Short term load forecasting using genetically optimized neural network cascaded with a Modified Kohonen clustering process

1997-07-18
Erkmen, İsmet
Ozdogan, A
In this study, a new intelligent approach is developed for short term load forecasting (STLF). The technique consists of three basic modules. The first module employ the clustering of daily load curves using Modified Kohonen algorithm (MKA). Second module determine the most appropriate supervised neural network topology and associated initial weight values for each cluster, extracted from the historical data base, by using genetic algorithm (GA). At the third module, genetically optimized three layered back propagation (BP) network is trained and run to perform hourly load forecasting. Effects of each module on the forecasting accuracy are considered separately. The proposed system is tested extensively with the load curves of Turkish electrical power system of 1993 using different day types from different times of the year and promising results are obtained with approximately 1 % of mean error for the days distributed throughout the year.

Suggestions

Forecasting Turkey's Short Term Hourly Load with Artificial Neural Networks
BİLGİÇ KÜÇÜKGÜVEN, MERİÇ; Girep, C. P.; ASLANOĞLU, SAİME YEŞER; AYDINALP KÖKSAL, MERİH (2010-04-22)
Load forecasting is important necessity to provide economic, reliable, high grade energy. In this study, short term hourly load forecasting systems were developed for nine load distribution regions of Turkey using artificial neural networks (ANN) approach. ANN is the most commonly preferred approach for load forecasting. The mean average percent error (MAPE) of total hourly load forecast for Turkey is found as 1.81%.
Medium-Term Electricity Demand Forecasting Based on MARS
İlseven, Engin; Göl, Murat (2017-09-29)
The paper proposes use of multivariate adaptive regression splines (MARS) method to perform monthly electricity demand forecasting for medium-term. The model is developed based on specific example of Turkey; however is applicable to any other system. Performance of the proposed method is compared to that of multiple linear regression (MLR), generalized additive model (GAM), and artificial neural networks (ANN) methods. The validation process shows that the proposed model outperforms the other ones by test e...
Active Flutter Control of a Smart Fin
Fatih Mutlu, Karadal; Volkan, Nalbantoğlu; Şahin, Melin; Güçlü, Seber; Ömer Faruk, Kırcalı; Yaman, Yavuz (null; 2008-10-06)
This study presents the theoretical analysis of an active flutter suppression methodology applied on a smart fin. The smart fin consisted of a cantilever aluminum plate-like structure with surface bonded piezoelectric (PZT, Lead- Zirconate-Titanate) patches. The robust controllers were designed via H∞ synthesis by considering both SISO (Single-Input, Single-Output) and MIMO Multi-Input, Multi-Output) aeroelastic system models. The developed controllers performed well around the flutter point and also stabil...
Robust optimization of risk-aware, resilient and sustainable closed-loop supply chain network design with Lagrange relaxation and fix-and-optimize
Lotfi, Reza; Sheikhi, Zohre; Amra, Mohsen; AliBakhshi, Mehdi; Weber, Gerhard Wilhelm (2021-12-01)
This study explores a Robust, Risk-aware, Resilient, and Sustainable Closed-Loop Supply Chain Network Design (3RSCLSCND) to tackle demand fluctuation like COVID-19 pandemic. A two-stage robust stochastic multiobjective programming model serves to express the proposed problems in formulae. The objective functions include minimising costs, CO2 emissions, energy consumption, and maximising employment by applying Conditional Value at Risk (CVaR) to achieve reliability through risk reduction. The Entropic Value ...
Optimum design of steel structures via differential evolution algorithm and application programming interface of SAP2000
Dedekargınoğlu, Özgür; Hasançebi, Oğuzhan; Department of Civil Engineering (2012)
The objective of this study is to investigate the use and efficiency of Differential Evolution (DE) method on structural optimization. The solution algorithm developed with DE is computerized into software called SOP2011 using VB.NET. SOP2011 is automated to achieve size optimum design of steel structures consisting of 1-D elements such as trusses and frames subjected to design provisions according to ASD-AISC (2010) and LRFD-AISC (2010). SOP2011 works simultaneously with the structural analysis and design ...
Citation Formats
İ. Erkmen and A. Ozdogan, “Short term load forecasting using genetically optimized neural network cascaded with a Modified Kohonen clustering process,” 1997, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/40055.