Nitin Anand Shrivastava

Prediction Interval Estimation of Electricity Prices Using PSO-Tuned Support Vector Machines

Uncertainty of the electricity prices makes the task of accurate forecasting quite difficult for the electricity market participants. Prediction intervals (PIs) are statistical tools which quantify the uncertainty related to forecasts by estimating the ranges of the future electricity prices. Traditional approaches based on neural networks (NNs) generate PIs at the cost of high computational burden and doubtful assumptions about data distributions. In this work, we propose a novel technique that is not plagued with the above limitations and it generates high-quality PIs in a short time. The proposed method directly generates the lower and upper bounds of the future electricity prices using support vector machines (SVM). Optimal model parameters are obtained by the minimization of a modified PI-based objective function using a particle swarm optimization (PSO) technique. The efficiency of the proposed method is illustrated using data from Ontario, Pennsylvania-New Jersey-Maryland (PJM) interconnection day-ahead and real-time markets.

Electricity price classification using extreme learning machines

Abstract Forecasting electricity prices has been a widely investigated research issue in the deregulated power market scenario. High price volatilities, price spikes caused by a number of factors such as weather uncertainty, fluctuating fuel prices, transmission bottlenecks, etc., make the task of accurate price forecasting a formidable challenge for the market participants. A number of models have been proposed by researchers; however, achieving high accuracy is always not possible. In some specific applications such as self-scheduling by demand side participants, certain price thresholds are more useful than accurate price forecasts. In this paper, we have investigated the application of a novel neural network-based technique called extreme learning machine for the problem of classification of future electricity prices with respect to certain price thresholds. Different models corresponding to different lead times are developed and tested with data corresponding to Ontario and PJM markets. It is observed that classification with ELM is fast, less sensitive to user defined parameters and easily implementable.

Point and prediction interval estimation for electricity markets with machine learning techniques and wavelet transforms

A growing number of countries all over the world are switching over to deregulated or the market structure of electricity sector with a view to enhance productivity, efficiency and to lower the prices. Barring a few cases, the deregulated structure is doing quite well in most of the countries. However a persistent issue that plagues the involved parties such as producers, traders, retailers etc., is the uncertainty that prevails in the system. Due to a number of known, unknown factors, the electricity prices exhibit fluctuating characteristics which is difficult to control as well as predict. Several forecasting techniques have been developed and successfully implemented for existing markets around the world with comparable performance. However, the uncertainty aspect of the point forecasts has not been analyzed significantly. In this work, an attempt is made to quantify such uncertainties existing in the market using statistical techniques like prediction intervals. Hybrid models using neural networks and Extreme Learning machines with wavelets as preprocessors are developed and applied for point as well as prediction interval forecasting for Ontario Electricity Market, PJM Day-Ahead and Real time markets.

Groundwater level forecasting using SVM-QPSO

Forecasting the groundwater levels in a water basin plays a significant role in the the management of groundwater resources. In this study, Support Vector Machines (SVM) is used to construct a ground water level forecasting system. Further Quantum behaved Particle Swarm Optimization function is adapted in this study to determine the SVM parameters. Later, the proposed SVM-QPSO model is employed in estimating the groundwater level of Rentachintala region of Andhra Pradesh in India. The performance of the SVM-QPSO model is then compared with the ANN (Artificial Neural Networks). The results indicate that SVM-QPSO is a far better technique for predicting groundwater levels as it provides a high degree of accuracy and reliability.

Prediction interval estimation for electricity price and demand using support vector machines

Uncertainty is known to be a concomitant factor of almost all the real world commodities such as oil prices, stock prices, sales and demand of products. As a consequence, forecasting problems are becoming more and more challenging and ridden with uncertainty. Such uncertainties are generally quantified by statistical tools such as prediction intervals (Pis). Pis quantify the uncertainty related to forecasts by estimating the ranges of the targeted quantities. Pis generated by traditional neural network based approaches are limited by high computational burden and impractical assumptions about the distribution of the data. A novel technique for constructing high quality Pis using support vector machines (SVMs) is being proposed in this paper. The proposed technique directly estimates the upper and lower bounds of the PI in a short time and without any assumptions about the data distribution. The SVM parameters are tuned using particle swarm optimization technique by minimization of a modified Pi-based objective function. Electricity price and demand data of the Ontario electricity market is used to validate the performance of the proposed technique. Several case studies for different months indicate the superior performance of the proposed method in terms of high quality PI generation and shorter computational times.

Prediction interval estimation for wind farm power generation forecasts using support vector machines

Accurate forecasting of wind power generation is quite an important as well as challenging task for the system operators and market participants due to its high uncertainty. It is essential to quantify uncertainties associated with wind power generation forecasts for their efficient application in optimal management of wind farms and integration into power systems. Prediction intervals (PIs) are well known statistical tools which are used to quantify the uncertainty related to forecasts by estimating the ranges of the future target variables. This paper investigates the application of a novel support vector machine based methodology to directly estimate the lower and upper bounds of the PIs without expensive computational burden and inaccurate assumptions about the distribution of the data. The efficiency of the method for uncertainty quantification is examined using monthly data from a wind farm in Australia. PIs for short term application are generated with a confidence level of 90%. Experimental results confirm the ability of the method in constructing reliable PIs without resorting to complex computational methods.

Wind ramp event prediction with parallelized gradient boosted regression trees

Accurate prediction of wind ramp events is critical for ensuring the reliability and stability of the power systems with high penetration of wind energy. This paper proposes a classification based approach for estimating the future class of wind ramp event based on certain thresholds. A parallelized gradient boosted regression tree based technique has been proposed to accurately classify the normal as well as rare extreme wind power ramp events. The model has been validated using wind power data obtained from the National Renewable Energy Laboratory database. Performance comparison with several benchmark techniques indicates the superiority of the proposed technique in terms of superior classification accuracy.

Wind Power Ramp Events Classification Using Extreme Learning Machines

Wind power is becoming increasingly popular as a renewable source of energy. Being a non-dispatchable energy resource, wind power facilities entail efficient forecast mechanisms to estimate the production of various wind power utilities available. In an integrated grid system, a balance must be maintained between production and consumption. Given that wind power is directly affected by meteorological factors (wind speed etc.) accurately predicting such fluctuations becomes extremely important. These events of fluctuation are termed as ramp events. Forecast of wind power is important but accurate prediction of ramp events is much more crucial to the safety of the grid as well as the security and reliability of the grid. In this paper we employ the ELM (Extreme Learning Machine) technique on wind power data of 2012 Alberta, Canada market for different sampling times to predict wind power ramp events. We also try to compare it with respect to other existing standard algorithms of feed-forward Neural Networks to analyze the efficacy of the technique in the area. ELM is shown to outperform other techniques in terms of computation time whereas prediction performance is at par with other neural network algorithms.

Price forecasting using computational intelligence techniques: A comparative analysis

Deregulation of Power market has initiated a multitude of reforms in the electricity sector aiming to make it more efficient, transparent and friendly to both the consumers and the suppliers. Accurate forecasting of the future electricity prices has become the most important management goal since it forms the basis of maximizing profits for the market participants. Electricity price forecasting however is a complex task due to non-linearity, non-stationarity and volatility of the price signal. SVM is a newly developed technique that has many attractive features and good performance in terms of prediction. An optimum selection amongst a large number of various input combinations and parameters is a real challenge for any modelers in using SVMs. This study applies SVM to predicting the hourly market prices of Ontario market. Optimal parameters of SVM are determined using computational intelligence techniques such as Genetic algorithm, Particle Swarm Optimization and Quantum inspired Particles Swarm Optimization (QPSO). A detailed analysis of these techniques has been performed to evaluate their robustness and ability to reach global solution in different scenarios and using different models.

A hybrid swarm-machine intelligence approach for day ahead price forecasting

Accurate forecasting of the future electricity prices in deregulated markets has become the most important management goal since it forms the basis of maximising profits for the market participants. Electricity price forecasting, however is a complex task due to non-linearity, nonstationarity and volatility of the price signal. SVM is a machine intelligence technique that has good performance in terms of prediction. An optimum selection amongst a large number of various input combinations and parameters is a real challenge for any modeller in using SVMs. This study applies SVM to predict the hourly electricity prices of Ontario market. Optimal parameters of SVM are determined using swarm intelligence techniques. Some strategies are also developed specifically for day ahead market price forecasting considering data availability, the dynamics of price movement and forecasting horizon. A detailed analysis of a hybrid technique clubbing together the machine and swarm intelligence technique has been performed with different scenarios and strategies.