http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Performance Comparison of Short Term Load Forecasting Techniques
Kumar Reddy Cheepati,T. Nageswara Prasad 보안공학연구지원센터 2016 International Journal of Grid and Distributed Comp Vol.9 No.4
Load forecasting plays a major role in planning and operation of a power system. Many techniques are available in the literature among these neural networks, linear multiple regression, regression trees, curve fitting and averaging models are the most popular because these models gives accurate solutions with very less tolerable Least Mean Absolute Percent Error(MAPE). In this paper a comparative study was made between these forecasting models and it was found that when compared to the four independent models, the averaging model i.e. combination of Curve Fitting, Regression Trees & Neural Network gives less MAPE. MATLAB programming results validates that averaging model gives better performance than individual models.
Kumar Reddy Cheepati,Nageswara Rao Maddala,Surya Kalavathi Munagala 대한전기학회 2020 Journal of Electrical Engineering & Technology Vol.15 No.2
The exponential growth of non-linear loads results the generation of harmonics in electrical distribution system. Major Harmonic generation efects due to non-linear loads are energy loss, nuisance tripping, equipment failure/mal-operation, and transformer saturation, overheating of neutral conductors and/or capacitors, interference with communication circuits, excess reactive power burden and lowering the true power factor. Improving the current quality is the prime responsibility of the consumers whereas utility is accountable for minimizing the supply voltage distortions. Shunt active flters (SAFs) were being used for many years to mitigate the current harmonics typically up to 25th order. Mainly, time and frequency domain reference current extraction control techniques were being used for SAF. Time-domain reference current extraction techniques were proved efcient than frequency-domain techniques due to their faster response. Time-domain reference current extraction techniques such as real and reactive (p-q) and synchronous reference frame (SRF) are having their own merits and demerits. The p-q control does not perform well under distorted and unbalanced supply voltage conditions whereas SRF control is limited to balanced loads. In this paper a novel reference current extraction control strategy is proposed i.e. inverse matrix averaging pq-SRF (IMApq-SRF) control. IMApq-SRF control extract the features of both conventional p-q and SRF control, based on inverse matrix average. The mathematical modeling of the proposed IMApq-SRF control is tested with MATLAB Simulink environment and it validates that the proposed IMApq-SRF control gives the superior performance as compared with conventional p-q and SRF techniques under balanced, unbalanced and distorted supply voltage and dynamic loading conditions.