Search

Recently, solar energy is expanding to combination of computing in real time by tracking the position of the sun to estimate the angle of inclination and make up freshly correcting a part of the solar radiation. Solar power is need that reliably linked technology to power generation system renewable energy in order to efficient power production that is difficult to output predict based on the position of the sun rise. In this paper, we analysis of prediction model for solar power generation to estimate the predictive value of solar power generation in the development of real-time weather data. Photovoltaic power generation input the correction factor such as temperature, module characteristics by the solar generator module and the location of the local angle of inclination to analyze the predictive power generation algorithm for the prediction calculation to predict the final generation. In addition, the proposed model in real-time national weather service forecast for medium-term and real-time observations used as input data to perform the short-term prediction models.

Recently, wind energy is expanding to combination of computing to forecast of wind power generation as well as intelligent of wind powerturbine. Wind power is rise and fall depending on weather conditions and difficult to predict the output for efficient power production. Wind power is need to reliably linked technology in order to efficient power generation. In this paper, distributed power generation forecasts to enhance the predicted and actual power generation in order to minimize the difference between the power of distributed power short-term prediction model is designed. The proposed model for prediction of short-term combining the physical models and statistical models were produced in a physical model of the predicted value predicted by the lattice points within the branch prediction to extract the value of a physical model by applying the estimated value of a statistical model for estimating power generation final gas phase produces a predicted value. Also, the proposed model in real-time National Weather Service forecast for medium-term and real-time observations used as input data to perform the short-term prediction models.

In this paper, we propose a recognition technique of electric poles and wires which are drawn on a power distribution facility map. The map represents power supply facilities. Proposed technique is based on circularity and connectivity, and consists of four phases. At first, we extract a power distribution facility area from input image using threshold value. Secondly, we apply a thinning. At the third step, we extract candidate poles based on circularity. Finally, after electric wires between two branch points is recognized based on connectivity, candidate poles with at least a wire are confirmed to electric poles.

KEPCO has installed electronic power meters for customers who have relatively high annual power consumption and operated the AMR (Automatic Meter Reading) system that records the amount of power consumption every 15 minutes. To analyze the load of the distribution line using the data collected by the AMR system, this study suggested a method of generating a typical load profile based on the clustering method using the load data of customers. Currently, typical load profiles are usually generated by calculating the average power consumption as recorded every 15 minutes based on the load profiles of customers with the same contract code. Even though they share the same contract code, however, the load analysis has low accuracy because it often shows different load profiles. This study suggested a means of performing customer clustering and generating the typical load profile of each group using the k-means method as one of the clustering methods and 15-minute AMR data of customers sharing the same contract code.

In this paper, we propose a recognition technique of electric poles and wires which are drawn on a power distribution facility map. The map represents power supply facilities from substation to consumer. Proposed technique is based on circularity and connectivity, and consists of four phases. At first, we extract a power distribution facility area from input image using threshold value obtained by histogram analysis. Secondly, a thinned image is obtained by applying a thinning operator. At the third step, we extract candidate poles based on circularity which is measured in the search area around the branch points of thinned image. Finally, after electric wires between two branch points is recognized based on connectivity, candidate poles with at least a wire are confirmed to electric poles. The experimental study is performed on randomly sampled 30 power distribution facility map.