Satyasis Mishra

Comparison of modified teaching---learning-based optimization and extreme learning machine for classification of multiple power signal disturbances

This paper presents a modified TLBO (teaching–learning-based optimization) approach for the local linear radial basis function neural network (LLRBFNN) model to classify multiple power signal disturbances. Cumulative sum average filter has been designed for localization and feature extraction of multiple power signal disturbances. The extracted features are fed as inputs to the modified TLBO-based LLRBFNN for classification. The performance of the proposed modified TLBO-based LLRBFNN model is compared with the conventional model in terms of convergence speed and classification accuracy. Also, an extreme learning machine (ELM) approach is used to optimize the performance of the proposed LLRBFNN and is compared with the TLBO method in classifying the multiple power signal disturbances. The classification results reveal that although the TLBO approach produces slightly better accuracy in comparison with the ELM approach, the latter is much faster in implementation, thus making it suitable for processing large quantum of power signal disturbance data.

Image denoising using neural network based Accelerated Particle Swarm Optimization

This paper proposes a new type of filter called neural network filter for image denoising. The noisy images are fed as input to the network and the weights are updated with LMS algorithm. Further the weights are updated by using a recently developed novel optimization technique called Accelerated Particle Swarm Optimization (APSO) for gray level image denoising application. Implementation of APSO is easier than the PSO(Particle Swarm Optimization) and GA(Genetic Algorithm) in terms of computational time. The results of comparison of the optimization has been presented.

Times Series Forecasting using Chebyshev Functions based Locally Recurrent neuro-Fuzzy Information System

The model proposed in this paper, is a hybridization of fuzzy neural network (FNN) and a functional link neural system for time series data prediction. The TSK-type feedforward fuzzy neural network does not take the full advantage of the use of the fuzzy rule base in accurate input-output mapping and hence a hybrid model is developed using the Chebyshev polynomial functions to construct the consequent part of the fuzzy rules. The model to be known as locally recurrent neuro fuzzy information system (LRNFIS) is used to provide an expanded nonlinear transformation to the input space thereby increasing its dimension which will be adequate to capture the nonlinearities and chaotic variations in the time series. The locally recurrent nodes will provide feedback connections between outputs and inputs allowing signal flow in both forward and backward directions, giving the network a dynamic memory useful to mimic dynamic systems. For training the proposed LRNFIS, an improved firefly-harmony search (IFFHS) learning algorithm is used to estimate the parameters of the consequent part and feedback loop parameters. Three real world time series databases like the electricity price of PJM electricity market, the widely studied currency exchange rates between US Dollar (USD) and other four currencies i.e. Australian Dollar (AUD), Swiss Franc (CHF), Mexican Peso (MXN), Brazilian Real (BRL), along with S&P 500 and Nikkei 225 stock market data are used for performance validation of the newly proposed LRNFIS.

Analysis of Voltage Stability in Radial Distribution System for Hybrid Microgrid

The hybrid microgrid is growing in India for rural electrification due to potential benefits in providing shape, reliable and sustainable electricity from renewable energy resources. As we know, the renewable energy resources are depending on nature and on the other hand, the loads on microgrid are variable. Due to instability in generation and load, voltage instability problem occurs. In this paper, we are discussing voltage stability by radial distribution network in microgrid with computational recursive method and implementing load flow analysis on 10-node system with simulation approach for voltage stability index (VSI). The critical node in microgrid is identifying with help of VSI.

Implementation of hybrid isolated microgrid for village electrification

The government of India introduce many programs for village electrification, as more than 70% of Indian population are living in the villages. Today villages are the major stockholder for economic growth of India. The major challenges for village electrification are grid connectivity and reliability of grid for providing un-power supply 24/7 to each household. In this paper, we are discussing the implementation of Hybrid isolated microgrid based on Bio-mass and Solar. The availability of Bio-mass is more feasible from animal wastage, agricultural wastage and as well as food wastage. These all wastage are used as a fuel for Bio-mass power plant for electrical generation. The Bio-mass plant is integrated with solar power plant to fulfil the 24/7 demand. In this, we are discussing basic model of isolated microgrid along with economical parameters for each house electrification in village.The government of India introduce many programs for village electrification, as more than 70% of Indian population are living in the villages. Today villages are the major stockholder for economic growth of India. The major challenges for village electrification are grid connectivity and reliability of grid for providing un-power supply 24/7 to each household. In this paper, we are discussing the implementation of Hybrid isolated microgrid based on Bio-mass and Solar. The availability of Bio-mass is more feasible from animal wastage, agricultural wastage and as well as food wastage. These all wastage are used as a fuel for Bio-mass power plant for electrical generation. The Bio-mass plant is integrated with solar power plant to fulfil the 24/7 demand. In this, we are discussing basic model of isolated microgrid along with economical parameters for each house electrification in village.

A study on economic power dispatch grid connected PV power plant in educational institutes

India has main concerns on environment and escalation of fuel prices with respect to diminution of fossil fuel reserves and the major focus on renewable Energy sources for power generation to fulfill the present and future energy demand. Installation of PV power plants in the Educational Institutions has grown up drastically throughout India. More PV power plant are integrated with load and grid through net metering. Therefore, this paper is an analysis of the 75kWp PV plant at chosen buses, considering the need of minimum demand from the grid. The case study is carried out for different generation level throughout the day and year w.r.t load and climate changes, load sharing on grid. The economic dispatch model developed for PV plant integrated with Grid.India has main concerns on environment and escalation of fuel prices with respect to diminution of fossil fuel reserves and the major focus on renewable Energy sources for power generation to fulfill the present and future energy demand. Installation of PV power plants in the Educational Institutions has grown up drastically throughout India. More PV power plant are integrated with load and grid through net metering. Therefore, this paper is an analysis of the 75kWp PV plant at chosen buses, considering the need of minimum demand from the grid. The case study is carried out for different generation level throughout the day and year w.r.t load and climate changes, load sharing on grid. The economic dispatch model developed for PV plant integrated with Grid.

Study on design and performance analysis of low noise high speed amplifier

Low noise amplifier is the front end block of radio-frequency receiver system. The design concept demonstrates the design trade-off with noise figure, power gain, power consumption and impedance matching. This paper, investigates the cascade LNA design using ladder matching network. The frequency range for the design ranges from 2GHz to 7GHz. The lump reactive element has been used as the input and the T-matching network as output terminal for the proposed LNA. The cascade low noise amplifier has a measured forward gain 19.23 dB and noise figure 1.03dB. The proposed LNA is designed using open source software OSCAD and implemented in TSMC 0.18 μm CMOS technology. This work is mainly proposed for IEEE 802.16 applications.