Bijay Ketan Panigrahi

Discrete harmony search based expert model for epileptic seizure detection in electroencephalography

Seizure detection and classification using signal processing methods has been an important issue of research for the last two decades. In the present study, a novel scheme was presented to detect epileptic seizure activity with very fast and highest accuracy from background electro encephalogram (EEG) data recorded from epileptic and normal subjects. The proposed scheme is based on discrete wavelet packet transform (DWT) with energy, entropy, standard deviation, mean, kurtosis, skewness and entropy estimation at each node of the decomposition tree followed by application of probabilistic neural network (PNN). Normal as well as epileptic EEG epochs were decomposed into approximation and details coefficients till sixth-level using DWT packet. Discrete harmony search with modified differential operator was used to select the optimal features out of all above mentioned statistical and non-statistical parameters. In order to demonstrate the efficacy of the proposed algorithm for classification purpose using PNN, we have implemented 10-fold cross validation. Clinical EEG data recorded from normal as well as epileptic subjects are used to test the performance of this new scheme. It is found that the detection rate is 100% accurate with same level of sensitivity and specificity.

Adaptive Distance Relaying Scheme for Transmission Network Connecting Wind Farms

Abstract This article presents an adaptive distance relay setting for a power transmission network connecting more than one wind farm. The ideal trip characteristics of the distance relay is greatly affected in the presence of complex mutual coupling of transmission lines, as the apparent impedance is significantly affected. Similarly, the reach setting of the relay for the lines connecting wind farms is significantly affected, as the relaying voltage fluctuates continuously. Thus, the proposed study focuses on developing an adaptive relay setting for a transmission network including more than one wind farm and considering variations in operating conditions of wind farms and mutual coupling of transmission lines together. The proposed relay algorithm is extensively tested on two-terminal as well as multi-terminal power networks with wide variations in operating parameters. The performance testing of the proposed adaptive relay characteristics for faults and faults during power swing indicates the potential ability of the approach in handling distance relaying in a transmission system.

Extreme Learning Machine Based Adaptive Distance Relaying Scheme for Static Synchronous Series Compensator Based Transmission Lines

Abstract This article presents an extreme learning machine based fast and accurate adaptive distance relaying scheme for transmission lines in the presence of a static synchronous series compensator. The ideal trip characteristics of the distance relay is greatly affected by pre-fault system conditions, ground fault resistance, and zero-sequence voltage. The proposed research develops an extreme learning machine based adaptive distance relaying scheme for two-terminal transmission networks with static synchronous series compensators when a single-line-to-ground fault situation is most likely to occur. The study includes an analytical approach, including a steady-state model of static synchronous series compensator with detailed simulation on MATLAB/Simulink (The MathWorks, Natick, Massachusetts, USA) and open real-time simulation software with MATLAB (OPAL-RT) platform (OPAL-RT Technologies, Montreal, Quebec, Canada). The proposed extreme learning machine based adaptive distance relaying scheme is extensively validated on the two terminal transmission lines with static synchronous series compensators, and the performance is compared with the existing radial basis feed-forward neural network based adaptive distance relaying scheme. The results on simulation and real-time platform show significant improvements in the performance indices, such as speed, selectivity, and reliability of the digital relay.

Energy management in hybrid electric vehicles using optimized radial basis function neural network

This paper deals with energy management in hybrid electric vehicles. Use of radial basis function neural network (RBFNN) for the problem of energy management gains importance in the present decade. Use of genetic algorithm (GA) and particle swarm optimization (PSO) as optimization algorithms for parameter estimation is also well known. However, none of the researchers in the area tried to use GA and PSO as training algorithms for the problem. Hence in this paper, we propose two novel methods, based on RBFNN. The difference between RBFNN-based approaches in the literature and those used in this paper is the use of GA and PSO (i.e. optimising algorithms) as training algorithm to train RBFNNs. Interestingly, it is seen that the proposed approaches of this paper outperform RBFNN-based approaches in the literature with traditional training.

Maximum power extraction from partially shaded PV panel in rainy season by using improved antlions optimization algorithm

In the rainy season, the climate fluctuation and rate of environmental change is very high. as well as the movement of clouds and water drops create a partial shaded situation on PV (photovoltaic) panel. Therefore, the extraction of maximum power from PV panel is the major challenge in the rainy season. This paper introduces a novel “Improved Antlions Optimization” (IAO) algorithm for quick searching the maximum power point (MPP). The IAO algorithm is inspired to the hunting behavior of the antlion and the prey selection behavior of antlion is improved by using ranking technique. Therefore, IAO reaches the global maximum power point (GMPP) very quickly and suitable for online searching on hardware. Here, the IAO based GMPP tracking (GMPPT) algorithm on the five types of PV patterns, is tested in MATLAB simulation and verified on a developed hardware of the SPV system through comparison to the actual MPP. The satisfactory steady-state and dynamic performances of the IAO algorithm are demonstrated under variable irradiance and temperature during partial shaded conditions.

Maximum power peak detection of partially shaded PV panel by using intelligent monkey king evolution algorithm

This work deals with the development of a new ‘intelligent monkey king evolution (IMKE) algorithm’ for maximum power peak (MPP) detection under partially shaded solar photovoltaic (SPV) conditions. The major advantages of the developed technique are simple in implementation, population free, extremely less memory requirement, zero algorithms constant dependence, fast convergence and perfect structure for the cheaper microcontroller. The proposed algorithm is performed on 10 types of power-voltage (P-V) pattern of partially shaded SPV array. Moreover, in the first stage, it is tested in MATLAB simulator after that verified on a developed hardware as well as compared with the state of the art methods. The satisfactory steady-state and dynamic performances of the IMKE algorithm at partially shaded SPV array shows the superiority over the state of the art control methods.

Normal harmonic search algorithm based MPPT of solar PV system

This paper introduces a single sensor based maximum power point tracking (MPPT) strategy for solar photovoltaic (PV) array fed battery charging by using normal harmonic search (NHS) algorithm. The NHS algorithm is an improved version of the harmony search, which is inspired to the music composition technique and its searching ability is improved by using the normal probability distribution factor. Therefore, NHS reaches the global maximum point (GMP) very quickly and found suitable for online searching. In this work, the objective of the NHS algorithm is, the maximum extraction of the power from a PV array and efficiently charging the battery through maximizing the charging current of the battery. Due to the single sensor, the cost of the MPPT is reduced, as well as the algorithm complexity and computational burden are very less, so it can be easily implemented on the low-cost microcontroller. Here, a single current sensor based battery charging by NHS algorithm is tested on MATLAB simulation and verified on a developed prototype of the PV system. The satisfactory steady-state and dynamic performances of the NHS algorithm is obtained for a single current sensor based battery charging, under variable irradiance and temperature.

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.

Evolutionary MPNN for Channel Equalization

This paper proposes a novel equalizer, termed here as Evolutionary MPNN, where a complex modified probabilistic Neural Networks (MPNN) acts as a filter for the detected signal pattern. The neurons were embedded with optimization algorithms. We have considered two optimization algorithms, Bacteria Foraging Optimization (BFO) and Ant Colony Optimization (ACO). The proposed structure has the ability to process complex signals also can perform for slowly varying channels. Also, Simulation results prove the superior performance of the proposed equalizer over the existing MPNN equalizers.