Application Of Flower Pollination Algorithm Research Articles

Optimized Tuned Deep Learning Model for Chronic Kidney Disease Classification

In recent times, Internet of Things (IoT) and Cloud Computing (CC) paradigms are commonly employed in different healthcare applications. IoT gadgets generate huge volumes of patient data in healthcare domain, which can be examined on cloud over the available storage and computation resources in mobile gadgets. Chronic Kidney Disease (CKD) is one of the deadliest diseases that has high mortality rate across the globe. The current research work presents a novel IoT and cloud-based CKD diagnosis model called Flower Pollination Algorithm (FPA)-based Deep Neural Network (DNN) model abbreviated as FPA-DNN. The steps involved in the presented FPA-DNN model are data collection, preprocessing, Feature Selection (FS), and classification. Primarily, the IoT gadgets are utilized in the collection of a patient’s health information. The proposed FPA-DNN model deploys Oppositional Crow Search (OCS) algorithm for FS, which selects the optimal subset of features from the preprocessed data. The application of FPA helps in tuning the DNN parameters for better classification performance. The simulation analysis of the proposed FPA-DNN model was performed against the benchmark CKD dataset. The results were examined under different aspects. The simulation outcomes established the superior performance of FPA-DNN technique by achieving the highest sensitivity of 98.80%, specificity of 98.66%, accuracy of 98.75%, F-score of 99%, and kappa of 97.33%.

Maiden application of flower pollination algorithm based tilt integral derivative controller with filter for control of electric machines

In this article we design tilt integral derivative controller with filter (TIDNC) for D.C Motor speed control. TIDN parameters are tuned by using flower pollinating algorithm (FPA). By using tuning parameters of TIDNC, we obtain desired step response. Thereafter comparative analysis is carried out with FPA based proportional integral derivative controller (PIDC), fractional order PIDC (FOPIDC) and tilt integral derivative controller (TIDC) in terms of desired step response and performance indices (PIs) like integral of square error (ISE), integral of time weighted absolute error (ITAE), integral of time weighted square error (ITSE) and integral of absolute error (IAE). After that, response of a D.C Motor with FPA is compared with other metaheuristic algorithms like particle swarm optimization (PSO) and firefly algorithms (FA).

Application of Flower Pollination Algorithm for Optimally Tuning Zeigler Nichols Parameters for PID Controller to Enhance Transient Stability through SVC

With the evolution of electrical networks, the complexity and non linearity of modern power systems has enhanced exponentially. In order to reduce these potentially harmful oscillations, power system stabilizers (PSS) are introduced in generators of modern power systems. The PSS brings the system back to a stable and balanced state and re-establishes the pre-fault performance of the system after removal of disturbance and restoration of line. However utilization of PSS in certain cases of increased transmission line loading and other significant faults is not very effective and is rather time consuming. These days to acquire better control and quality of power, FACTS devices are being commonly used in large power systems. When SVC, a versatile FACTS device is used simultaneously with PSS, there is not only improvement in power transfer capability and controllability but also a distinct enhancement in power system stability. In order to increase the performance of the conventional PID controller of the PSS, it is tuned with a very simple and quick tuning method called Zeigler Nichols (ZN) which provides very fast elimination to disturbances in power system. However the conventional and ZN based PID controllers are confined only to linear control of power system. To further enhance the dynamic tuning process in order to obtain much faster and better transient as well as dynamic stability, a very adaptable and robust nature inspired technique of Flower Pollination Algorithm (FPA) is used to tune the ZN based PID controller. To realise the system transient stability for the conventional and proposed method, root locus and total harmonic distortion techniques have been adopted. The results ultimately reveal the efficacy and productiveness of FP based ZN- PID in successfully damping out inter area oscillations thus reducing the harmonics and improving overall stability in power systems as compared to other tuning methods.

Application of flower pollination algorithm for enhanced proton exchange membrane fuel cell modelling

Modelling of Proton Exchange Membrane Fuel Cell (PEMFC) characteristics assumes importance in view of better understanding, analysis and design of high efficient fuel cell systems. Limited by its complexity, strongly coupled behaviour and multivariate characteristics; optimization techniques are attempted to model PEMFC characteristics. Influenced by convergence speed, computational efficiency, level of complexity, dependency on initial solution and ability to locate global optimum; recently evolved Flower Pollination Algorithm is utilized in this work for PEMFC modelling. This method is applied to derive unknown model parameters of fuel cells having different characteristics and rating. Further, to illustrate the superiority of the method, results obtained are compared with some of the recent works. Moreover, to showcase its efficiency; comprehensive comparison is made in terms of model parameter values, sum of squared error, individual absolute error and relative error values.

Rescheduling of Generators with Pumped Hydro Storage Units to Relieve Congestion Incorporating Flower Pollination Optimization

In this paper, a Flower Pollination Algorithm (FPA) has been proposed for relieving congestion in the deregulated power electricity industry. Congestion in the power market is one the contemplative challenges to be overcome in the era of deregulation. The primary cause of congestion is due to the loss of the transmission line, an increase in load, or loss of generator(s). Hence, managing congestion is one of the issues which have to be tackled in the present scenario. There are several techniques to relieve congestion. It is quite well-known that the thermal limits of transmission lines in a power system are fixed. One of the methods to abate congestion is to reschedule the real power of the generators. The purpose of the present work is to benefit the Independent System Operator (ISO) in reliving congestion. (1) In order to meet this objective effectively, a FPA algorithm has been proposed for relieving congestion and is simulated on a modified IEEE 30-bus system initially. (2) Congestion cost, compared with and without the application of FPA, is computed. (3) To validate its effectiveness, the obtained results are compared with recent power system optimization algorithms present in the literature. (4) Further, the work has been extended with the incorporation of a Pumped Hydro Storage Unit (PHSU). Here an economic analysis of congestion cost reduction employing FPA before and after the incorporation of PHSU is investigated applying FPA. In comparison with other evolutionary algorithms, the uniqueness of generating a new population is attained in FPA by the levy flight procedure. It is one of the latest evolved algorithms and is suited for different power system problem due to fewer clear-cut tuning parameters in contrast with other algorithms. (5) Furthermore, the effects of other network parameters, including system losses and voltage, has been computed. The result obtained is tested in terms of congestion mitigation with and without the incorporation of PHSU, in terms of novel objective improvement, and with and without applying recently evolving FPA for the above application. Thus the objective-wise and algorithmic-wise innovative concept has been presented. This proves effectiveness of the algorithm in terms of minimized cost convergence and other parameter including system losses and voltage before and after the incorporation of PHSU as compared with other recent trendsetting reported optimization techniques.

Review of modified and hybrid flower pollination algorithms for solving optimization problems

Flower pollination algorithm (FPA) is a nature-inspired meta-heuristics to handle a large scale optimization process. This paper reviews the previous studies on the application of FPA, modified FPA and hybrid FPA for solving optimization problems. The effectiveness of FPA for solving the optimization problems are highlighted and discussed. The improvement aspects include local and global search strategies and the quality of the solutions. The measured enhancements in FPA are based on various research domains. The results of review indicate the capability of the enhanced and hybrid FPA for solving optimization problems in variety of applications and outperformed the results of other established optimization techniques.

Assembly sequence optimization using a flower pollination algorithm-based approach

One of the important decisions in assembly process planning is determination of assembly sequence. Choice of the optimum sequence is made difficult due to various reasons. There are various precedence constraints and optimization criteria. Moreover, a product may be possible to assemble in many alternative ways following different sequences, thus making assembly sequence optimization a multi-modal optimization problem with multiple optimum solutions. It is necessary to generate as many unique optimum solutions as possible in order to allow the process planner to take a decision. Moreover, with increase in part count, the number of feasible sequences rises staggeringly, thereby making assembly sequence optimization laborious and time consuming. Most conventional mathematical algorithms are known to perform poorly when used to obtain multiple optimum solutions. On the other hand, soft computing based evolutionary optimization algorithms are good candidates for multi-modal optimization. Another challenge is to develop an algorithm that can automatically maintain diversity in the optimum solutions found over the generations (i.e. optimum solutions having the same fitness but unique). Keeping the above in mind, in the present paper, an intelligent assembly sequence optimization methodology based on application of flower pollination algorithm (FPA) has been developed to automatically generate multiple unique optimal assembly sequences, subject to various precedence constraints, based on minimisation of number of orientation changes and tool changes. Since in the present paper, FPA has been applied for the first time to a discrete optimization problem like assembly sequence optimization, the main challenge before us in applying FPA was the continuous nature of the original FPA. Therefore, modifications have been made by us in the rules for local and global pollination of FPA to make it suited for solving the given discrete optimization problem. In order to evaluate the performance of FPA, the results have been compared with two other well-known soft computing techniques namely, Genetic Algorithm (GA) and Ant Colony Optimization (ACO) and also with a recently published soft computing based algorithm, Improved Harmony Search (IHS). It was found that the novelty of the proposed FPA lies in its capability to find multiple unique optimum solutions in one single simulation run and capability to automatically maintain diversity in the optimum solutions found over the generations. On the other hand, in case of GA, ACO and IHS, it is not possible to maintain the diversity in multiple optimum solutions as the complete population finally converges to a few unique optimum solutions. Therefore, it can be concluded that FPA performs better in solving the given multi-modal optimization problem of assembly sequence optimization.

Application of flower pollination algorithm in load frequency control of multi-area interconnected power system with nonlinearity

This work presents an application of bio-inspired flower pollination algorithm (FPA) for tuning proportional–integral–derivative (PID) controller in load frequency control (LFC) of multi-area interconnected power system. The investigated power system comprises of three equal thermal power systems with appropriate PID controller. The controller gain [proportional gain (K p), integral gain (K i) and derivative gain (K d)] values are tuned by using the FPA algorithm with one percent step load perturbation in area 1 (1 % SLP). The integral square error (ISE) is considered the objective function for the FPA. The supremacy performance of proposed algorithm for optimized PID controller is proved by comparing the results with genetic algorithm (GA) and particle swarm optimization (PSO)-based PID controller under the same investigated power system. In addition, the controller robustness is studied by considering appropriate generate rate constraint with nonlinearity in all areas. The result cumulative performance comparisons established that FPA-PID controller exhibit better performance compared to performances of GA-PID and PSO-PID controller-based power system with and without nonlinearity effect.

Application of flower pollination algorithm for optimal placement and sizing of distributed generation in Distribution systems

Distributed generator (DG) resources are small, self contained electric generating plants that can provide power to homes, businesses or industrial facilities in distribution feeders. By optimal placement of DG we can reduce power loss and improve the voltage profile. However, the values of DGs are largely dependent on their types, sizes and locations as they were installed in distribution feeders. The main contribution of the paper is to find the optimal locations of DG units and sizes. Index vector method is used for optimal DG locations. In this paper new optimization algorithm i.e. flower pollination algorithm is proposed to determine the optimal DG size. This paper uses three different types of DG units for compensation. The proposed methods have been tested on 15-bus, 34-bus, and 69-bus radial distribution systems. MATLAB, version 8.3 software is used for simulation.

An Application of Flower Pollination Algorithm to Solve Combined Economic Emission Dispatch by Considering Valve-Point Loading Effect

Flower Pollination Algorithm (FPA) is a new biologically inspired meta-heuristic optimization technique based the pollination process of flowers. FPA mimics the flower pollination characteristics in order to survival by the fittest. This paper presents implementation of FPA optimization in solving Combined Economic Emission Dispatch (CEED) problems in power system. CEED actually is a bi-objective problem where the objective of economic dispatch (ED) and emission dispatch (EMD) are combined into a single function by using price penalty factor. Hence, CEED is used to minimize the total generation cost by minimizing fuel cost and emission concurrently and at the same time determines the optimum power generation. In this paper, the valve point loading effect problem in power system also will be considered. The proposed algorithm are tested on four different test systems which are: 6-generating unit and 11-generating unit without valve point effect with no transmission loss, 10-generating unit with having valve point effect and transmission loss, and lastly 40-generating unit with having valve point effect without transmission loss. The results of these four different test cases were compared with the optimization techniques reported in recent literature in order to observe the effectiveness of FPA. Result shows FPA able to perform better than other algorithms by having minimum fuel cost and emission

Application of flower pollination algorithm to multi-objective environmental/economic dispatch

Environmental/economic dispatch is a fundamental issue in power system operations as it deals with the scheduling of the generating output among available units for simultaneous minimization of fuel cost and emission output, two objectives that collide. Furthermore the violation of specific constraints must be avoided. In this paper, environmental/economic dispatch is solved applying a new meta-heuristic optimization method, namely flower pollination algorithm. The proposed method is inspired by the pollination process of flowering plants with Lévy flight to imitate the movement of insect pollinators. The multi-objective environmental/economic dispatch problem can be described by polynomial objective functions and converted into single-objective using weighted sum method that produces non-dominated solutions. The most satisfactory solution is chosen according to a decision maker that is based on fuzzy set theory. Effectiveness of the proposed approach is examined on two test systems. The first system comprises three generating units while the second one is a six-unit system. Numerical results obtained are compared to those obtained by other modern optimization methods. The proposed flower pollination algorithm seems to be a promised optimization technique as it provides fast and efficient solutions.