After the COVID-19 pandemic, the global economy began to recover. However, stock market fluctuations continue to affect economic stability, making accurate predictions essential. This study proposes an improvedwhale ...
详细信息
After the COVID-19 pandemic, the global economy began to recover. However, stock market fluctuations continue to affect economic stability, making accurate predictions essential. This study proposes an improved whale optimization algorithm (IWOA) to optimize the parameters of the Long Short-Term Memory (LSTM) model, thereby enhancing stock index predictions. The IWOA improves upon the traditional whaleoptimizationalgorithm (WOA) by integrating logistic chaotic mapping to increase population diversity and prevent premature convergence. Additionally, it incorporates a dynamic adjustment mechanism to balance global exploration and local exploitation, thus boosting optimization performance. Experiments conducted on five representative global stock indices demonstrate that the IWOA-LSTM model achieves higher accuracy and reliability compared to WOA-LSTM, LSTM, and RNN models. This highlights its value in predicting complex time-series data and supporting financial decision-making during economic recovery.
Since Markowitz introduced the mean-variance model, many investors have described investment return rates by assuming they are stochastic or fuzzy variables. However, the inherent complexity and unpredictability of fi...
详细信息
Since Markowitz introduced the mean-variance model, many investors have described investment return rates by assuming they are stochastic or fuzzy variables. However, the inherent complexity and unpredictability of financial markets often render these assumptions insufficient. To address these challenges, an increasing number of researchers are exploring portfolio optimization within the framework of uncertainty theory. This paper proposes two portfolio optimization models that incorporate investors' utility under the criteria of expected value and optimistic value. We derive the deterministic forms of these two models under the assumption that the variables follow uncertain normal distributions. Additionally, we compare the differences between the multi-factor expected value-standard deviation utility (ESU) model and the optimistic value- standard deviation utility (OSU) model in terms of their ability to maximize investors' utility. To solve these models effectively, we propose an improved whale optimization algorithm (IWOA) based on the Levy flight strategy, adaptive position weight strategy, and adaptive probability threshold. Extensive numerical experiments validate the effectiveness of the improvedalgorithm and compare the differences between the two models.
As an important renewable energy source, wind energy is significant for realizing energy transition and reducing carbon emissions. With the increasing penetration of wind energy in the global energy system, higher pre...
详细信息
As an important renewable energy source, wind energy is significant for realizing energy transition and reducing carbon emissions. With the increasing penetration of wind energy in the global energy system, higher prediction accuracy is needed to ensure the safe and stable operation of the power grid. However, the existing wind power prediction methods are constantly pursuing model improvement, ignoring the importance of data quality to the prediction performance, resulting in a stagnation of the upper limit of prediction accuracy. In this paper, we establish a comprehensive wind power prediction system based on correct multi-scale clustering ensemble, similarity matching, and an improved whale optimization algorithm. Firstly, multiple classification algorithms combined with meteorological data are used to correct the extreme scenarios in the clustering results. Secondly, a library of typical fluctuation patterns is established based on the clustering ensemble results, and the optimal training dataset is determined by similarity matching. Finally, complete ensemble empirical mode decomposition with adaptive noise(CEEMDAN) is used to extract further the power data's local features and time-frequency characteristics and to predict the modal components using the improved whale optimization algorithm(IWOA)-optimized BiLSTM network. The results of the three sets of experiments show that the proposed model is able to improve more than 10% in terms of MAE, RMSE, and MAPE compared to other models, and the model robustness is high.
The activity of slag components is one of the primary factors influencing the thermodynamic properties of slag. In this study, a feasible model was established to predict the a(CaO) using improvedwhaleoptimization a...
详细信息
The activity of slag components is one of the primary factors influencing the thermodynamic properties of slag. In this study, a feasible model was established to predict the a(CaO) using improved whale optimization algorithm (IWOA) and Categorical Boosting (CatBoost). The effects of other variables on a(CaO) were listed in descending order of influence as follows: w(CaO), w(SiO2), temperature, w(MgO), and w(Al2O3). And the IWOA-CatBoost model achieved the highest R2 value of 0.9200, lowest RMSE of 0.0042, and lowest MAE of 0.0030 in predicting the a(CaO). The performance of the optimal IWOA-CatBoost model was evaluated and compared with that of known models. The results demonstrate that the IWOA-CatBoost model outperformed existing models and methods, such as the Factsage, ion and molecule coexistence theory, and genetic algorithm-backpropagation neural network. The accurate calculation of slag component activity is of great significance to the analysis of the thermodynamic properties of slag. Meanwhile, the approach and algorithm used to develop the a(CaO) prediction model can also be applied to predicting the activity of other slag components or other metallurgical applications (e.g., predicting molten steel temperature, steel composition, and alloy yield).
Energy storage power plants are critical in balancing power supply and ***,the scheduling of these plants faces significant challenges,including high network transmission costs and inefficient inter-device energy *** ...
详细信息
Energy storage power plants are critical in balancing power supply and ***,the scheduling of these plants faces significant challenges,including high network transmission costs and inefficient inter-device energy *** tackle these challenges,this study proposes an optimal scheduling model for energy storage power plants based on edge computing and the improved whale optimization algorithm(IWOA).The proposed model designs an edge computing framework,transferring a large share of data processing and storage tasks to the network *** architecture effectively reduces transmission costs by minimizing data travel *** addition,the model considers demand response strategies and builds an objective function based on the minimization of the sum of electricity purchase cost and operation *** IWOA enhances the optimization process by utilizing adaptive weight adjustments and an optimal neighborhood perturbation strategy,preventing the algorithm from converging to suboptimal *** results demonstrate that the proposed scheduling model maximizes the flexibility of the energy storage plant,facilitating efficient charging and *** successfully achieves peak shaving and valley filling for both electrical and heat loads,promoting the effective utilization of renewable energy *** edge-computing framework significantly reduces transmission delays between energy ***,IWOA outperforms traditional algorithms in optimizing the objective function.
The independently controllable wheels of a 4WIS/4WID vehicle endow it with high maneuverability and driving stability. However, the excessive number of control inputs for wheel steering angles and motor torques signif...
详细信息
The independently controllable wheels of a 4WIS/4WID vehicle endow it with high maneuverability and driving stability. However, the excessive number of control inputs for wheel steering angles and motor torques significantly increases control complexity, making it challenging to balance driving stability and path-tracking accuracy. To address this issue, this paper proposes a hierarchical control strategy based on an improved whale optimization algorithm (IWOA), consisting of three layers: path-tracking, stability control, and torque-angle allocation. First, a front-wheel steering controller is designed based on a single-point preview deviation model to achieve path-tracking control. Second, a sliding mode controller integrating rear-wheel steering and direct yaw moment control is developed based on a two-degree-of-freedom vehicle model and sliding mode control theory. This controller mitigates the adverse effects of sideslip angle deviation and yaw rate deviation on vehicle stability. A novel reaching law is introduced to suppress chattering in the sliding mode controller. Additionally, dynamic load transfer and Ackermann steering theory are employed to distribute wheel torques and steering angles, respectively. Finally, to address the issue of control coupling between wheel steering angles and drive torques caused by the difficulty of multi-parameter tuning in the sliding mode controller, an improved whale optimization algorithm (IWOA) is proposed. The enhancement incorporates three strategies: chaotic mapping-based initialization, nonlinear convergence factor updating, and adaptive inertia weight adjustment. Furthermore, a comprehensive fitness function that considers both vehicle stability and path tracking accuracy is designed, and the proposed algorithm is applied to optimize the parameters of the sliding mode controller. Simulation results demonstrate that, compared to front-wheel steering and 4WIS-4WID control strategies, the proposed 4WIS-4WID intelligent v
Since the steel plate surface defect image often has complicated background and lots of noise, the segmentation accuracy is low when using the single threshold Otsu method. Therefore, this paper introduces the whale o...
详细信息
Since the steel plate surface defect image often has complicated background and lots of noise, the segmentation accuracy is low when using the single threshold Otsu method. Therefore, this paper introduces the whaleoptimizationalgorithm (WOA) to optimize the threshold of the dual-threshold image segmentation. To avoid the premature convergence, slow convergence speed and easy fall into the local optimum of the original WOA, an improved WOA is proposed. Firstly, the WOA is discretized by using round function;secondly, the sin mapping generation chaotic sequence is used to replace the randomly generated initial population in the initialization process of the WOA to enhance the multiformity of population;thirdly, the global search and local development capabilities are balanced and improved by nonlinear time-varying factors and inertia weights in the position updating mechanism;finally, the improved WOA is applied to the two-dimensional Otsu (2D-Otsu) algorithm to select the optimal threshold for image segmentation. The simulation results of 8 classic benchmark functions show that the improved WOA can obtain the optimal value of the function 0, - 12,569.5. The improved WOA can raise convergence speed and improve the global search ability and get rid of the local optimum. The experimental results show that the proposed algorithm outperforms the Otsu algorithm and can achieve more accurate segmentation of steel plate surface defect image. Compared with 2D-Otsu algorithm, the proposed algorithm reduces running time by 0.34 s and has the highest segmentation efficiency for rolled-in scale defects.
The ordinary partial transmission sequence (OPTS) technique is known as an inherent and accurate peak-to-average power ratio (PAPR) reduction scheme in orthogonal frequency division multiplexing (OFDM). However, it su...
详细信息
The proportional integral derivative (PID) controller is one of the most robust and simplest configuration controllers used for industrial applications. However, its performance purely depends on the tuning of its pro...
详细信息
The proportional integral derivative (PID) controller is one of the most robust and simplest configuration controllers used for industrial applications. However, its performance purely depends on the tuning of its proportional (K-P), integral (K-I) and derivative (K-D) gains. Therefore, a proper combination of these gains is primarily required to achieve an optimal performance of the PID controllers. The conventional methods of PID tuning such as Cohen-Coon (CC) and Ziegler-Nichols (ZN) generate unwanted overshoots and long-lasting oscillations in the system. Owing to the mentioned problems, this paper attempts to achieve an optimized combination of PID controller gains by exploiting the intelligence of the whaleoptimizationalgorithm (WOA) and one of its recently introduced modified versions called improved whale optimization algorithm (IWOA) in an automatic voltage regulator (AVR) system. The stability of the IWOA-AVR system was studied by assessing its root-locus, bode maps, and pole/zero plots. The performance superiority of the presented IWOA-AVR design over eight of the recently explored AI-based approaches was validated through a comprehensive comparative analysis based on the most important transient response and stability metrics. Finally, to assess the robustness of the optimized AVR system, robustness analysis was conducted by analyzing the system response during the variation in the time constants of the generator, exciter, and amplifier from -50% to 50% range. The results of the study prove the superiority of the proposed IWOA-based AVR system in terms of transient response and stability metrics.
A model for predicting the end-point temperature and end-point carbon content of RH refining steel based on an improved whale optimization algorithm and a stochastic configuration network (LWOA-SCN) is proposed to sol...
详细信息
A model for predicting the end-point temperature and end-point carbon content of RH refining steel based on an improved whale optimization algorithm and a stochastic configuration network (LWOA-SCN) is proposed to solve the existing problem of inaccurate detection of the steel composition in the ladle during the steelmaking process. The algorithm has an implicit layer structure that can be generated adaptively based on the training effect and has the ability of strong generalization performance, simple structure, fast convergence, high accuracy, and jumping out of local optimum. Firstly, the LWOA-SCN algorithm is used to construct the prediction model. Secondly, the model was tested against RBF, GA-BP, and PSO-SVM models, and the results showed that the LWOA-SCN model had the highest predicted effect. Finally, the LWOA-SCN model was tested in industrial production applications, and the results showed that the hit rate is 90.6%, 95.6%;93.7%, 94.3% for refining end-point temperature and end-point carbon content error within +/- 5 degrees C, +/- 10 degrees C;and +/- 0.005%, +/- 0.01%, respectively. which can well meet the practical needs of a steel mill. The model provides theoretical guidance and production guidance for studying the control of refining end-point temperature and end-point carbon content.
暂无评论