{"title":"A hybrid \"k-means, VSS LMS\" learning method for RBF network in short-term load forecasting","authors":"E. Mostafapour, M. Panahi, M. Farsadi","doi":"10.1109/ELECO.2015.7394463","DOIUrl":"https://doi.org/10.1109/ELECO.2015.7394463","url":null,"abstract":"In this paper we investigate the performance of a hybrid learning algorithm for RBF network in the application of short-term load forecasting. In this method the algorithm for finding radial basis function centers of hidden layer is k-means and the algorithm for training the weights of output layer is adaptive variable step-size algorithm. We proved this method is both accurate and fast in comparison with other presented schemes. Also we demonstrated that this method requires less computational processing and can perform well when amount of the input data is large. Our simulation results show there is up to 30 percent improvement in processing time and 37% improvement in prediction accuracy when compared with previously improved k-means learning.","PeriodicalId":369687,"journal":{"name":"2015 9th International Conference on Electrical and Electronics Engineering (ELECO)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115697961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Robust & optimal model predictive controller design for twin rotor MIMO system","authors":"A. Ulasyar, Haris Sheh Zad","doi":"10.1109/ELECO.2015.7394488","DOIUrl":"https://doi.org/10.1109/ELECO.2015.7394488","url":null,"abstract":"In this paper a two degree of freedom Twin Rotor MIMO System (TRMS), which is employed to model the pitch and yaw directions of a helicopter, is considered. Using the model of TRMS, MATLAB simulaitons are performed. The open loop model of the system is unstable. Since the system is both controllable and observable, a robust and optimal Model Predictive Controller (MPC) is designed to control the system. The simulations of the controller give better results as compared to the one obtained from LQR approach.","PeriodicalId":369687,"journal":{"name":"2015 9th International Conference on Electrical and Electronics Engineering (ELECO)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123528791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
O. Ceylan, M. Starke, P. Irminger, B. Ollis, K. Tomsovic
{"title":"A regression based hourly day ahead solar irradiance forecasting model by labview using cloud cover data","authors":"O. Ceylan, M. Starke, P. Irminger, B. Ollis, K. Tomsovic","doi":"10.1109/ELECO.2015.7394592","DOIUrl":"https://doi.org/10.1109/ELECO.2015.7394592","url":null,"abstract":"This paper applies a regression based numerical method for photovoltaic power output hourly forecast. The method uses a historical data composed of irradiance, azimuth, zenith angle and time of day information. In every run of the forecast program, publicly available cloud cover forecast data for the following day is obtained, and by using a numerical regression based method a function is fit. Then by using the publicly available temperature forecast data, forecasted irradiance data, and computed solar position (zenith, azimuth) data, both power output and temperature module output of PV array is computed. Numerical forecast results show that, they are in accordance with the actual data.","PeriodicalId":369687,"journal":{"name":"2015 9th International Conference on Electrical and Electronics Engineering (ELECO)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123844652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Ozturk, S. Tosun, Selman Alkan, Beytullah Bozalı
{"title":"Investigating voltage stability problem in the electrical power system using gravitational search algorithms","authors":"A. Ozturk, S. Tosun, Selman Alkan, Beytullah Bozalı","doi":"10.1109/ELECO.2015.7394492","DOIUrl":"https://doi.org/10.1109/ELECO.2015.7394492","url":null,"abstract":"This study aims to utilize the Gravitational Search Algorithm (GSA) to find the optimal values of the proportional integral derivative (PID) controller parameters to control the automatic voltage regulator (AVR). GSA is categorized as a heuristic algorithm. In finding the optimal values, we try to minimize the performance index also called the error in the closed loop control diagram. We observed and compared the three different situations of the error, namely the integrated absolute error (IAE), the integral of squared error (ISE), and the integral time absolute error (ITAE). We, then, employed a conventional Ziegler-Nicolas Method (ZNM) to find the optimal values under the same conditions with GSA. The values obtained through both methods are compared at the end. We show that the proposed method using GSA has a better performance than ZNM in terms of settling time, oscillations and overshoot. We also compared our results with the ones obtained through Genetic Algorithms (GA). Similarly, our method performs better.","PeriodicalId":369687,"journal":{"name":"2015 9th International Conference on Electrical and Electronics Engineering (ELECO)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125366175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Solution to short term hydrothermal scheduling problem by modified subgradient algorithm based on feasible values","authors":"S. Fadil, Burak Urazel","doi":"10.1109/ELECO.2015.7394453","DOIUrl":"https://doi.org/10.1109/ELECO.2015.7394453","url":null,"abstract":"In this paper, the modified subgradient algorithm based on feasible values (F-MSG) is applied to a short term hydrothermal coordination problem. Power system transmission loss is inserted into this model as equality constraints via load flow equations. Unit generation constraints, transmission line capacity constraints, bus voltage magnitude constraints, off nominal tap ratio constraints, SVAR system susceptances constraints, hydraulic units' minimum and maximum reservoir volume constraints, hydraulic units' starting and final reservoir volume constraints are also added into the optimization problem. Since all constraints in the nonlinear programming model are functions of complex bus voltages, off-nominal tap ratios and SVAR system susceptances (once there are off nominal tap changing transformers and SVAR systems in the power system), they are taken as independent variables. The proposed approach is tested on 16 bus test system where there are four serial-parallel hydraulically coupled hydro plants. The same dispatch problem was also solved by other dispatch techniques that use pseudo spot price algorithm and classical gradient method previously. Results obtained from those algorithms and F-MSG are also compared.","PeriodicalId":369687,"journal":{"name":"2015 9th International Conference on Electrical and Electronics Engineering (ELECO)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125506622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Design and implementation of adaptive vibration filter for MEMS based low cost IMU","authors":"Ufuk Guner, H. Canbolat, A. Unluturk","doi":"10.1109/ELECO.2015.7394499","DOIUrl":"https://doi.org/10.1109/ELECO.2015.7394499","url":null,"abstract":"In this work, an adaptive vibration filter was designed for Micro Electro - Mechanical System (MEMS) based on low cost Inertial Measurement Unit (IMU). Designed IMU has ten degree freedom. It consists of three axis accelerometer, three axis gyroscope, three axis magnetometer and one axis barometric pressure sensor. All sensors are connected to Cortex M3 based microcontroller. Kalman Filter was used as sensor fusion algorithm. Although Kalman filter could overcome many noise sources, it could give undesirable output signal when sensors, which are combined with Kalman filter, were affected by simultaneously same noise like as vibration noise. So in order to overcome the vibration affection of IMU, an Adaptive Noise Canceller (ANC) was designed and implemented for the IMU. In addition, an experimental setup was built to compare the IMU output with and without ANC.","PeriodicalId":369687,"journal":{"name":"2015 9th International Conference on Electrical and Electronics Engineering (ELECO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129799031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Huseyin Cukur, Hamidullah Binol, Faruk Sukru Uslu, Yusuf Kalayci, A. Bal
{"title":"Cross correlation based clustering for feature selection in hyperspectral imagery","authors":"Huseyin Cukur, Hamidullah Binol, Faruk Sukru Uslu, Yusuf Kalayci, A. Bal","doi":"10.1109/ELECO.2015.7394552","DOIUrl":"https://doi.org/10.1109/ELECO.2015.7394552","url":null,"abstract":"One of the main problems with hyperspectral image processing is to be contained large amount of data. Furthermore, pattern recognition methods are highly sensitive to problems related to high dimensional feature spaces. Therefore, feature selection in hyperspectral remote sensing data is investigated by researchers. This paper propose a clustering strategy that divides a feature set into subsets within which features are closely related to each other by means of cross correlation between all spectral bands. After that a band selection strategy based on Minimum Redundancy Maximum Relevance (mRMR) eliminates redundant bands into band clusters. The effectiveness of the proposed method is carried out on a real hyperspectral data set. The obtained results clearly affirm the superiority of the proposed method.","PeriodicalId":369687,"journal":{"name":"2015 9th International Conference on Electrical and Electronics Engineering (ELECO)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129948877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"High frequency Gaussian beam interaction with plasma medium","authors":"Selçuk Alparslan Avci, E. Afacan","doi":"10.1109/ELECO.2015.7394455","DOIUrl":"https://doi.org/10.1109/ELECO.2015.7394455","url":null,"abstract":"Finite difference time domain method (FDTD) is a widely used numerical method for solving time domain electromagnetic problems. In this paper, the behaviour of a sine wave inside a Gaussian envelope propagating through two cascade plasma media is investigated. Perfectly matched layer (PML) is used as the absorbing boundary condition.","PeriodicalId":369687,"journal":{"name":"2015 9th International Conference on Electrical and Electronics Engineering (ELECO)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128859209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Evaluation of parametric and non-parametric methods for power curve modelling of wind turbines","authors":"D. Panahi, S. Deilami, M. Masoum","doi":"10.1109/ELECO.2015.7394497","DOIUrl":"https://doi.org/10.1109/ELECO.2015.7394497","url":null,"abstract":"The growing applications of wind power systems and their essential roles in renewable energy production require development of accurate methods for their parameter identification such as the wind turbine power curves. This paper evaluates and compares the parametric and non-parametric approaches for power curve modelling of wind turbine which is a very complicated and nonlinear function of different mechanical, electrical and metrological input parameters. In fact achieving a complete model that can accurately describe the turbine output characteristic is very difficult. However, there are different modelling techniques that could lead to have a better estimation of turbine generation model. In this paper, four different algorithms for modelling the output power of wind turbines in form of two strategies using two case studies will be developed and the results of different models will be compared.","PeriodicalId":369687,"journal":{"name":"2015 9th International Conference on Electrical and Electronics Engineering (ELECO)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116477410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
F. Shahir, M. Farsadi, Heydar Zafari, A. Sadighmanesh
{"title":"Solving economic emission load dispatch problems using particle swarm optimization with smart inertia factor","authors":"F. Shahir, M. Farsadi, Heydar Zafari, A. Sadighmanesh","doi":"10.1109/ELECO.2015.7394638","DOIUrl":"https://doi.org/10.1109/ELECO.2015.7394638","url":null,"abstract":"This paper attempts to propose particle swarm optimization algorithm with smart inertia factor (PSO-SIF) to solve the problem of economic emission load dispatch (EELD) in thermal power plants. The aim of EELD solution is synchronous reduction of both fuel costs and emission level. EELD problem is a non-linear and non-convex problem which uses evolutionary algorithms as efficient to solve such problems due to its complicated characteristics. PSO-SIF algorithm is an efficient and robust algorithm to exploit universal optimal point of optimization problems. Tests implemented on 10-unite systems, considering valve-point loading effects, network losses with Multi-objective functions such as system fuel cost and emission level, to show PSO-SIF algorithm capabilities in solving EELD problems. Results obtained from present investigation indicated universal optimal point exploitation of the problems and superiority of the proposed algorithm compared to other new and efficient algorithms.","PeriodicalId":369687,"journal":{"name":"2015 9th International Conference on Electrical and Electronics Engineering (ELECO)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124157619","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}