M. M. Tripathi

Day ahead hourly load and price forecast in ISO New England market using ANN

In restructured daily power markets, forecasting electricity price and load are most essential tasks and basis for any decision making. Short-term load forecasting is an essential instrument in power system planning, operation, and control. Also, the accurate day ahead electricity price forecasting provides crucial information for power producers and consumers to develop accurate bidding strategies in order to maximize their profit. In this paper artificial intelligence (AI) has been applied in short-term load and price forecasting that is, the day-ahead hourly forecast of the electricity market parameters (load and price) over a week. Neural network fitting tool of MATLAB Software has been used to compute the forecasted load and price in ISO New England market. The data used in the forecasting are hourly historical data of the temperature, electricity load and natural gas price of ISO New England market. The ANN was trained on hourly data from the 2007 to 2011 and tested on out-of-sample data from 2012. The simulation results have shown highly accurate day-ahead forecasts with very small error in load and price forecasting.

Long term load forecasting with hourly predictions based on long-short-term-memory networks

The conventional methodology for long term load forecasting is mostly restricted to electricity load data with monthly or annual granularity. This leads to forecasts with very low accuracy. In this paper, a novel method for long term load forecasting with hourly resolution is proposed. The model is fundamentally centered on Recurrent Neural Network consisting of Long-Short-Term-Memory (LSTM-RNN) cells. The long term relations in a time series data of electricity load demand are taken into account using LSTM-RNN and hence results in more accurate forecasts. The proposed model is implemented on real time data of ISO New England electricity market. Precisely, publicly available data of twelve years from 2004 to 2015 have been collected to train and validate the model. Electricity demand predictions have been made for a period of five years from 2011 to 2015 on a rolling basis. The proposed model is found to be highly accurate with a Mean Absolute Percentage Error (MAPE) of 6.54 within a confidence interval of 2.25%. Moreover, the model has a computation time of approximately 30 minutes which is favorable for offline training to forecast electricity load for a period of five years.

Artificial neural network based wind power forecasting in belgium

Power generation from renewable energy sources needs great attention for future power sector to meet steadily increasing power demand and to reduce global warming. But, wind power generation is very unsure and intermittent in its nature. Wind power forecasting assists grid integration of enormous capacity wind farms to great extent. Grid stability is greatly accrued with the help of correct wind power forecasting This paper describes the suitability of NARX Artificial neural network in wind power forecasting with the historical power data accessible from European nation Belgium wind farms and meteorological information for wind speed.

Novel hybrid price forecasting model using wavelet transform, time series time delay neural network and zero phase filter in AEMC market

In the daily price market, effective price forecasting in presence of the noisy data and intricate load features are important in deregulated power system. This paper presents a novel method of wavelet transform (WT) with data pre-filtering a prediction network based on time series time delay artificial neural network (TSDNN), and an error predicting algorithm based on TSDNN to forecast electricity prices of AEMC market for 2015. Filtered price is decomposed into various components at various frequencies using wavelet decomposition, seperate neural networks (NN) are applied to record individual components, finally results are then combined for final forecasts. Zero phase filter (ZPF) is applied to remove the delay. Error Prediction is shown through the box-plot distribution. Furthermore, low values obtained for the root mean square error (RMS) and mean absolute error (MAE) shows high accuracy of the proposed model. Numerical comparison signifies the effects of data pre-filtering and the accuracy of wavelet neural networks (WNN) based on a data set from AEMC Australia Market.

Short-term price forecasting using new wavelet-neural network with data pre filtering in ISO New England market

Effective load and price forecasting in presence of the noisy data collection process and complicated load features is important in deregulated power system. This paper presents a method of wavelet neural networks with data pre-filtering for short term price forecasting. The key idea is to use a spike filtering technique to detect spikes in load data and correct them. Wavelet decomposition is then used to decompose the filtered loads into multiple components at different frequencies, separate neural networks are applied to capture the features of individual components, and results of neural networks are then combined to form the final forecasts. To perform moving forecasts, six dedicated wavelet neural networks are used based on test results. Numerical testing demonstrates the effects of data pre-filtering and the accuracy of wavelet neural networks based on a data set from ISO New England.

An analysis of short-term price forecasting of power market by using ANN

In deregulated power markets, forecasting electricity parameters are most essential tasks & basis for any decision making. Price forecasting in competitive electricity markets is critical for consumers and producers in planning their operations and managing their price risk, and it also plays a key role in the economic optimization of the electric energy industry. Accurate, short-term price forecasting is an essential instrument which provides crucial information for power producers and consumers to develop accurate bidding strategies in order to maximize their profit. In this paper artificial intelligence (AI) has been applied in short-term price forecasting that is, the day-ahead hourly forecast of the electricity market price. A new artificial neural network (ANN) has been used to compute the forecasted price in ISO New England market using MATLAB R13. The data used in the forecasting are hourly historical data of the temperature, electricity load and natural gas price of ISO New England market. The simulation results have shown highly accurate day-ahead forecasts with very small error in price forecasting.

A novel wavelet modulation scheme for single phase inverter

DC-AC Inverters are key components in various industrial applications that include power supplies, motor drive systems and power systems. Now-a-days dc-ac inverters (both 1-phase & 3-phase) are finding more attention in renewable energy systems also. In this paper a new kind of switching scheme is discussed where gate pulses for switching of Single Phase 4 pulse voltage source (VS) DC-AC inverters are generated using wavelet modulation. Simulation for different loading conditions is performed and results are compared with results of PWM and Square pulse switching under same loading conditions. The wavelet modulation technique has shown tremendous advantages over PWM technique.