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.

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.