Cloud computing is a massively distributed system in which existing resources interact with user-requested tasks to meet their requests. In such a system, the problem of optimizing Resource Allocation and Scheduling (RAS) is vital, because recourse allocation and scheduling deals with the mapping between recourses and user requests and also is responsible for optimal allocating of tasks to available resources. In the cloud environment, a user may face hundreds of computational resources to do his work. Therefore, manually recourse allocation and scheduling are impossible, and having a schedule between user requests and available recourses seems logical. In this paper, we used Whale Optimization Algorithm (WOA) to solve resource allocation and task scheduling problem in cloud computing to have optimal resource allocation and reduce the total runtime of requested services by users. The proposed Algorithm is compared with the other existed Algorithms. Results indicate the proper performance of the proposed Algorithm than other ones.

Clustering is a method of data analysis and one of the important methods in data mining that has been considered by researchers in many fields as well as in many disciplines. In this paper, we propose combining WOA with BA for data clustering. To assess the efficiency of the proposed method, it has been applied in data clustering. In the proposed method, first, by examining BA thoroughly, the weaknesses of this Algorithm in exploitation and exploration are identified. The proposed method focuses on improving BA exploitation. Therefore, in the proposed method, instead of the random selection step, one solution is selected from the best solutions, and some of the dimensions of the position vector in BA are replaced We change some of the best solutions with the step of reducing the encircled mechanism and updating the WOA spiral, and finally, after selecting the best exploitation between the two stages of WOA exploitation and BA exploitation, the desired changes are applied on solutions. We evaluate the performance of the proposed method in comparison with other meta-heuristic Algorithms in the data clustering discussion using six datasets. The results of these experiments show that the proposed method is statistically much better than the standard BA and also the proposed method is better than the WOA. Overall, the proposed method was more robust and better than the Harmony Search Algorithm (HAS), Artificial Bee Colony (ABC), WOA and BA.

K-Nearest Neighbors (KNN) is a classification Algorithm based on supervised machine learning, which works according to a voting system. The performance of the KNN Algorithm depends on different factors, such as unbalanced distribution of classes, the scalability problem, and considering equal values for all training samples. Regarding the importance of the KNN Algorithm, different improved versions of this Algorithm are introduced, such as fuzzy KNN, weighted KNN, and KNN with variable neighbors. In this paper, a weighted KNN based on Whale Optimization Algorithm is proposed for the objective of increasing the level of detection accuracy. The proposed Algorithm devotes a weight to each training sample of every feature by employing the WOA to explore the optimized weight matrix. The Algorithm is implemented and experimented on five standard datasets. The evaluation results prove that the proposed Algorithm performs better than both weighted KNN based on the Genetic Algorithm (GA) and the classic KNN Algorithm.

The household energy management system (HEMS) can optimally schedule home appliances for transferring loads from peak to off-peak times. Consumers of smart houses have HEM, renewable energy sources and storage systems to reduce the bill. In this article, a new HEM model based on the time of usage pricing planning with renewable energy systems is proposed to use the energy more efficiently. The new meta-heuristic Whale Optimization Algorithm (WOA) and the common meta-heuristic of particle swarm Optimization (PSO) are used to achieve that. To improve the performance, a mapping chaos theory (CWOA) is proposed. Also, an independent solar energy source is used as a support of the microgrid to achieve a better performance. It is concluded that the energy saving achieved by the proposed Algorithm is able to decrease the electricity bill by about 40-50% rather than the WOA and PSO methods. The proposed system is simulated in MATLAB environment.

To realize the self-healing concept of smart grids, an accurate and reliable fault locator is a prerequisite. This paper presents a new fault location method for active power distribution networks which is based on measured voltage sag and use of Whale Optimization Algorithm (WOA). The fault induced voltage sag depends on the fault location and resistance. Therefore, the fault location can be found by investigation of voltage sags recorded throughout the distribution network. However, this approach requires a considerable effort to check all possible fault location and resistance values to find the correct solution. In this paper, an improved version of the WOA is proposed to find the fault location as an Optimization problem. This Optimization technique employs a number of agents (Whales) to search for a bunch of fish in the optimal position, i. e. the fault location and its resistance. The method is applicable to different distribution network configurations. The accuracy of the method is verified by simulation tests on a distribution feeder and comparative analysis with two other deterministic methods reported in the literature. The simulation results indicate that the proposed optimized method gives more accurate and reliable results.

Polynomial neural network (PNN) is a supervised learning Algorithm that is one of the most popular models used in real applications. The architectural complexity of polynomial neural networks in terms of both the number of partial descriptions (PDs) and the number of layers, leads to more computation time and more storage space requirements. In general, it can be said that the architecture of the polynomial neural networks is very complex and it requires large memory and computation time. In this research, a novel approach has been proposed to improve the classification performance of a polynomial neural network using the Whale Optimization Algorithm (PNN-WOA). In this approach, the PDs are generated at the first layer based on the combination of two features. The second layer nodes consist of PDs generated in the first layer, input variables and bias. Finally, the polynomial neural network output is obtained by sum of weighted values of the second layer outputs. Using the Whale Optimization Algorithm (WOA), the best vector of weighting coefficients will be obtained in such a way that the PNN network reach to the highest classification accuracy. Eleven different dataset from UCI database has been used as input data of the proposed PNN-WOA and the results have been presented. The proposed method outperforms state-of-the-art approaches such as PNN-RCGA, PNN-MOPPSO, RCPNN-PSO, and S-TWSVM in most cases. For datasets, an improvement of accuracy between 0. 18% and 10. 33% can be seen. Also, the results of the Friedman test indicate the statistical superiority of the proposed PNN-WOA model compared to other methods with p value of 0. 039.

Today, the use of hydrological models is mainly necessary to simulate changes in water source and flow (runoff and evaporation). Proper modeling of hydrological processes requires the determination of model parameters. In calibration processes, the values ​​of the model parameters are estimated so that the model can simulate a natural system well. It is generally impossible to estimate the parameters of such models directly due to the large number of parameters and it is necessary to estimate them with the help of Optimization tools (model calibration). In the present study, the parameters of the daily Hymod rainfall-runoff model (a simple conceptual rainfall-runoff model) were calibrated using the Whale Algorithm (WOA), which is derived from the way Whale food is searched. The evaluation of the mentioned calibration method was performed using daily precipitation, evapotranspiration and transpiration data for 5 years and its validation was performed in 5 years in the Leaf River Basin of the United States. The simulated and observed flow rates were compared using correlation coefficient (R2), root mean square error (RMSE) and Nash-Sutcliffe coefficient (NS). The values ​​of error measurement criteria were 0.91, 1.2 and 0.8 for the calibration period and 0.91, 2.5 and 0.83 for the validation period, respectively. Also, the parameters calculated using the Whale Algorithm, the maximum moisture storage in the area of 216.95 mm, spatial variation of soil moisture storage 0.38, the distribution factor between the two moisture tanks 0.98, the shelf life in the laminar tank 0.08 days and Shelf life in fast flow tank is 0.47 days. Examination of error values ​​showed that the Whale Optimization Algorithm has high efficiency in calibrating rainfall-runoff models.

One of the most critical challenges of wireless sensor networks is the limited energy of the nodes, which has tried to manage energy consumption in these networks by using more accurate clustering. So far, many methods have been proposed to increase the accuracy of clustering, which reduces the energy consumption of nodes and thus increases network throughput. In this paper, we propose a method for clustering wireless sensor networks using the Whale Optimization Algorithm, which results in increased throughput in these networks. Although much work has been done in this area in terms of energy, some do not have good throughput. Therefore, in this paper, a clustering method based on the Whale Optimization Algorithm is proposed. Features of this Algorithm include easy implementation, providing high- quality solutions, quick convergence, and the ability to escape from local minima. Also, in terms of clustering, in addition to paying attention to energy consumption, has appropriate throughput. In the proposed method, the Euclidean distance is used to assign data to the cluster and determine the cluster centers by the Whale Optimization Algorithm. In other words, concentrated clusters are created. Then, according to the two remaining energy parameters and the distance of the nodes to the centers of the cluster, two clusters are selected. To evaluate the research, we have used MATLAB software and compared the proposed method with one of the latest works. The results show an improvement in throughput and comparable in terms of energy