Due to the rise and rapid growth of E-Commerce, use of credit cards for online purchases has dramatically increased and it caused an explosion in the credit card fraud. As credit card becomes the most popular mode of payment for both online as well as regular purchase, cases of fraud associated with it are also rising. In real life, fraudulent transactions are scattered with genuine transactions and simple pattern matching techniques are not often sufficient to detect those frauds accurately. Implementation of efficient fraud detection systems has thus become imperative for all credit card issuing banks to minimize their losses. Many modern techniques based on Artificial Intelligence, Data mining, Fuzzy logic, Machine learning, Sequence Alignment, Genetic Programming etc., has evolved in detecting various credit card fraudulent transactions. A clear understanding on all these approaches will certainly lead to an efficient credit card fraud detection system. This paper presents a survey of various techniques used in credit card fraud detection mechanisms and evaluates each methodology based on certain design criteria.
This article proposes a new meta-heuristic optimization algorithm named grey wolf optimization algorithm based on leadership and hunting behavior of grey wolf for the reactive power planning of a connected power network. The performance of the proposed opposition-based grey wolf optimization (OGWO) and grey wolf optimization (GWO) is examined and tested successfully in standard IEEE 14, IEEE 30, and IEEE 57 bus test systems for the minimization of active power loss and the total operating cost while maintaining voltage profile of the buses within permissible limit. Active power loss and total operating cost are minimized by optimal planning of the reactive generation of generators, transformer tap setting arrangements, and reactive output of shunt capacitors as installed at weak nodes under different loading conditions. The weak nodes are detected by power flow analysis. The results obtained by GWO algorithm is compared to other popular techniques recently reported in recent state-ofthe-art literature. It is observed that proposed OGWO and GWO algorithm yields much better result in terms of reducing operating cost and minimizing active power loss. Merit lies with GWO is that its simple structure for implementation and its ability not to be trapped in local minima, thus exploring wider search area.KEYWORDS active power loss, grey wolf optimization, operating cost, opposition based learning, reactive power planning 1 | INTRODUCTION Reactive power planning (RPP) problem is considered as one of the challenging problem, as it has to minimize active power loss and total operating cost of a connected power network while maintaining healthy voltage profile throughout the power network. The above criteria can only be met by proper coordination of all reactive power sources existing in the system that ultimately helps in maintaining healthy voltage profile along the entire network. Hence, RPP is the proper coordination of control variables, ie, reactive power generation of the generators, transformer tap positions, and shunt capacitors, that minimizes real power loss and operating cost while satisfying system constraints. This RPP problem or the problem of reactive power optimization has been considered as a research topic for the power system engineers. Real power loss has been minimized by controlling reactive power in Ei-Sayed et al. 1 Linear programming method has been used in Iba et al 2 for RPP. Deeb and Shahidehpour 3 have tried to reduce real power loss and improve voltage profile using decomposition approach. Chiang et al 4,5 have used simulated annealing technique to determine
Power system instability primarily results from the deviation of the frequency from its predefined rated value. This deviation causes voltage collapse, which further leads to sudden blackouts of the power system network. It is often triggered by a lack of reactive capacity. The solution to the reactive capacity problem can be obtained in two stages. In the first stage, the vulnerable buses, also known as ‘weak buses’, where voltage failure might occur are identified, and the Var compensating devices are mounted at those locations. The proposed approach utilizes three simple vulnerable bus detection methods: the fast voltage stability index, line stability index, and voltage collapse proximity index (VCPI). In the second stage, various optimization algorithms are implemented to determine the optimal setting of Var sources, such as particle swarm optimization, differential evolution, the whale optimization algorithm, the grasshopper optimization algorithm, the salp swarm algorithm, grey wolf optimization, and oppositional grey wolf optimization (OGWO). The results indicate that the best approach to poor bus recognition is the VCPI, and the OGWO technique provides a much less expensive system than other optimization strategies used for problems of optimal reactive power planning.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.