link the accident sequences to the possible release categories, the proposed method is capable to find the most likely release category for the candidate accidents scenarios, namely the source term. The probabilities of possible accident sequences and the source term are calculated. Finally, the prototype software is checked against several sets of accident scenario data which are generated by the simulator of AP1000-NPP, including large loss of coolant accident, loss of main feedwater, main steam line break, and steam generator tube rupture. The results show that the proposed method for rapid source term estimation under nuclear emergency decision making is promising.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4246-4267
• /
• 2020

As the network goes deep into all aspects of people's lives, the number and the complexity of network traffic is increasing, and traffic classification becomes more and more important. How to classify them effectively is an important prerequisite for network management and planning, and ensuring network security. With the continuous development of deep learning, more and more traffic classification begins to use it as the main method, which achieves better results than traditional classification methods. In this paper, we provide a comprehensive review of network traffic classification based on deep learning. Firstly, we introduce the research background and progress of network traffic classification. Then, we summarize and compare traffic classification based on deep learning such as stack autoencoder, one-dimensional convolution neural network, two-dimensional convolution neural network, three-dimensional convolution neural network, long short-term memory network and Deep Belief Networks. In addition, we compare traffic classification based on deep learning with other methods such as based on port number, deep packets detection and machine learning. Finally, the future research directions of network traffic classification based on deep learning are prospected.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.1037-1040
• /
• 2000

We introduce the forecasting method for a next day electric peak load that uses the optimal combination of two types of neural networks. First network uses learning data that are past 10days of the target day. We name the neural network Short Term Neural Network (STNN). Second network uses those of last year. We name the neural network Long Term Neural Network (LTNN). Then we get the forecasting results that are the linear combination of the forecasting results by STNN and the forecasting results by LTNN. We name the method Combination Forecasting Method (CFM). Then we discuss the optimal combination of STNN and LTNN. Using CFM of the optimal combination of STNN and LTNN, we can reduce the forecasting error.

• 경영과학
• /
• 제28권3호
• /
• pp.1-13
• /
• 2011

Hub-and-spoke transportation network is a powerful and useful network structure that takes full advantage of economies of scale on routes between hubs. In recent studies, the network structure is extended to hybrid hub-andspoke that allows direct transportation between spokes. In this study, we considered more extended network structure which is called hybrid multiple hub-and-spoke that has multiple hubs and allows direct transportation between spokes. We developed a mathematical optimization model for automotive service parts transportation planning under hybrid multiple hub-and-spoke network structure. The model suggests a long-term transportation route planning and a short-term vehicle assignment planning. The model is verified by simulation and validated in real world application to Hyundai Mobis automotive service parts transportation planning. From the simulation result, the model reduced the transportation cost about 24.7%, the total distance about 6.8% and the CO2 emissions about 8.8%. In real world application for 6 months from July to December 2010, the model reduced the transportation cost about 9.1% by changing the long-term transportation route without daily vehicle assignment planning.

• Journal of Electrical Engineering and Technology
• /
• 제9권6호
• /
• pp.1882-1890
• /
• 2014

This paper proposes an augmented Lagrange Hopfield network (ALHN) based method for solving multi-objective short term fixed head hydrothermal scheduling problem. The main objective of the problem is to minimize both total power generation cost and emissions of $NO_x$, $SO_2$, and $CO_2$ over a scheduling period of one day while satisfying power balance, hydraulic, and generator operating limits constraints. The ALHN method is a combination of augmented Lagrange relaxation and continuous Hopfield neural network where the augmented Lagrange function is directly used as the energy function of the network. For implementation of the ALHN based method for solving the problem, ALHN is implemented for obtaining non-dominated solutions and fuzzy set theory is applied for obtaining the best compromise solution. The proposed method has been tested on different systems with different analyses and the obtained results have been compared to those from other methods available in the literature. The result comparisons have indicated that the proposed method is very efficient for solving the problem with good optimal solution and fast computational time. Therefore, the proposed ALHN can be a very favorable method for solving the multi-objective short term fixed head hydrothermal scheduling problems.