STUDY OF THE SHORT-TERM GENERATION BLOCK FREQUENCY FORECASTING OF A POWER GENERATION UTILITY USING ARTIFICIAL NEURAL NETWORK

Shailendra Singh, R P Payasi, S K Sinha

Abstract: Frequency forecasting a very vital aspect in power system operation and control. For power generation utilities the computation of the frequency forecasting is crucial for administering power generation and trading optimally. Beside this, frequency of the grid is the most vital and decisive parameter for the appraisal of the entire power system network safety, and to estimate the grid power quality. Frequency of the power system corresponds to power generation balance to any point of time with respect to load/demand. The power generation inequality/imbalance leads to differ frequency from its nominal value i.e. 50 Hz in our country. Larger deviation in frequency can sabotage power system operation severely in the form of Grid turmoil along with the tripping of the Generators and turbines connected to Grid which can eventually leads to grid collapse. Forecasting the frequency ahead in time is desired to avert all these problems instigating on the frequency deviations. Importance of the frequency perceived with advent of the ABT, by imposing the tariff to power generating utilities sensitive to the frequency. Part of this tariff is paid for UI (Unscheduled Interchange) of power supplied in deviation with scheduled power. In traditional approaches, frequency prediction algorithms prepared based on pattern matching of the previous frequencies, but here in this paper an algorithms is prepared which will include the various other non linear parameters also such as actual power generated, load demand in term of scheduled power generation allocated to particular utility. This deficit/surplus power is taken as one of the key factor for forecasting the frequency to a fair degree of accuracy. ANN’s ability to provide most accurate forecasting results with smaller processing time is utilized here in this paper. In this work, we will study short-term frequency prediction for a thermal power generating station station with the help of ANN. We will utilize the past two year data of plant’s suggested generation, declared capacity and frequency for each block of 15 minutes to train the Artificial Neural Network.

Keywords: ABT, Unscheduled Interchange, NRLDC Artificial Neural Network, Load Dispatch

DOI: https://doi.org/10.15623/ijret.2017.0611007