Very short-term load forecasting using artificial neural networks

Charytoniuk, W.; Chen, M.-S.

doi:10.1109/59.852131

Cited by 253 publications

(106 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Yapay sinir ağları (YSA) en güçlü tahmin yöntemlerinden birisidir ve birçok alanda kullanılmaktadır [11]- [18]. YSA ile tahmin işlemi yapılmadan önce YSA'nın eğitilmesi gereklidir.…”

Section: Introductionunclassified

Forecasting applications of the sheath current of high voltage cable with artificial neural network based hybrid methods

Akbal¹

2017

Pamukkale J Eng Sci

View full text Add to dashboard Cite

GirişElektrik enerjisinin iletiminde ve dağıtımında havai hatlar ile yüksek gerilim yeraltı kablolu hatlar kullanılmaktadır. Yüksek gerilim yeraltı kabloları yalıtımlı olduğundan dolayı havai hatlara göre daha güvenlidir. Fakat havai hatların maliyeti daha düşük olduğundan dolayı tercih sebebidir. Son yıllardaki nüfus artışından ve şehirlere olan göçün artmasından dolayı şehir merkezlerindeki yapılaşma artmıştır. Bu yüzden havai hatlar, yapılara ve insanların yaşam alanlarına yakın yapılmaktadır. Buda istenmeyen kısa devrelere ve elektrik çarpılmalarına neden olmaktadır. Bu türlü durumları engellemek için şehir merkezlerinde ve yapılaşmanın sık olduğu bölgelerde havai hatlar yeraltı kablolu hatlara dönüştürülmektedir.Yüksek gerilim yeraltı kablolarının yalıtımı genellikle XLPE (Çapraz bağlı polietilen) yalıtkanı ile yapılmaktadır ve XLPE yalıtkanı, kılıf ve zırh ile korunmaktadır. Fakat XLPE yalıtkanını korumak için kullanılan metal malzeme üzerinde kılıf akımı oluşmaktadır. Kılıf akımı kabloda ek ısı oluşturarak kablonun akım taşıma kapasitesini yani performansını düşürmekte aynı zamanda XLPE yalıtkanından kaynaklanan arızalara neden olmaktadır. Ayrıca kılıf akımı zırh üzerinde gerilim indükler ve bu gerilim seviyesinin 50 V olan dokunma gerilimini aşması durumunda elektrik çarpılma riski oluşturmaktadır. Bu türlü durumların engellenmesi için gereken önlemlerin alınması gerekmektedir. Fakat genellikle bu tür önlemler ya bir elektrik çarpılması veya ciddi bir arızadan sonra alınmaktadır. Eğer yüksek gerilim yeraltı kablolu hat kurulmadan yani proje aşamasında iken oluşabilecek kılıf akımı belirlenebilirse, bu istenmeyen olaylar yaşanmaz. Böylece yüksek gerilim yeraltı kablolu hattın güvenlik seviyesi ve verimi artırılmış olur. Kılıf akımının belirlenebilmesi için öncelikle bu akımın oluşumu ve bunu etkileyen faktörlerin bilinmesi gerekir.Kılıf akımının oluşmasındaki en önemli etken dengesiz yük akımıdır [1]. Dengesiz yük akımının artışı kılıf akımını da artırmaktadır. Yeraltı kabloların tesisindeki geometrisi de kılıf akımı etkileyen diğer bir faktördür. Yüksek gerilim yeraltı

show abstract

Section: Introductionunclassified

Forecasting applications of the sheath current of high voltage cable with artificial neural network based hybrid methods

Akbal¹

2017

Pamukkale J Eng Sci

View full text Add to dashboard Cite

show abstract

“…In contrast, the literature on specific forecasting systems, which concentrates on the solutions to specific forecasting problems, is extensive. Many of these systems have been developed for electric load forecasting (Kim et al, 1995;Khotanzad et al, 1997;Vermaak and Botha, 1998;Charytoniuk and Chen, 2000;Vilcahuamán et al, 2004). The rest are mainly for weather forecasting (Nelson and Winter, 1964;Kallos et al, 1997;Stern, 2002), stock price forecasting (Baba and Kozaki, 1992;Hiemstra, 1994), sales forecasting (Kuo, 2001;Thomassey and Fiordaliso, 2006) and flood forecasting (Kouwen, 2000;Li et al, 2006).…”

Section: Forecasting Systemsmentioning

confidence: 99%

Developing a Web-Based Tourism Demand Forecasting System

2008

View full text Add to dashboard Cite

Tourism demand is the foundation on which all tourism-related business decisions ultimately rest and so accurate forecasts of tourism demand are crucial for tourism industry practitioners. From the functional point of view, a tourism demand forecasting system (TDFS) is a forecasting support system capable of providing quantitative tourism demand forecasts and allowing users to make their own 'what-if' scenario forecasts. From the technical point of view, a TDFS is an information system consisting of a set of computer-based modules or components that support tourism demand forecasting and scenario analysis. This paper establishes a widely accessible Web-based TDFS which not only takes advantage of advanced econometric tourism demand forecasting techniques but also incorporates the real-time judgemental contribution of experts in the field. Furthermore, scenario forecasts are permitted within the system. Built on Webbased technology, the system provides advanced information sharing and communication and brings considerable convenience to various stakeholders engaged in tourism demand forecasting at different locations. In attempting to generate more accurate tourism demand forecasts, the system is designed to incorporate a two-stage forecasting methodology, which integrates judgemental adjustments with statistically based forecasts. The software architecture, detailed components and development environment of the Web-based TDFS are described in detail. A three-tiered client-server architecture is employed, which offers great flexibility, reusability and reliability. The prototype system has been developed and screen shots of interaction with the system are presented using Hong Kong tourism as an example.Keywords: tourism demand forecasts; econometric models; forecasting systems; judgemental forecasts; Web/Internet; Hong Kong Accurate forecasts of tourism demand are crucial for practitioners in the tourism industry (see Song and Witt, 2006). Over the past few decades, numerous researchers have been involved in the area of tourism demand forecasting and a wide variety of techniques have been developed. Most articles focus on quantitative modelling techniques, especially econometric and time-series methodsThe authors would like to thank the Hong Kong Polytechnic University for financial support (Grant No 1-BB08). TOURISM ECONOMICS 446(for detailed reviews of the tourism demand forecasting literature see Witt and Witt, 1995;Li et al, 2005). Many advanced quantitative tourism demand forecasting models have therefore been developed in the academic literature, but practitioners usually have little interest in scholarly journals and so either are not familiar with modern forecasting methods, or do not have the time to be involved in the design and development of advanced models to generate more accurate forecasts. For practitioners, one way of achieving more accurate forecasts is through a specialized forecasting system. The development of such systems is expensive and they often suffer from the limitations of individual ...

show abstract

“…Although the paper has been frequently cited, its autoregressive models were incorrectly applied to the load series. Charytoniuk and Chen proposed another approach using a set of ANNs to model the load dynamics instead of the actual loads [8]. For VSTLF, Taylor used the observations of minute-by-minute British electricity demand to evaluate various methods including autoregressive integrated moving average (ARIMA) models and two exponential smoothing methods [9].…”

Section: Introductionmentioning

confidence: 99%

Real-time anomaly detection for very short-term load forecasting

Luo

Hong

Yue

2018

J. Mod. Power Syst. Clean Energy

View full text Add to dashboard Cite

Although the recent load information is critical to very short-term load forecasting (VSTLF), power companies often have difficulties in collecting the most recent load values accurately and timely for VSTLF applications. This paper tackles the problem of real-time anomaly detection in most recent load information used by VSTLF. This paper proposes a model-based anomaly detection method that consists of two components, a dynamic regression model and an adaptive anomaly threshold. The case study is developed using the data from ISO New England. This paper demonstrates that the proposed method significantly outperforms three other anomaly detection methods including two methods commonly used in the field and one state-of-the-art method used by a winning team of the Global Energy Forecasting Competition 2014. Finally, a general anomaly detection framework is proposed for the future research.

show abstract

Very short-term load forecasting using artificial neural networks

Cited by 253 publications

References 12 publications

Forecasting applications of the sheath current of high voltage cable with artificial neural network based hybrid methods

Forecasting applications of the sheath current of high voltage cable with artificial neural network based hybrid methods

Developing a Web-Based Tourism Demand Forecasting System

Real-time anomaly detection for very short-term load forecasting

Contact Info

Product

Resources

About