In this article, a new practical approach is implemented to analyze combined heat and power economic dispatch (CHPED) and wind based CHPED (CHPEDW) problems with a chaotic based whaleoptimizationalgorithm (WOA). The...
详细信息
In this article, a new practical approach is implemented to analyze combined heat and power economic dispatch (CHPED) and wind based CHPED (CHPEDW) problems with a chaotic based whaleoptimizationalgorithm (WOA). The conflict objectives of this problem are used to minimize fuel costs as well as emission. The proposedWOAworks on the searching behavior of humpback whales, which helps to satisfy the problem's objective functions. The chaotic nature has been integrated with WOA to enhance the convergence speed of the problem. The presence of valve point loading, prohibited operating zone, and uncertainty of wind has expanded the problem nonlinearity. It has been tested on two different nonlinear realistic power areas to judge the satisfactory results of the proposed algorithm. The superiority of the proposed algorithm is judged by comparing it with presently developed some other meta-heuristic optimization techniques.
This paper proposes an experimental verification of a hybrid partial feedback linearization (PFL) and deadbeat (DB) control scheme as in Hamdy et al. (2018) with chaotic whale optimization algorithm (CWOA) for a nonli...
详细信息
This paper proposes an experimental verification of a hybrid partial feedback linearization (PFL) and deadbeat (DB) control scheme as in Hamdy et al. (2018) with chaotic whale optimization algorithm (CWOA) for a nonlinear gantry crane (GC) system. The PFL linearizes the nonlinear model to end up with a linear closed-loop system. The DB controller is utilized for the desirable accelerated response without any oscillation or undesirable effects on the internal dynamics stability. The CWOA is used to tune the controller parameters. A sliding-mode observer (SMO) is utilized to estimate the unmeasured states. Using this hybrid scheme, a better payload sway elimination can be obtained. Finally, the experimental results are presented to illustrate the efficiency and the effectiveness of the proposed scheme with a comparative study. (C) 2019 ISA. Published by Elsevier Ltd. All rights reserved.
In this manuscript, a novel energy detection-based chaotic whale optimization algorithm (ED-CWOA) is proposed to maximize the spectrum utilization, duration, and threshold in cognitive radio network (CRN). Here, the s...
详细信息
In this manuscript, a novel energy detection-based chaotic whale optimization algorithm (ED-CWOA) is proposed to maximize the spectrum utilization, duration, and threshold in cognitive radio network (CRN). Here, the spectrum utilization is designed taking into account sensing duration and threshold in multi-objective function is formulated by considering its primary user (PU) protection restrictions and secondary user (SU) throughput. To get the global optimal solution, the CWOA and the multi-objective optimization problem are finally carried out on a single objective. The execution is performed on NS2 simulator. The simulation outcome demonstrates that the proposed ED-CWOA system has lower delay 33.878%, 26.206%;higher delivery ratio 35.536%, 22.65%;lower Fairness Index 46.66%, 58.332%;lower energy consumption 25.462%, 35.524%;and higher throughput 96.82%, 49.28% for different nodes analyzed with the existing methods, like energy detection-based bivariate Levy-stable bat algorithm (ED-BLSBA) and genetic algorithm-based energy detection (ED-GA), respectively. The simulation outcome indicates that the proposed system may be able to get the optimal global solutions efficiently and accurately.
Induction motors are essential in industrial production, and their fault diagnosis is vital for ensuring continuous and efficient equipment operation. Minimizing downtime losses and optimizing maintenance costs are ke...
详细信息
Induction motors are essential in industrial production, and their fault diagnosis is vital for ensuring continuous and efficient equipment operation. Minimizing downtime losses and optimizing maintenance costs are key to maintaining smooth production and enhancing economic efficiency. This paper presents a novel diagnostic approach for diverse motor faults, integrating time series analysis, Transformer-based networks, and multi-modal data fusion. Firstly, multiple signals such as three-phase current, vibration, device sound, and ambient sound are collected to form a multi-modal dataset. Subsequently, a Transformer network for single time series classification is developed, and multiple instances are concatenated in parallel to create an ensemble Transformer network. The self-attention mechanism is then utilized to dynamically integrate features from different modal data for accurate motor fault identification. During network training, the chaotic WOA optimizes the ensemble Transformer network's hyper-parameters. Finally, the proposed method is trained and tested on a motor measurement multi-modal dataset. Experimental results show that it performs outstandingly on multi-modal datasets, attaining a high diagnostic accuracy of 99.10%. Compared with single-mode data and state-of-the-art methods, it demonstrates superior diagnostic accuracy and reliability.
Power load forecasting is an important part of smart grid, and its accuracy will directly affect the control and planning of power system operation. In the context of electricity market reform, real-time electricity p...
详细信息
Power load forecasting is an important part of smart grid, and its accuracy will directly affect the control and planning of power system operation. In the context of electricity market reform, real-time electricity prices affect users' electricity consumption patterns. A short-term load forecasting model based on support vector regression (SVR) with whaleoptimizationalgorithm (WOA) considering real-time electricity price is proposed in this paper. Meta-heuristics are very promising in optimizing the parameters of SVR, and the WOA algorithm is used to determine the appropriate combination of SVR's parameters to accurately establish a forecasting model. The initial value of the original WOA algorithm lacks ergodicity, and has defects such as easy to fall into local optimum and low convergence accuracy. Chaos mechanism and elite opposition-based learning strategy are introduced into WOA to balance the exploration and exploitation of the algorithm and improve the algorithm convergence speed. Numerical examples involving two power load datasets show that the proposed model can achieve better forecasting performance in comparison with other models, such as SVR, BPNN. At the same time, it proves that the forecasting accuracy with electricity price is higher than that without electricity price.
Recently, integration of distributed generations (DGs) and shunt capacitors in radial distribution network are becoming popular to withstand the rapidly increasing in electricity demands. In this article, a hybrid met...
详细信息
Recently, integration of distributed generations (DGs) and shunt capacitors in radial distribution network are becoming popular to withstand the rapidly increasing in electricity demands. In this article, a hybrid method is proposed to obtain the best locations and sizes of capacitors and DGs in radial distribution network. This hybrid method is based on chaotic whale optimization algorithm (CWOA) and loss sensitivity factor (LSF). The proposed method is tested on IEEE 69-bus system to enhance the buses voltages, increase the distribution system capacity, and decrease the total power loss. The obtained results prove that the proposed method based on CWOA and LSF can be highly effective in determining the locations and sizes of capacitors and DGs in RDS compared with other optimization techniques.
In this paper, network dynamics are investigated in a periodically forced chemical system. At the same time, the ring network and ring-star network based on the periodically forced chemical system are designed. The ch...
详细信息
In this paper, network dynamics are investigated in a periodically forced chemical system. At the same time, the ring network and ring-star network based on the periodically forced chemical system are designed. The chaotic dynamics of the ring network and ring-star network are analyzed by using the Lyapunov exponent spectrum, bifurcation diagram and correlation function. We show that the coupling strength of ring network has an important influence on chaotic dynamics and synchronization. By comparing ten, eleven and 100 nodes, we find that the bifurcation path of the ring-star network is robust to the number of nodes, which is different from the ring network. In addition, the ring-star network in comparison with the ring network achieved chaotic complete synchronization among all nodes. Finally, we proposed a new chaoticwhaleoptimization (CWO) algorithm using the randomness of the ring-star network. It is used to tune the parameters of the PID controller with large time-delay systems. The simulation results show that the proposed CWO algorithm presents better performance than other available algorithms in the literature.
ABSTR A C T With the manufacturing reshoring to the US, increasing attention are focus on its energy consumption and environmental effects and accurate prediction of carbon emissions is vital to controlling growth fro...
详细信息
ABSTR A C T With the manufacturing reshoring to the US, increasing attention are focus on its energy consumption and environmental effects and accurate prediction of carbon emissions is vital to controlling growth from the source. Considering the slowing growth in carbon emissions with the Gompertz's law, this paper establishes a Gompertz differential equation. According to the differential information principle and fractional accumulation operator, this differential equation is transformed into a fractional accumulation grey Gompertz model. Furthermore, the chaotic whale optimization algorithm is used to optimize the order of accumulation generation and the grey background value in the proposed model. Then the Gompertz's datasets and six validation cases about carbon emissions are used to show that the proposed model demonstrates better accuracy in all cases and efficiency in the carbon emissions forecasting with several existing models. Three case studies indicate that the proposed model can fit the trend of American industrial carbon emissions better. The model results also reveal the recent policy changes have promoted the uptrend of the industrial and the total carbon emissions in the U.S. The future forecasting suggests that U.S. carbon emission is estimated to be 17.01% (in total emissions) or 17.89% (in industrial emission) percent below 2005 levels by 2025 under current policies, falling short of its commitment submitted to the United Nations Framework Convention on Climate Change. (c) 2021 Elsevier Ltd. All rights reserved.
暂无评论