Browsing by Author "Mishra S.K."

Now showing 1 - 8 of 8

A comparative performance assessment of a set of multiobjective algorithms for constrained portfolio assets selection
(2014) Mishra S.K.; Panda G.; Majhi R.
This paper addresses a realistic portfolio assets selection problem as a multiobjective optimization one, considering the budget, floor, ceiling and cardinality as constraints. A novel multiobjective optimization algorithm, namely the non-dominated sorting multiobjective particle swarm optimization (NS-MOPSO), has been proposed and employed efficiently to solve this important problem. The performance of the proposed algorithm is compared with four multiobjective evolution algorithms (MOEAs), based on non-dominated sorting, and one MOEA algorithm based on decomposition (MOEA/D). The performance results obtained from the study are also compared with those of single objective evolutionary algorithms, such as the genetic algorithm (GA), tabu search (TS), simulated annealing (SA) and particle swarm optimization (PSO). The comparisons of the performance include three error measures, four performance metrics, the Pareto front and computational time. A nonparametric statistical analysis, using the Sign test and Wilcoxon signed rank test, is also performed, to demonstrate the superiority of the NS-MOPSO algorithm. On examining the performance metrics, it is observed that the proposed NS-MOPSO approach is capable of identifying good Pareto solutions, maintaining adequate diversity. The proposed algorithm is also applied to different cardinality constraint conditions, for six different market indices, such as the Hang-Seng in Hong Kong, DAX 100 in Germany, FTSE 100 in UK, S&P 100 in USA, Nikkei 225 in Japan, and BSE-500 in India. � 2014 Elsevier B.V.
Comparative performance evaluation of multiobjective optimization algorithms for portfolio management
(2009) Mishra S.K.; Meher S.; Panda G.; Panda A.
The objective of portfolio optimization is to find an optimal set of assets to invest on
Constrained portfolio asset selection using multiobjective bacteria foraging optimization
(2014) Mishra S.K.; Panda G.; Majhi R.
Portfolio asset selection (PAS) is a challenging and interesting multiobjective task in the field of computational finance, and is receiving the increasing attention of researchers, fund management companies and individual investors in the last few decades. Selecting a subset of assets and corresponding optimal weights from a set of available assets, is a key issue in the PAS problem. A Markowitz model is generally used to solve this optimization problem, where the total profit is maximized, while the total risk is to be minimized. However, this model does not consider the practical constraints, such as the minimum buy in threshold, maximum limit, cardinality etc. The Practical constraints are incorporated in this study to meet a real world financial scenario. In the proposed work, the PAS problem is formulated in a multiobjective framework, and solved using the multiobjective bacteria foraging optimization (MOBFO) algorithm. The performance of the proposed approach is compared with a set of competitive multiobjective evolutionary algorithms using six performance metrics, the Pareto front and computational time. On examining the performance metrics, it is concluded that the proposed MOBFO algorithm is capable of identifying a good Pareto solution, maintaining adequate diversity. The proposed algorithm is also successfully applied to different cardinality constraint conditions, for six different market indices. � 2013 Springer-Verlag Berlin Heidelberg.
A coordinated planning framework of electric power distribution system: Intelligent reconfiguration
(2018) Kumar D.; Singh A.; Mishra S.K.; Jha R.C.; Samantaray S.R.
This paper has proposed a comprehensive coordinated planning framework for solving the network reconfiguration with simultaneous installation of distribution generation (DG) units, with an objective of minimizing the feeder power loss and boosting the voltage profile of the electric distribution system. A meta-heuristic bit-shift operator�based particle-swarm-optimization (PSO) technique has been used for simultaneous reconfiguration with the optimal siting and sizing of the DG units. The bit-shift operator�based PSO has been obtained by incorporating a shift operator in the velocity equation of the basic PSO, such that the problem moves in the direction of finding the best optimal reconfigured system. The entire problem has been investigated in the light of both voltage independent and dependent loads, such as residential, industrial, and commercial, to evaluate the performance of the proposed work in a practical scenario. A sensitivity analysis has been applied for finding the optimal location for the DG placement. The efficacy and validation of the proposed method have been tested on a standard IEEE test system under 4 different load models for 5 different cases. Copyright � 2018 John Wiley & Sons, Ltd.
Fast discrete S-transform based differential relaying scheme for UPFC compensated parallel line
(2015) Tripathy L.N.; Samantaray S.R.; Jena M.K.; Mishra S.K.
This paper presents a new differential relaying scheme for a parallel transmission line in presence of Unified Power Flow Controller (UPFC). In this work, a new algorithm is proposed to detect and classify the fault along with to identify the faulty section with respect to UPFC location. The UPFC is placed at midpoint of the one of the transmission line. The scheme starts by retrieving the three phase currents signals at both ends of the transmission line synchronously and processing it though Fast Discrete S- transform to derive the spectral energy of the current signals. The differential spectral energy of current signals (i.e spectral energy of current measured at sending end minus spectral energy of current measured at receiving end) of respective phases of transmission lines is used to register the fault pattern. The proposed algorithm is very simple and accurate for fault detection and classification in double-circuit transmission lines including UPFC in one of the line. The scheme has been extensively tested on different faulted conditions with wide variations in operating parameters of the UPFC as well as transmission line and the test results indicate the effectiveness of this scheme. � 2015 IEEE.
Improved portfolio optimization combining multiobjective evolutionary computing algorithm and prediction strategy
(2012) Mishra S.K.; Panda G.; Majhi B.; Majhi R.
In conventional mean-variance model of portfolio optimization problem the expected return is taken as the mean of the past returns. This assumption is not correct and hence the method leads to poor portfolio optimization performance. Hence an alternative but efficient method is proposed in which the mean and variance of expected return are first predicted with a low complexity functional link artificial neural network model (FLANN). The predicted values of mean and variance are consequently used in multi objective swarm intelligence techniques for achieving better performance. The multi objective swarm intelligence techniques chosen are non-dominated sorting genetic algorithm-II (NSGA - II) and multi objective particle swarm optimization (MOPSO).The performance of the proposed prediction based portfolio optimization model has been compared with the Markowitz mean-variance model. The comparison of the performance includes three performance metrics, Pareto front and nonparametric statistical test using the Sign test. On examining the performance metrics it is observed that the proposed prediction based portfolio optimization model approach provided improved Pareto solutions but maintaining adequate diversity. � 2012 Newswood Limited. All rights reserved.
Portfolio management assessment by four multiobjective optimization algorithm
(2011) Mishra S.K.; Panda G.; Meher S.; Majhi R.; Singh M.
The portfolio optimization aims to find an optimal set of assets to invest on, as well as the optimal investment for each asset. This optimal selection and weighting of assets is a multi-objective problem where total profit of investment has to be maximized and total risk is to be minimized. In this paper four well known multi-objective evolutionary algorithms i.e. Pareto Archived Evolution Strategy (PAES), Pareto Envelope-based Selection Algorithm (PESA), Adaptive Pareto Archived Evolution Strategy (APAES) algorithm and Non dominated Sorting Genetic Algorithm II (NSGA II) are chosen and successfully applied for solving the biobjective portfolio optimization problem. Their performances have been evaluated through simulation study and have been compared in terms of Pareto fronts, the delta, C and S metrics. Simulation results of various portfolios clearly demonstrate the superior portfolio management capability of NSGA II based method compared to other three standard methods. Finally NSGA II algorithm is applied to the same problem with some real world constraint. � 2011 IEEE.
Prediction based mean-variance model for constrained portfolio assets selection using multiobjective evolutionary algorithms
(2016) Mishra S.K.; Panda G.; Majhi B.
In this paper, a novel prediction based mean-variance (PBMV) model has been proposed, as an alternative to the conventional Markowitz mean-variance model, to solve the constrained portfolio optimization problem. In the Markowitz mean-variance model, the expected future return is taken as the mean of the past returns, which is incorrect. In the proposed model, first the expected future returns are predicted, using a low complexity heuristic functional link artificial neural network (HFLANN) model and the portfolio optimization task is carried out by using multi-objective evolutionary algorithms (MOEAs). In this paper, swarm intelligence based, multiobjective optimization algorithm, namely self-regulating multiobjective particle swarm optimization (SR-MOPSO) has also been proposed and employed efficiently to solve this important problem. The Pareto solutions obtained by applying two other competitive MOEAs and using the proposed PBMV models and Markowitz mean-variance model have been compared, considering six performance metrics and the Pareto fronts. Moreover, in the present study, the nonparametric statistical analysis using the Sign test and Wilcoxon rank test are also carried out, to compare the performance of the algorithms pair wise. It is observed that, the proposed PBMV model based approach provides better Pareto solutions, maintaining adequate diversity, and also quite comparable to the Markowitz model. From the simulation result, it is observed that the self regulating multiobjective particle swarm optimization (SR-MOPSO) algorithm based on PBMV model, provides the best Pareto solutions amongst those offered by other MOEAs. � 2016 Elsevier B.V.