Short-term wind speed forecasting is fundamental to improving the stability of power grid operation and enhancing its transmission efficiency;thus, it has long been a research hotspot. Nonetheless, quantities of liter...
详细信息
Short-term wind speed forecasting is fundamental to improving the stability of power grid operation and enhancing its transmission efficiency;thus, it has long been a research hotspot. Nonetheless, quantities of literature in this field only used the single prediction model and overemphasized deterministic prediction, which resulted in deficient forecasting performance. To address these issues, a novel point and interval combination prediction system was developed in this paper. Specifically, wind speed time series were reconstructed by dividing windows and fuzzification to input highly effective data;next, four single prediction models and a multi-objective weight-determining mechanism were integrated to obtain the point prediction results;and their distributions were assessed to implement interval prediction under distinct confidence levels. In the meantime, this study demonstrated that the proposed system reached the Pareto optimal by the theoretical proof, and empirical research was conducted based on 10-min real wind speed data from the wind farm in China. Judging from the experimental results, the combination prediction system was always capable of providing the most satisfactory forecasting performance by contrast with the comparative models. Consequently, it has broad application prospects in guiding the operation of wind farms and optimizing the power grid dispatching.
In order to further reduce the subjectivity of network design and improve the ability of model feature extraction, an ultrasonic detection method for weld defects based on neural network architecture search is propose...
详细信息
In order to further reduce the subjectivity of network design and improve the ability of model feature extraction, an ultrasonic detection method for weld defects based on neural network architecture search is proposed. Through the designed multi-level and multi-branch search space and an untrained architecture search and evaluation method, an efficient defect classification network was automatically constructed to complete the task of weld defect classification. Experiments were carried out on a self-constructed data set, and compared with the manually designed model, the classification accuracy of defect types reached 95.26% when the number of parameters was only 7.3 M. Compared with the model constructed using neural network architecture search, the proposed method can reduce the searching time to 8.29% of the baseline model while weighing multiple conflicting objectives, which proved the efficiency and effectiveness of the proposed method.
This paper proposes the multi-objective variant of the recently-introduced fitness dependent optimizer (FDO). The algorithm is called a multi-objective fitness dependent optimizer (MOFDO) and is equipped with all five...
详细信息
This paper proposes the multi-objective variant of the recently-introduced fitness dependent optimizer (FDO). The algorithm is called a multi-objective fitness dependent optimizer (MOFDO) and is equipped with all five types of knowledge (situational, normative, topographical, domain, and historical knowledge) as in FDO. MOFDO is tested on two standard benchmarks for the performance-proof purpose: classical ZDT test functions, which is a widespread test suite that takes its name from its authors Zitzler, Deb, and Thiele, and on IEEE Congress of Evolutionary Computation benchmark (CEC-2019) multi-modal multi-objective functions. MOFDO results are compared to the latest variant of multi-objective particle swarm optimization, non-dominated sorting genetic algorithm third improvement (NSGA-III), and multi-objective dragonfly algorithm. The comparative study shows the superiority of MOFDO in most cases and comparative results in other cases. Moreover, MOFDO is used for optimizing real-world engineering problems (e.g., welded beam design problems). It is observed that the proposed algorithm successfully provides a wide variety of well-distributed feasible solutions, which enable the decision-makers to have more applicable-comfort choices to consider.
Reservoirs play an important role in flood control, irrigation, water supply, and environmental protection. The optimal operation of reservoir flood control includes various constraints such as upstream and downstream...
详细信息
Reservoirs play an important role in flood control, irrigation, water supply, and environmental protection. The optimal operation of reservoir flood control includes various constraints such as upstream and downstream flood control, dam safety, and irrigation needs. Therefore, it is necessary to build a multi-objective reserve flood control operation preference model. In this experiment, a decomposition based multi-objective evolutionary algorithm was adopted as the basic research method. At the same time, a preference model was combined in the experiment to construct scheduling methods. The results indicate that the multi-objective reserve flood control operation preference model can significantly weaken flood peaks and reduce losses caused by floods. The algorithm has successfully converged to a specific region of the ideal Pareto Front, both of which are extremely close to the ideal Pareto optimal solution set. The inverted generational distance indicators of multi-objective Evolutionary (MOEA/D-PWA) were tested in test sets 3, 4, and 6 with results of 1.73E-03, 2.04E03, and 3.61E-03, respectively. The test results of its spacing index in test sets 1 and 3 are 1.56E-03 and 1.73E-03, respectively. The test results of its hypervolume index in test sets 1 and 3 are 7.59E01 and 6.33E-01, respectively. The results confirmed that MOEA/D-PWA can develop appropriate reservoir flood control scheduling plans and more efficiently utilize flood resources.
This paper considers a reach-avoid differential game between heterogeneous UUVs in a rectangular play region, and a set of Pareto optimal evasion strategies is given. The evader aims to reach the target line without b...
详细信息
ISBN:
(纸本)9798350362077
This paper considers a reach-avoid differential game between heterogeneous UUVs in a rectangular play region, and a set of Pareto optimal evasion strategies is given. The evader aims to reach the target line without being captured, while the pursuers strive to prevent that by capturing the evader. The evader has a minimum turning radius. We focus on constructing a barrier in the time domain for this variation of differential games under great rigorous circumstances in which the opponent possesses great maneuverability and complete information perception ability. First, the restriction of the differential game proposed in this paper is given. Second, the Trajectory-Tree planning method with continuous state action is given, and the decision-making mechanism of both sides is explained. We build a mechanism for modifying UUV's rationality, and the problem of barrier construction is transformed into multi-objectiveoptimization. Then, a variation of the multi-objective optimization algorithm is presented to acquire the Pareto evasion strategy set. Finally, the effectiveness of the algorithm has been verified in a confrontation with multi-pursuers.
In an effort to encourage industries to switch from fossil fuels to renewable energy resources for supplying their energy demands, the exergy and financial aspects of a thermodynamic energy generation system were stud...
详细信息
In an effort to encourage industries to switch from fossil fuels to renewable energy resources for supplying their energy demands, the exergy and financial aspects of a thermodynamic energy generation system were studied. The suggested system was modeled by MATLAB commercial software to assess the decision -making parameters affecting power generation, cooling capacity, and to produce hydrogen. The objective functions of this study were exergy efficiency and cost rate, while the temperatures at the inlet of the turbine and the evaporator, irradiated solar energy, mass flow rate, and surface area of the collector were the decision -making variables. The model was optimized via MOPSO and its results were compared with two widely utilized algorithms, namely NSGA-II and SPEA-II. The comparison results indicated that MOPSO surpassed other two optimizationalgorithm resulting in exergy efficiency and cost rate of 2.11 % and 21.14 $/h, respectively. According to this method, the optimum generated power was equal to 21.01 kW. Eventually, this system was utilized and evaluated in the city of Semnan, Iran. The performance results of the system in Semnan showed that the annual power output, taking into account the changes in radiation and ambient temperature, is between 316667.4 and 428080.5 kW. Also, the amount of hydrogen production is between 1503.66 and 1534.997 kg.
This paper introduces a tool designed to optimize electric vehicle (EV) charging infrastructures within the smart grid framework. The tool utilizes a multi -objective approach and is programmed in Python. It enables d...
详细信息
This paper introduces a tool designed to optimize electric vehicle (EV) charging infrastructures within the smart grid framework. The tool utilizes a multi -objective approach and is programmed in Python. It enables dynamic management of energy distribution among different EV charging infrastructures, addressing scenarios where surplus photovoltaic (PV) power generation exceeds charging demands but faces challenges due to storage costs and electric energy transmission rates to alternative infrastructures. In instances of low PV production relative to charging demand, thc algorithm strategically selects thc optimal procurement strategy. either purchasing electric energy from neighboring infrastructures or utilizing surplus PV energy for direct charging. The tool empowers stakeholders to make informed decisions by facilitating comparisons between the cost of storing electric energy locally and the expense of procuring it from external sources, thereby enhancing the efficiency and cost-effectiveness of EV charging infrastructures in the smart grid ecosystem. Extensive simulations and case studies demonstrate the efficacy of the proposed approach, showcasing its potential to optimize energy distribution and promote sustainable practices within the EV charging domain.
Using an index fund is a popular strategy that is designed to simulate the behavior of a market index and obtain the excess return that is more stable than other mutual funds. In setting up an index fund, investors mu...
详细信息
Using an index fund is a popular strategy that is designed to simulate the behavior of a market index and obtain the excess return that is more stable than other mutual funds. In setting up an index fund, investors must first choose a small number of stocks and then assign a weight to each selected stock. However, with traditional methods, investors hardly determine how well the designed index fund can mimic the market index. The main objective of this paper is to demonstrate the improvement of index fund performance by using a multi-objective optimization algorithm that can assign weights automatically.
Artificial bee colony algorithm as a recent meta-heuristic algorithm, inspired from the foraging behavior of honey bees, can be considered as a proper technique to handle optimization problems. In this paper, a multi-...
详细信息
Artificial bee colony algorithm as a recent meta-heuristic algorithm, inspired from the foraging behavior of honey bees, can be considered as a proper technique to handle optimization problems. In this paper, a multi-objective artificial bee colony algorithm is introduced in which an archive is defined to store non-dominated solutions. Furthermore, to reduce computations and to have evenly distributed solutions, the archive is pruned using a technique based on neighborhood radius concepts. A group of bees that is responsible for improvement of the solutions chooses and exploits one solution of the archive. Because of the definition of neighborhood radius and retaining adjacent solutions, the remaining solutions have an equal chance to be selected by onlooker bees. In order to examine the proposed algorithm, some benchmark functions are used and the results are compared with true Pareto fronts. Moreover, the algorithm is utilized to optimize the coefficients of a new combined controller applied to a ball-beam system. In fact, the proposed controller is a combination of robust decoupled sliding mode and adaption laws based on the gradient decent method. The objective functions are considered as the integral time of absolute of errors of the ball position and the beam angle that should be minimized with a constraint on the control effort. To evaluate and validate the suggested approach, the obtained time responses of the ball-beam system are compared with those of other recently reported controllers.
Performing scientific and accurate forecasting and realizing the quantitative description of uncer-tainties in air quality remain challenging prospects. Because of the strong volatility and uncertainty of air pollutan...
详细信息
Performing scientific and accurate forecasting and realizing the quantitative description of uncer-tainties in air quality remain challenging prospects. Because of the strong volatility and uncertainty of air pollutant concentrations, this problem increases in difficulty when multiple requirements are considered. In this study, a novel air quality deterministic and probabilistic forecasting system based on hesitant fuzzy sets and nonlinear robust outlier correction was proposed to realize air quality early warning. The proposed system solves the non-stochastic non-deterministic problem in air quality forecasting considering a novel hesitant fuzzy time series forecasting model wherein the intervals are partitioned by different approaches with optimal weights determined by the multi-objective JAYA algorithm. The forecasting performance is further enhanced with the introduction of a new nonlinear error correction model based on an outlier robust extreme learning machine and multi-objective JAYA algorithm, and the quality of the solution obtained is verified by sensitivity analysis. However, point forecast information alone is not sufficient to facilitate the rational integration of pollution control measures. Therefore, this study conducts probabilistic forecasting and constructs proper prediction intervals based on the optimal distribution of the forecasting residuals. By comparing the results with typical counterparts and comparison models considering multiple metrics, the experimental results confirmed the improvement scheme proposed in this study on the traditional fuzzy time series forecasting method while the effectiveness of applying the proposed system to air quality early warning was confirmed as well. (c) 2021 Elsevier B.V. All rights reserved.
暂无评论