Short Term load forecasting for a Captive Power Plant Using Artificial Neural Network

The irregularity of Indian grid system increases, with increase in the power demand. The quality of power supplied by the power grid is also poor due to continuous variation in frequency and voltage. To overcome this problem of power deficit, Captive Power Plants installed capacity has grown at a faster rate. Here short term load forecasting of Yara Fertilizers India Private limited installed at Babrala, Uttar Pradesh is performed using multi-layer feed-forward Neural network in MATLAB. The algorithm used is a Levenberg Marquardt algorithm. However, the training and results from ANN are very fast and accurate. Inputs given to the Neural Network are time, ambient air temperature from the compressor, cool air temperature at the compressor and IGV opening. The need, benefits and growth of CPP in India and use of ANN for short term load forecasting of CPP has been explained in detail in the paper.

Download Full-text

Comparative Study Of Short Term Load Forecasting Using Multilayer Feed Forward Neural Network With Back Propagation Learning And Radial Basis Functional Neural Network

SAMRIDDHI A Journal of Physical Sciences Engineering and Technology ◽

10.18090/samriddhi.v7i1.4466 ◽

2015 ◽

Vol 7 (1) ◽

Cited By ~ 2

Author(s):

Amit Tiwari ◽

Adarsh Dhar Dubey ◽

And Devesh Patel

Keyword(s):

Neural Network ◽

Power System ◽

Structural Changes ◽

Unit Commitment ◽

Network Reliability ◽

Peak Load ◽

Load Forecasting ◽

Short Term ◽

Feed Forward Neural Network ◽

Short Term Load Forecasting

The term load forecast refers to the projected load requirement using systematic process of defining load in sufficient quantitative detail so that important power system expansion decisions can be made. Load forecasting is necessary for economic generation of power, economic allocation between plants (unit commitment scheduling), maintenance scheduling & for system security such as peak load shaving by power interchange with interconnected utilities. With structural changes to electricity in recent years, there is an emphasis on Short Term Load Forecasting (STLF).STLF is the essential part of power system planning & operation. Basic operating functions such as unit commitment, economic dispatch, and fuel scheduling & unit maintenance can be performed efficiently with an accurate forecast. Short term load forecasting can help to estimate load flows & to make decisions that can prevent overloading. Timely implementations of such decisions lead to improvement of network reliability & to the reduced occurrences of equipment failures & blackouts. The aim of short term load forecasting is to predict future electricity demands based, traditionally on historical data and predicted weather conditions. Short term load forecasting in its basic form is a statistical problem, where in the previous load values (time series variables) and influencing factors (casual variables) are used to determine the future loads.

Download Full-text

A NOVEL APPROACH FOR SHORT-TERM LOAD FORECASTING USING SUPPORT VECTOR MACHINES

International Journal of Neural Systems ◽

10.1142/s0129065704002078 ◽

2004 ◽

Vol 14 (05) ◽

pp. 329-335 ◽

Cited By ~ 24

Author(s):

LIANG TIAN ◽

AFZEL NOORE

Keyword(s):

Neural Network ◽

Load Forecasting ◽

Support Vector ◽

Short Term ◽

Feed Forward Neural Network ◽

Modeling Approach ◽

Novel Approach ◽

Power Load ◽

Short Term Load Forecasting ◽

Network Approaches

A support vector machine (SVM) modeling approach for short-term load forecasting is proposed. The SVM learning scheme is applied to the power load data, forcing the network to learn the inherent internal temporal property of power load sequence. We also study the performance when other related input variables such as temperature and humidity are considered. The performance of our proposed SVM modeling approach has been tested and compared with feed-forward neural network and cosine radial basis function neural network approaches. Numerical results show that the SVM approach yields better generalization capability and lower prediction error compared to those neural network approaches.

Download Full-text