whale optimization algorithm

Sensors of the Internet of Things and wireless sensor networks need accurate localization to provide information, such as road information. Installing a locator on all the nodes and sensors is very expensive, and, for this reason, indirect localization is done. One of the low-cost localization methods is DVHop algorithm. Due to the simplicity of DVHop algorithm, its execution time is not long; for this reason, it does not impose much energy consumption, and it is considered a low-cost algorithm. One of the challenges of the DVHop method is its significant error in localization. To solve this problem, in the present paper, a smart locator system is presented using the DVHop algorithm and improved Whale optimization algorithm to estimate the location of objects and sensors. The proposed method has three main steps for smart localization. Experiments showed that the proposed method has less localization error than PSO, WOA, GWO, and HHO algorithms and has high stability due to less standard deviation in localizing the error. Compared to the DVHop, PSODVHop, GSODVHop, and DEIDVHop, the proposed method reduces errors by 1.73, 1.60, 1.28, and 1.13 times, respectively.

With the increase in the number of locally distributed generation resources and the increase of smart buildings in today's microgrids, the computational volume and data exchanged between units have increased. Therefore, it is necessary to perform on-site calculations and send the final information to the upstream layer for decision-making and planning. This paper presents a cloud-fog computing structure that reduces the computational burden and time of calculations for energy management of smart buildings in the smart microgrids. The proposed system has several smart buildings, each with fixed and shiftable loads, an energy storage system, and a photovoltaic system. In the proposed energy management of smart buildings, the cost and peak-to-average ratio are presented as objective functions in a multi-objective problem. Every smart building can buy and sell energy with the upstream network. Whale optimization algorithm has been used to solve the optimization problem and the cost and peak-average ratio have been reduced and optimized simultaneously. By implementing cloud-fog computing and solving the optimization problem of each smart building locally, the computational burden and computing time have been reduced from 465.46 seconds to 48.52 seconds compared to the case without cloud-fog structure. Therefore, cloud-fog computing has reduced the computational burden and the time of calculations in the proposed energy management system of each smart building, after which the planning of the units is done locally.

In today's digital era, security issues and cyber attacks have become a serious and attention-needed concern as they hamper secured and vital information relating to organizations or individuals. Accordingly, timely detection of these vulnerabilities made by intruders is essential, wherein the cornerstone of security ensures the user's data privacy as an intrusion detection system (IDS). On the other hand, with the rapid development of machine learning (ML) and deep learning (DL) methods in the data world, one of their significant applications is dedicated to IDS using state-of-the-art classification algorithms, which has been the subject of numerous research to enhance accuracy and reliability in recent years. As a consequence, this paper presents a hybrid model integrating feature selection, classification, and hyper-parameters optimization. First, the initial massive features are subjected separately to the modified mutual information (MMI), genetic algorithm (GA), and Anova F-value approaches, followed by extracting the common outputs as optimal and reduced final features. Subsequently, a compound CNN and LSTM classifier (CNN-LSTM) is employed, where its hyper-parameters will be determined through a random switch grey wolf-whale optimization algorithm (RS-GWO-WOA) instead of a time-consuming trial and error manual process. Ultimately, to analyze the suggested scheme, a comparison with other strategies in terms of accuracy, precision, recall, F1 score, and periods of time on the NSL-KDD dataset has been accomplished, confirming the superiority of the developed approach.

In the current complicated supply chains, sustainability and two social and environmental perspectives have significantly caught researchers’ attention due to their significant role in cost reduction. The present study aims to propose a sustainable multi-tier supply chain model for power plant products for industrial and manufacturing factories.

To this end, a mathematical model was proposed with three

maximizing the social responsibility, minimizing the emission of environmental pollutants, and reducing the costs of the supply chain. The whale and genetic metaheuristic algorithms were employed to propose and solve the model since sustainable supply chain planning was considered an NH-hard problem.

In order to solve the proposed model, the experimental sample was designed in three groups including small, medium, and large in terms of the data of Atmosphere Company. The results of whale optimization and genetic algorithms were compared according to the comparative indices of quality, dispersion, uniformity, and solving time.

Originality/Value:

 According to the results, the whale algorithm was able to provide higher quality and near-optimal solutions than genetic algorithm; in addition, by comparison, it could efficiently explore and extract possible areas of the solution in terms of quality and dispersion indices. However, a shorter amount of time was required for genetic algorithm to uniformly find solutions.

Software fault prediction methods are used to predict fault-prone modules in the early stages of software development. Machine learning techniques are the most common techniques used in software fault prediction. Data dimensionality is one of the problems that affect the performance of machine learning algorithms. Data dimensionality means the existence of irrelevant or redundant features that may mislead the learning algorithm hence decrease its accuracy. Low accuracy of software fault prediction causes late detection of some faulty modules and as a result increases the effort and cost of fixing faults abnormally. Therefore, solving data dimensionality problem is necessary to increase the accuracy of software fault prediction. Researchers use feature selection algorithms for dimensionality reduction. Feature selection algorithms are divided into two types of filter-based feature selection and wrapper-based feature selection algorithms. Wrapper-based algorithms lead to higher accuracy prediction models. In these algorithms we can use different methods to search for the best solutions that best of them is metaheuristic search. Each of the metaheuristic algorithms has some strengths and weaknesses that researchers use combination of these algorithms to address these weaknesses. In this research, to address the weaknesses of each metaheuristic algorithm, a combination of genetic, ant colony and whale optimization algorithm is used as wrapper feature selection. Obviously, the application of early software faults prediction methods before the actual test is one of the effective passive defense techniques in reducing software systems development costs. 19 software projects are used to evaluate proposed method. Comparison of the results with other methods shows that the proposed method outperforms other methods.

This study presented a new method to accurate design of shell and tube heat exchanger network. It’s considered some parameters as decision variables such as the design of determined the flow path of each fluids, number of required shell side, allowable velocity and pressure drop, number of tubes, number of passes in shell and tube sides, length of tube, layouts of tubes, size and percentage of baffle cut, shell diameter, tube diameter, tube pitch and experimental equations to calculate pressure drop and heat transfer coefficients in shell and tube side heat exchanger units. It has been used whale algorithm to achieve optimum total annual cost for heat exchanger unit. The total annual cost is as objective function that included capital and energy costs. The results showed in two cases studies including four and ten streams in shell and tube heat exchanger networks. The total annual cost reduced almost 20.55% and 14.40% compared with others for two case study.

Rate of penetration (ROP) estimation in a drilling process is very important because it leads to the optimal selection of drilling parameters and reduction of the operating costs. The main purpose of this paper is to modeling and estimating ROP using optimized multilayer perceptron neural network with whale optimization algorithm (WOA-MLPNN), optimized multilayer perceptron neural network with ant colony optimization algorithm (ACO-MLPNN), back propagation multilayer perceptron neural network (BP-MLPNN) and two mathematical models including Bourgoyne and Young model (BYM) and Bingham model. The data required for development of the models were collected from the mud logging unit and the final reports of three drilled wells in an oil field located in southwestern Iran, which were first pre-processed to remove outliers and reduce noise. In the following, 12.25” hole-section information of two wells containing a similar sequence of drilled formations was used to train and test the models, and then the generated models were validated by the third well information. In the end, the performance of models was evaluated by statistical indicators and various graphical tools. The results of this study showed that the machine learning methods are much more accurate than conventional mathematical models. Also, more detailed studies showed that the WOA-MLPNN model with AAPRE values of 3.19, 5.48 and 9.31 for the three sections of training, testing and validation, respectively, has the highest performance compared to other models.