Lin Yongxing; Si Yanru
Abstract
One of the most widely used metals in the world is the Iron. The world cost of iron ore is defineded by its supply and demand. Numerous variabes such as steel, scrap, oil, gold, interest rate, inflation rate, dollar value, and stock value affect the world price of iron ore. Therefore, for economic investment ...
Read More
One of the most widely used metals in the world is the Iron. The world cost of iron ore is defineded by its supply and demand. Numerous variabes such as steel, scrap, oil, gold, interest rate, inflation rate, dollar value, and stock value affect the world price of iron ore. Therefore, for economic investment of iron ore, it should be forecasted precisely by the scientists to give a direction to the decision makers to make a proper decision for the society. Due to the multiplicity of effective parameters and the complexity of the relationships between the iron ore variables, artificial intelligence is the best idea for forecasting. In this paper, we utilized a new optimized version of Convolutional Neural Network (CNN) to facilitate this task. To do so, a modified version of the Search and Rescue (MSAR) optimization algorithm has been designed and used for optimizing the CNN for improving its training efficiency in forecasting the iron ore price volatilities. The method is then validated based on ten different variables. Finally, a comparison of the results with various state of the art techniques was carried out to show the suggested method effectiveness. The results showed that the suggested technique has the fittest results in comparison to the other newest techniques.
Dong Sun
Abstract
One of the important and more challenging categories in the smart cities and IoT is to monitor the vehicles plate licenses. This system is a key factor in most of the traffic monitoring in the IoT based smart city applications. In this research, a method for plate license recognition based on optimal ...
Read More
One of the important and more challenging categories in the smart cities and IoT is to monitor the vehicles plate licenses. This system is a key factor in most of the traffic monitoring in the IoT based smart city applications. In this research, a method for plate license recognition based on optimal training of the CNN is proposed. To do this, the configuration and the hyperparameters of the CNN were optimized by a new hybrid optimization including world cup optimizer, whale optimizer, and chaotic theory to obtain a better result with high convergence. Simulations are applied to the UFPR-ALPR dataset and are compared with six popular techniques in terms of accuracy and time. Experimental achievements indicated that the proposed method gives superiority toward the other comparative techniques and is an efficient method for vehicles plate licenses detection.
Arda Karasakal
Abstract
Several methods have been proposed for sale and payment mechanisms in electricity markets; but, appropriate evaluation of this mechanisms is so difficult. The offer cost minimization (OCM) has been presented previously for solving this problem which minimizes the total offer cost through the evaluation ...
Read More
Several methods have been proposed for sale and payment mechanisms in electricity markets; but, appropriate evaluation of this mechanisms is so difficult. The offer cost minimization (OCM) has been presented previously for solving this problem which minimizes the total offer cost through the evaluation by locational marginal prices (LMPs). In recent years, payment cost minimization (PCM) method is suggested which directly minimizes the consumer payments and is more complicated than OCM in terms of framework and converting to single-level linearized optimization problem as well as computational burden. In the current study, a new meta-heuristic optimizer has been proposed for to PCM through solving the joint energy-reserve PCM problem. The achievements are put in comparison with conventional model based offer cost minimization through various studied cases.
Guobin Yan; Shunlei Li
Abstract
Recently, the application of the intelligent parking lot (IPL) in the power market has been exponentially increasing to decrease the greenhouse gasses, the pollution, and to decrease the deviation cost of the energy production based on electric vehicles (EV). IPLs uses charge and discharge features of ...
Read More
Recently, the application of the intelligent parking lot (IPL) in the power market has been exponentially increasing to decrease the greenhouse gasses, the pollution, and to decrease the deviation cost of the energy production based on electric vehicles (EV). IPLs uses charge and discharge features of EVs to exchange the energy in the upstream grid. This paper study on a new interval-analysis based optimal solution of an IPL by considering the interval uncertainties for the price of upstream gird value. The method based on using an interval-based particle swarm optimization algorithm to optimize an interval objective function with lower and upper limitations with a single-valued output. Simulation results of the presented procedure are compared with a deterministic mixed-integer linear programming to show its superiority. The results show that deviation cost has been decreased up to 10.74% while average cost has been raised into 5.17% which demonstrates the methods high performance in decreasing the average cost of IPL and the reliability of the intelligent parking lot in the presence of uncertainties derived from the upstream grid.
Caiyuan Xiao; Guiju Zhang
Abstract
This paper presents an analysis of improving the efficiency of a hybrid solid oxide fuel cell (SOFC) and a micro gas turbine (mGT) system. The main reason for using SOFC technology is the generation of its less harmful products with higher performance compared to the traditional power generation systems. ...
Read More
This paper presents an analysis of improving the efficiency of a hybrid solid oxide fuel cell (SOFC) and a micro gas turbine (mGT) system. The main reason for using SOFC technology is the generation of its less harmful products with higher performance compared to the traditional power generation systems. In addition, the combination of the gas turbine can improve the SOFC system’s reliability. Due to the importance of SOFC systems degradation in the industry, using the optimized hybrid system to reduce SOFC degradation is a proper process. This study presents a new developed bio-inspired optimization technique based on the rhino herd algorithm. After validation of the method with some different bio-inspired methods, it is employed to optimal size selection of the gas turbine for the fuel cell system reliability. Simulation results show that using a larger size of the turbine gives a higher level of power to the SOFC. It also decreases the efficiency of the initial turbine and increases the initial capital investment.
)
