scispace - formally typeset
Search or ask a question
Author

K. Manivannan

Bio: K. Manivannan is an academic researcher from VIT University. The author has contributed to research in topics: Link adaptation & Feature extraction. The author has an hindex of 8, co-authored 28 publications receiving 280 citations. Previous affiliations of K. Manivannan include Pondicherry Engineering College & Indian Institute of Technology Madras.

Papers
More filters
Journal ArticleDOI
14 Jul 2003
TL;DR: In this article, a neural-based Tabu Search (NBTS) method is used to solve the short-term unit commitment problem (UCP) using a flexible memory system, which has the ability to avoid entrapment in local minima.
Abstract: An approach to solving the short-term unit commitment problem (UCP) using a neural-based tabu search (NBTS) is presented. The solution of the unit commitment problem is a complex optimisation problem. The exact solution of the UCP can be obtained by a complete enumeration of all feasible combinations of generating units, which could be a huge number. The unit commitment has commonly been formulated as a nonlinear, large-scale, mixed-integer combinational optimisation problem. The objective is to find the generation scheduling such that the total operating cost can be minimised, when subjected to a variety of constraints. This also means that it is desirable to find the optimal generating unit commitment in the power system for the next H hours. Tabu search is a powerful optimisation procedure that has been successfully applied to a number of combinatorial optimisation problems. It has the ability to avoid entrapment in local minima by employing a flexible memory system. The neural network combines good solution quality for tabu search with rapid convergence for an artificial neural network. The neural based tabu search method is used to find the unit commitment. By doing so, it gives the optimum solution rapidly and efficiently. The Neyveli Thermal Power Station (NTPS) Unit – II in India has been considered as a case study and extensive studies have also been performed for different power systems consisting of 10, 26, and 34 generating units. The data collected has been used for implementation in the above methods. Numerical results are shown, comparing the cost solutions and computation time obtained by using the intelligent techniques with the conventional methods like dynamic programming and Lagrangian relaxation to reach proper unit commitment.

59 citations

Proceedings ArticleDOI
17 Apr 2002
TL;DR: In this paper, a new approach to solve short-term unit commitment problem (UCP) using Neural Based Tabu Search (NBTS) is presented, where the objective is to find the generation scheduling such that the total operating cost can be minimized, when subjected to a variety of constraints.
Abstract: This paper presents a new approach to solve short-term unit commitment problem (UCP) using Neural Based Tabu Search (NBTS). The solution of the unit commitment problem is a complex optimization problem. The exact solution of the UCP can be obtained by a complete enumeration of all feasible combinations of generating units, which could be very huge number. The unit commitment has commonly been formulated as a nonlinear, large scale, mixed-integer combinational optimization problem. The objective of this paper is to find the generation scheduling such that the total operating cost can be minimized, when subjected to a variety of constraints. This also means that it is desirable to find the optimal generating unit commitment in the power system for next H hours. Neyveli Thermal Power Station II in India, demonstrates the effectiveness of the proposed approach. Numerical results are shown to compare the superiority of the cost solutions obtained using the Tabu Search (TS) method in reaching proper unit commitment.

45 citations

Journal ArticleDOI
TL;DR: A new intelligent methodology in bearing condition diagnosis analysis has been proposed to predict the status of rolling bearing based on vibration signals by multi class support vector machine (MSVM), a classification algorithm.
Abstract: A new intelligent methodology in bearing condition diagnosis analysis has been proposed to predict the status of rolling bearing based on vibration signals by multi class support vector machine (MSVM), a classification algorithm Wavelet packet transform (WPT) is used for signal processing and standard statistical feature extraction process Feature reduction is a method used to deselect the irrelevant features acquired from the large dataset Recent survey shows feature reduction is used widely in the field of machine learning to discover the knowledge with reduced features Rough set is hybridized with particle swarm optimization (PSO), an population based stochastic optimization technique, to reduce the features The efficiency of classification algorithm is compared based on their classification accuracy before and after feature reduction Four states of bearing health conditions such as normal, defective inner race, defective outer race and defective ball conditions are simulated and used in this proposed work

42 citations

Journal ArticleDOI
TL;DR: An algorithm called as rough k means clustering algorithm for segmentation, which is applying an oppositional fruit fly algorithm to develop an effectiveness of the Gabor filter, is introduced.
Abstract: From the classifications, an effective brain tumor classification and segmentation is the curious part for identifying the tumor and non-tumor cells in brain and the cell levels are evaluated. The brain tumor segmentation and classification is established on their experiences. The accuracy of tumor segmentation is very crucial to diagnosis accuracy. So, in our work we are align and improve an approach for tumor identification applying brain MR image segmentation. With an efficient, accurate and reproducible manner, the aim of our suggested method is to evaluate the tumor. Then the brain tumor is separated by using the effective techniques. For segmentation process, first the MRI image must be preprocessed. Next, the process of feature extraction is done by using preprocessed images. In feature extraction process, a raised Gabor wavelet transform (IGWT) is applied. In this research, the means of optimization technique is changed from the traditional Gabor wavelet transform. And the effectiveness of that optimization technique is aligned by using an oppositional fruit fly algorithm. At the end of the process, feature values are transferred in to the clustering process for segmentation. In this article we are introduced an algorithm called as rough k means clustering algorithm for segmentation. Here, we are applying an oppositional fruit fly algorithm to develop an effectiveness of the Gabor filter. Further to raise the classification accuracy of brain tumor we are introduced a multi kernel support vector machine algorithm.

40 citations

Proceedings ArticleDOI
01 Jan 2007
TL;DR: In this paper, the BER and Pe are estimated using Effective Exponential SIR Mapping (EESM) mapping using mathematical model developed for BPSK under AWGN channel.
Abstract: Multicarrier communication systems with adaptive modulation and coding systems such as OFDM are well suited for high speed and mobility oriented networks like mobile WIMAX that has to support users in different fading and mobility conditions. The channel estimation and link prediction are worked out at different levels. These estimators and predictors are normally examined using complex emulators and simulators. It is very difficult to predict the performance of different links with same SNR. There is a need to design simple link performance predictors. In this paper the BER and Pe are estimated using Effective Exponential SIR Mapping. This method is proved better than conventional methods used for prediction. The results are showed to be within the boundary conditions defined by chernoff union bound. The bound was developed for EESM mapping using mathematical model developed for BPSK under AWGN channel. The results are showed for different modulations order and different channel realizations.

28 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: In this article, a bibliographical survey, mathematical formulations, and general backgrounds of research and developments in the field of modern unit commitment (UC) problem for past 35 years based on more than 150 published articles.
Abstract: With the fast-paced changing technologies in the power industry, new power references addressing new technologies are coming to the market. So there is an urgent need to keep track of international experiences and activities taking place in the field of modern unit-commitment (UC) problem. This paper gives a bibliographical survey, mathematical formulations, and general backgrounds of research and developments in the field of UC problem for past 35 years based on more than 150 published articles. The collected literature has been divided into many sections, so that new researchers do not face any difficulty in carrying out research in the area of next-generation UC problem under both the regulated and deregulated power industry.

898 citations

Proceedings ArticleDOI
16 May 2010
TL;DR: A MATLAB computationally efficient LTE system level simulator capable of evaluating the performance of the Downlink Shared Channel of LTE SISO and MIMO networks using Open Loop Spatial Multiplexing and Transmission Diversity transmit modes is presented.
Abstract: In order to evaluate the performance of new mobile network technologies, system level simulations are crucial. They aim at determining whether, and at which level predicted link level gains impact network performance. In this paper we present a MATLAB computationally efficient LTE system level simulator. The simulator is offered for free under an academic, noncommercial use license, a first to the authors' knowledge. The simulator is capable of evaluating the performance of the Downlink Shared Channel of LTE SISO and MIMO networks using Open Loop Spatial Multiplexing and Transmission Diversity transmit modes. The physical layer model is based on the postequalization SINR and provides the simulation pre-calculated "fading parameters" representing each of the individual interference terms. This structure allows the fading parameters to be pregenerated offline, vastly reducing computational complexity at run-time.

578 citations

Proceedings ArticleDOI
24 Aug 2009
TL;DR: This paper presents a MATLAB-based downlink physical-layer simulator for LTE that can efficiently be executed on multi-core processors to significantly reduce the simulation time.
Abstract: Research and development of signal processing algorithms for UMTS Long Term Evolution (LTE) requires a realistic, flexible, and standard-compliant simulation environment. To facilitate comparisons with work of other research groups such a simulation environment should ideally be publicly available. In this paper, we present a MATLAB-based downlink physical-layer simulator for LTE. We identify different research applications that are covered by our simulator. Depending on the research focus, the simulator offers to carry out single-downlink, single-cell multi-user, and multi-cell multi-user simulations. By utilizing the Parallel Computing Toolbox of MATLAB, the simulator can efficiently be executed on multi-core processors to significantly reduce the simulation time.

515 citations

Journal ArticleDOI
TL;DR: This research paper presents solution to single-area unit commitment problem for 14-bus system, 30- bus system and 10-generating unit model using swarm-intelligence-based particle swarm optimization algorithm and a hybrid PSO–GWO algorithm.
Abstract: Particle swarm optimization algorithm is a inhabitant-based stochastic search procedure, which provides a populace-based search practice for getting the best solution from the problem by taking particles and moving them around in the search space and efficient for global search. Grey Wolf Optimizer is a recently developed meta-heuristic search algorithm inspired by Canis-lupus. This research paper presents solution to single-area unit commitment problem for 14-bus system, 30-bus system and 10-generating unit model using swarm-intelligence-based particle swarm optimization algorithm and a hybrid PSO---GWO algorithm. The effectiveness of proposed algorithms is compared with classical PSO, PSOLR, HPSO, hybrid PSOSQP, MPSO, IBPSO, LCA---PSO and various other evolutionary algorithms, and it is found that performance of NPSO is faster than classical PSO. However, generation cost of hybrid PSO---GWO is better than classical and novel PSO, but convergence of hybrid PSO---GWO is much slower than NPSO due to sequential computation of PSO and GWO.

157 citations