Search results

The purpose of this paper is to deal with the economic requirements of power system loading dispatch and reduce the fuel cost of generation units. In order to optimize the scheduling of power load, an improved chicken swarm optimization (ICSO) is proposed to be adopted, for solving economic load dispatch (ELD) problem.

The ICSO increased the self-foraging factor to the chicks whose activities were the highest. And the evolutionary operations of chicks capturing the rooster food were increased. Therefore, these helped the ICSO to jump out of the local extreme traps and obtain the global optimal solution. In this study, the generation capacity of the generation unit is regarded as a variable, and the fuel cost is regarded as the objective function. The particle swarm optimization (PSO), chicken swarm optimization (CSO), and ICSO were used to optimize the fuel cost of three different test systems.

The result showed that the convergence speed, global search ability, and total fuel cost of the ICSO were better than those of PSO and CSO under different test systems. The non-linearity of the input and output of the generating unit satisfied the equality constraints; the average ratio of the optimal solution obtained by PSO, CSO, and ICSO was 1:0.999994:0.999988. The result also presented the equality and inequality constraints; the average ratio of the optimal solution was 1:0.997200:0.996033. The third test system took the non-linearity of the input and output of the generating unit that satisfied both equality and inequality constraints; the average ratio was 1:0.995968:0.993564.

This study realizes the whole fuel cost minimization in which various types of intelligent algorithms have been applied to the field of load economic scheduling. With the continuous evolution of intelligent algorithms, they save a lot of fuel cost for the ELD problem.

The ICSO is applied to solve the ELD problem. The quality of the optimal solution and the convergence speed of ICSO are better than that of CSO and PSO. Compared with PSO and CSO, ICSO can dispatch the generator more reasonably, thus saving the fuel cost. This will help the power sector to achieve greater economic benefits. Hence, the ICSO has good performance and significant effectiveness in solving the ELD problem.

The purpose of this paper is to focus on the cost-effective and environmentally sustainable operation of thermal power systems to allocate optimum active power generation resultant for a feasible solution in diverse load patterns using the grey wolf optimization (GWO) algorithm.

The economic dispatch problem is formulated as a bi-objective optimization subjected to several operational and practical constraints. A normalized price penalty factor approach is used to convert these objectives into a single one. The GWO algorithm is adopted as an optimization tool in which the exploration and exploitation process in search space is carried through encircling, hunting and attacking.

A linear interpolated price penalty model is developed based on simple analytical geometry equations that perfectly blend two non-commensurable objectives. The desired GWO algorithm reports a new optimum thermal generation schedule for a feasible solution for different operational strategies. These are better than the earlier reports regarding solution quality.

The proposed method seems to be a promising optimization tool for the utilities, thereby modifying their operating strategies to generate electricity at minimum energy cost and pollution levels. Thus, a strategic balance is derived among economic development, energy cost and environmental sustainability.

A single optimization tool is used in both quadratic and non-convex cost characteristics thermal modal. The GWO algorithm has discovered the best, cost-effective and environmentally sustainable generation dispatch.

The purpose of this paper is to develop an efficient brain tumor detection model using the beneficial concept of hybrid classification using magnetic resonance imaging (MRI) images Brain tumors are the most familiar and destructive disease, resulting to a very short life expectancy in their highest grade. The knowledge and the sudden progression in the area of brain imaging technologies have perpetually ready for an essential role in evaluating and concentrating the novel perceptions of brain anatomy and operations. The system of image processing has prevalent usage in the part of medical science for enhancing the early diagnosis and treatment phases.

The proposed detection model involves five main phases, namely, image pre-processing, tumor segmentation, feature extraction, third-level discrete wavelet transform (DWT) extraction and detection. Initially, the input MRI image is subjected to pre-processing using different steps called image scaling, entropy-based trilateral filtering and skull stripping. Image scaling is used to resize the image, entropy-based trilateral filtering extends to eradicate the noise from the digital image. Moreover, skull stripping is done by Otsu thresholding. Next to the pre-processing, tumor segmentation is performed by the fuzzy centroid-based region growing algorithm. Once the tumor is segmented from the input MRI image, feature extraction is done, which focuses on the first-order and higher-order statistical measures. In the detection side, a hybrid classifier with the merging of neural network (NN) and convolutional neural network (CNN) is adopted. Here, NN takes the first-order and higher-order statistical measures as input, whereas CNN takes the third level DWT image as input. As an improvement, the number of hidden neurons of both NN and CNN is optimized by a novel meta-heuristic algorithm called Crossover Operated Rooster-based Chicken Swarm Optimization (COR-CSO). The AND operation of outcomes obtained from both optimized NN and CNN categorizes the input image into two classes such as normal and abnormal. Finally, a valuable performance evaluation will prove that the performance of the proposed model is quite good over the entire existing model.

From the experimental results, the accuracy of the suggested COR-CSO-NN + CNN was seemed to be 18% superior to support vector machine, 11.3% superior to NN, 22.9% superior to deep belief network, 15.6% superior to CNN and 13.4% superior to NN + CNN, 11.3% superior to particle swarm optimization-NN + CNN, 9.2% superior to grey wolf optimization-NN + CNN, 5.3% superior to whale optimization algorithm-NN + CNN and 3.5% superior to CSO-NN + CNN. Finally, it was concluded that the suggested model is superior in detecting brain tumors effectively using MRI images.

This paper adopts the latest optimization algorithm called COR-CSO to detect brain tumors using NN and CNN. This is the first study that uses COR-CSO-based optimization for accurate brain tumor detection.

The innovation in big data is increasing day by day in such a way that the conventional software tools face several problems in managing the big data. Moreover, the occurrence of the imbalance data in the massive data sets is a major constraint to the research industry.

The purpose of the paper is to introduce a big data classification technique using the MapReduce framework based on an optimization algorithm. The big data classification is enabled using the MapReduce framework, which utilizes the proposed optimization algorithm, named chicken-based bacterial foraging (CBF) algorithm. The proposed algorithm is generated by integrating the bacterial foraging optimization (BFO) algorithm with the cat swarm optimization (CSO) algorithm. The proposed model executes the process in two stages, namely, training and testing phases. In the training phase, the big data that is produced from different distributed sources is subjected to parallel processing using the mappers in the mapper phase, which perform the preprocessing and feature selection based on the proposed CBF algorithm. The preprocessing step eliminates the redundant and inconsistent data, whereas the feature section step is done on the preprocessed data for extracting the significant features from the data, to provide improved classification accuracy. The selected features are fed into the reducer for data classification using the deep belief network (DBN) classifier, which is trained using the proposed CBF algorithm such that the data are classified into various classes, and finally, at the end of the training process, the individual reducers present the trained models. Thus, the incremental data are handled effectively based on the training model in the training phase. In the testing phase, the incremental data are taken and split into different subsets and fed into the different mappers for the classification. Each mapper contains a trained model which is obtained from the training phase. The trained model is utilized for classifying the incremental data. After classification, the output obtained from each mapper is fused and fed into the reducer for the classification.

The maximum accuracy and Jaccard coefficient are obtained using the epileptic seizure recognition database. The proposed CBF-DBN produces a maximal accuracy value of 91.129%, whereas the accuracy values of the existing neural network (NN), DBN, naive Bayes classifier-term frequency–inverse document frequency (NBC-TFIDF) are 82.894%, 86.184% and 86.512%, respectively. The Jaccard coefficient of the proposed CBF-DBN produces a maximal Jaccard coefficient value of 88.928%, whereas the Jaccard coefficient values of the existing NN, DBN, NBC-TFIDF are 75.891%, 79.850% and 81.103%, respectively.

In this paper, a big data classification method is proposed for categorizing massive data sets for meeting the constraints of huge data. The big data classification is performed on the MapReduce framework based on training and testing phases in such a way that the data are handled in parallel at the same time. In the training phase, the big data is obtained and partitioned into different subsets of data and fed into the mapper. In the mapper, the features extraction step is performed for extracting the significant features. The obtained features are subjected to the reducers for classifying the data using the obtained features. The DBN classifier is utilized for the classification wherein the DBN is trained using the proposed CBF algorithm. The trained model is obtained as an output after the classification. In the testing phase, the incremental data are considered for the classification. New data are first split into subsets and fed into the mapper for classification. The trained models obtained from the training phase are used for the classification. The classified results from each mapper are fused and fed into the reducer for the classification of big data.

This paper aims to study a parameter tuning method for the active disturbance rejection control (ADRC) to improve the anti-interference ability and position tracking of the performance of the servo system, and to ensure the stability and accuracy of practical applications.

This study proposes a parameter self-tuning method for ADRC based on an improved glowworm swarm optimization algorithm. The algorithm is improved by using sine and cosine local optimization operators and an adaptive mutation strategy. The improved algorithm is then used for parameter tuning of the ADRC to improve the anti-interference ability of the control system and ensure the accuracy of the controller parameters.

The authors designed an optimization model based on MATLAB, selected examples of simulation and experimental research and compared it with the standard glowworm swarm optimization algorithm, particle swarm algorithm and artificial bee colony algorithm. The results show that the response time of using the improved glowworm swarm optimization algorithm to optimize the auto-disturbance rejection control is short; there is no overshoot; the tracking process is relatively stable; the anti-interference ability is strong; and the optimization effect is better.

The innovation of this study is to improve the glowworm swarm optimization algorithm, propose a sine and cosine, local optimization operator, expand the firefly search space and introduce a new adaptive mutation strategy to adaptively adjust the mutation probability based on the fitness value, improve the global search ability of the algorithm and use the improved algorithm to adjust the parameters of the active disturbance rejection controller.

Notable energy losses and voltage deviation issues in low-voltage radial distribution systems are a major concern for power planners and utility companies because of the integration of electric vehicles (EVs). Electric vehicle charging stations (EVCSs) are the key components in the network where the EVs are equipped to energize their battery. The purpose of this paper is coordinating the EVCS and distributed generation (DG) so as to place them optimally using swarm-based elephant herding optimization techniques by considering energy losses, voltage sensitivity and branch current as key indices. The placement and sizing of the EVCS and DG were found in steps.

The IEEE 33-bus test feeder and 52-bus Indian practical radial networks were used as the test system for the network characteristic analysis. To enhance the system performance, the radial network is divided into zones for the placement of charging stations and dispersed generation units. Balanced coordination is discussed with three defined situations for the EVCS and DG.

The proposed analysis shows that DG collaboration with EVCS with suitable size and location in the network improves the performance in terms of stability and losses.

Stability and loss indices are handled with equal weight factor to find the best solution.

The proposed method is coordinating EVCS and DG in the existing system; the EV integration in the low-voltage side can be incorporated suitably. So, it has societal impact.

In this study, the proposed method shows improved results in terms EVCS and DG integration in the system with minimum losses and voltage sensitivity. The results have been compared with another population-based particle swarm optimization method (PSO). There is an improvement of 18% in terms of total power losses and 9% better result in minimum node voltage as compared to the PSO technique. Also, there is an enhancement of 33% in the defined voltage stability index which shows the proficiency of the proposed analysis.

This paper aims to propose a double-sided switched reluctance linxear generator (DSRLG) exclusively for wave power generation. The initial dimensions are given through design experience and principles. To ameliorate comprehensive performance of the DSRLG, the multi-objective optimization design is processed.

The multi-objective optimization design of the DSRLG is processed by adopting a modified entropy technique for order of preference by similarity to ideal solution (TOPSIS) algorithm. First, sensitivity analyzes on geometric parameters of the DSRLG are conducted to determine several pivotal geometric parameters as optimization variables. Then, the multi-objective optimization is conducted on the basis of initial dimensions. After determination of synthetical evaluation value of each structure parameter, the best dimension scheme of the DSRLG is concluded.

After verification by finite element method simulation and dynamic simulation, the final dimension scheme proves to perform better than the initial scheme. Finally, experiments are conducted to verify the accuracy of both the stable finite element DSRLG model and dynamic simulation system model so that the conclusion of this paper proves to be reliable and compelling.

This paper proposes an improved structure of the DSRLG, which is superior for wave power generation. Meanwhile, a novel modified entropy TOPSIS algorithm is applied to the field of electrical machine multi-objective optimal design for the first time.

The purpose of this paper is to improve energy efficiency and further reduction of side lobe level the algorithm proposed is firework algorithm. In this paper, roused by the eminent swarm conduct of firecrackers, a novel multitude insight calculation called fireworks algorithm (FA) is proposed for work enhancement. The FA is introduced and actualized by mimicking the blast procedure of firecrackers. In the FA, two blast (search) forms are utilized and systems for keeping decent variety of sparkles are likewise all around planned. To approve the presentation of the proposed FA, correlation tests were led on nine benchmark test capacities among the FA, the standard PSO (SPSO) and the clonal PSO (CPSO).

The antenna arrays are used to improve the capacity and spectral efficiency of wireless communication system. The latest communication systems use the antenna array technology to improve the spectral efficiency, fill rate and the energy efficiency of the communication system can be enhanced. One of the most important properties of antenna array is beam pattern. A directional main lobe with low side lobe level (SLL) of the beam pattern will reduce the interference and enhance the quality of communication. The classical methods for reducing the side lobe level are differential evolution algorithm and PSO algorithm. In this paper, roused by the eminent swarm conduct of firecrackers, a novel multitude insight calculation called fireworks algorithm (FA) is proposed for work enhancement. The FA is introduced and actualized by mimicking the blast procedure of firecrackers. In the FA, two blast (search) forms are utilized and systems for keeping decent variety of sparkles are likewise all around planned. To approve the presentation of the proposed FA, correlation tests were led on nine benchmark test capacities among the FA, the standard PSO (SPSO) and the clonal PSO (CPSO). It is demonstrated that the FA plainly beats the SPSO and the CPSO in both enhancement exactness and combination speed. The results convey that the side lobe level is reduced to −34.78dB and fill rate is increased to 78.53.

Samples including 16-element LAAs are conducted to verify the optimization performances of the SLL reductions. Simulation results show that the SLLs can be effectively reduced by FA. Moreover, compared with other benchmark algorithms, fireworks has a better performance in terms of the accuracy, the convergence rate and the stability.

With the use of algorithms radiation is prone to noise one way or other. Even with any optimizations we cannot expect radiation to be ideal. Power dissipation or electro magnetic interference is bound to happen, but the use of optimization algorithms tries to reduce them to the extent that is possible.

16-element linear antenna array is available with latest versions of Matlab.

The latest technologies and emerging developments in the field of communication and with exponential growth in users the capacity of communication system has bottlenecks. The antenna arrays are used to improve the capacity and spectral efficiency of wireless communication system. The latest communication systems use the antenna array technology which is to improve the spectral efficiency, fill rate and the energy efficiency of the communication system can be enhanced.

By using FA, the fill rate is increased to 78.53 and the side lobe level is reduced to 35dB, when compared with the bench mark algorithms.

For the crews and assets of the European Union’s (EU’s) Joint Operations available today, but a vast area in the Mediterranean Sea to monitor, detection of small boats and rafts in distress can take up to several days or even fail at all. This study aims to outline how an energy-autonomous swarm of Unmanned Aerial System can help to increase the monitored sea area while minimizing human resource demand.

A concept for an unattended swarm of solar powered, unmanned hydroplanes is proposed. A swarm operations concept, vehicle conceptual design and an initial vehicle sizing method is derived. A microscopic, multi-agent-based simulation model is developed. System characteristics and surveillance performance is investigated in this delimited environment number of vehicles scale. Parameter variations in insolation, overcast and system design are used to predict system characteristics. The results are finally used for a scale-up study on a macroscopic level.

Miniaturization of subsystems is found to be essential for energy balance, whereas power consumption of subsystems is identified to define minimum vehicle size. Seasonal variations of solar insolation are observed to dominate the available energy budget. Thus, swarm density and activity adaption to solar energy supply is found to be a key element to maintain continuous aerial surveillance.

This research was conducted extra-occupationally. Resources were limited to the available range of literature, computational power number and time budget.

A proposal for a probable concept of operations, as well as vehicle preliminary design for an unmanned energy-autonomous, multi-vehicle system for maritime surveillance tasks, are presented and discussed. Indications on path planning, communication link and vehicle interaction scheme selection are given. Vehicle design drivers are identified and optimization of parameters with significant impact on the swarm system is shown.

The proposed system can help to accelerate the detection of ships in distress, increasing the effectiveness of life-saving rescue missions.

For continuous surveillance of expanded mission theatres by small-sized vehicles of limited endurance, a novel, collaborative swarming approach applying in situ resource utilization is explored.

The purpose of this paper is to predict or even control the food safety risks during the distribution of perishable foods. Considering the food safety risks, the distribution route of perishable foods is reasonably arranged to further improve the efficiency of cold chain distribution and reduce distribution costs.

This paper uses the microbial growth model to identify a food safety risk coefficient to describe the characteristics of food safety risks that increase over time. On this basis, with the goal of minimizing distribution costs, the authors establish a vehicle routing problem with a food safety Risk coefficient and a Time Window (VRPRTW) for perishable foods. Then, the Weight-Parameter Whale Optimization Algorithm (WPWOA) which introduces inertia weight and dynamic parameter into the native whale optimization algorithm is designed for solving this model. Moreover, benchmark functions and numerical simulation are used to test the performance of the WPWOA.

Based on numerical simulation, the authors obtained the distribution path of perishable foods under the restriction of food safety risks. Moreover, the WPWOA can significantly outperform other algorithms on most of the benchmark functions, and it is faster and more robust than the native WOA and avoids premature convergence.

This study indicates that the established model and the algorithm are effective to control the risk of perishable food in distribution process. Besides, it extends the existing literature and can provide a theoretical basis and practical guidance for the vehicle routing problem of perishable foods.