Wind energy's role in the global electric grid is set to expand significantly. New York State alone anticipates offshore wind farms (WFs) contributing 9GW by 2035. Integration of energy storage emerges as crucial ...
详细信息
ISBN:
(数字)9798350352528
ISBN:
(纸本)9798350352535
Wind energy's role in the global electric grid is set to expand significantly. New York State alone anticipates offshore wind farms (WFs) contributing 9GW by 2035. Integration of energy storage emerges as crucial for this advancement. In this study, we focus on a WF paired with a captive battery energy storage system (BESS). We aim to ascertain the power capacity credit for a BESS with specified nameplate energy (MWh) and power capacity (MW). Unlike prior methods rooted in reliability theory, we define a power alignment function, which leads to a straightforward definition of capacity and incremental capacity for the BESS. We develop a solution method based on a linear programming formulation. Our analysis utilizes wind data, collected by NYSERDA off Long Island's coast and load demand data from NYISO. Additionally, we present theoretical insights into BESS sizing and a key time-series property influencing BESS capacity, aiding in simulating wind and demand for estimating BESS energy requirements.
linear programming is a method for solving linear optimization problems with constraints, widely met in real-world applications. In the vast majority of these applications, the number of constraints is significantly l...
详细信息
linear programming is a method for solving linear optimization problems with constraints, widely met in real-world applications. In the vast majority of these applications, the number of constraints is significantly larger than the number of variables. Since the crucial subject of these problems is to detect the constraints that will be verified as equality in an optimal solution, there are methods for investigating such constraints to accelerate the whole process. In this paper, a technique named proximity technique is addressed, which under a proposed theoretical framework gives an ascending order to the constraints in such a way that those with low ranking are characterized of high priority to be binding. Under this framework, two new linear programming optimization algorithms are introduced, based on a proposed Utility matrix and a utility vector accordingly. For testing the addressed algorithms firstly a generator of 10,000 random linear programming problems of dimension n with m constraints, where , is introduced in order to simulate as many as possible real-world problems, and secondly, real-life linear programming examples from the NETLIB repository are tested. A discussion of the numerical results is given. Furthermore, already known methods for solving linear programming problems are suggested to be fitted under the proposed framework.
Traditional methods for classifying and recognizing musical note features suffer from low accuracy. In response, we propose a music note feature recognition method leveraging the Dynamic Time Warping (DTW) algorithm. ...
详细信息
ISBN:
(数字)9798350374407
ISBN:
(纸本)9798350374414
Traditional methods for classifying and recognizing musical note features suffer from low accuracy. In response, we propose a music note feature recognition method leveraging the Dynamic Time Warping (DTW) algorithm. The approach begins with an in-depth analysis of musical notes, utilizing the similarity matrix of note similarity under the standard distance of notes as the DTW distance matrix. From this matrix, we derive a criterion for selecting note features, which serves as the objective function for optimizing the subset of music note features. By operating with multiple populations, we obtain the expected value of higher musical note classification accuracy from various populations, serving as the quality evaluation for multi-population classification. Subsequently, a global objective evaluation is conducted on each musical note based on the evaluation values, facilitating music note classification and recognition. Experimental results validate the efficacy of the proposed method, demonstrating its ease of adoption in computer-assisted systems. Moreover, it achieves higher accuracy in music note feature classification and recognition, while reducing the overall recognition time compared to existing musical note feature extraction methods.
This paper presents a study on the optimization of recipes based on genetic algorithms and NSGA-II for multi-objective design. To address recipe optimization under different objectives, the study divides the optimizat...
详细信息
ISBN:
(数字)9798331527624
ISBN:
(纸本)9798331527631
This paper presents a study on the optimization of recipes based on genetic algorithms and NSGA-II for multi-objective design. To address recipe optimization under different objectives, the study divides the optimization into single-objective and multi-objective categories, establishing a single-objective optimization model based on GA and a multi-objective optimization model based on NSGA-II. For the single-objective model, the objective functions include maximizing the protein amino acid score and minimizing meal costs, while the multi-objective optimization aims to simultaneously satisfy both objectives. For the maximization of amino acid scores, men improved from 93.5 to 98.1077, and women from 89 to 96.1483. In the case of minimizing meal costs, men improved from 18.5 to 6.5, and women from 16 to 6. The multi-objective optimization model achieved notable results, increasing the amino acid scores for men from 80 to 98.5064 and reducing meal costs from 28 to 6, while for women, the scores improved from 81 to 97.0679 and the costs decreased from 45 to 3. The comprehensive superior evaluation values were calculated as [99.2373, 90.9347], [97.2297, 88.9271], and [90.2272, 81.9246], with the multi-objective optimization model demonstrating the most effective performance.
Despite the remarkable performance and generalization levels of deep learning models in a wide range of artificial intelligence tasks, it has been demonstrated that these models can be easily fooled by the addition of...
详细信息
Despite the remarkable performance and generalization levels of deep learning models in a wide range of artificial intelligence tasks, it has been demonstrated that these models can be easily fooled by the addition of imperceptible yet malicious perturbations to natural inputs. These altered inputs are known in the literature as adversarial examples. In this paper, we propose a novel probabilistic framework to generalize and extend adversarial attacks in order to produce a desired probability distribution for the classes when we apply the attack method to a large number of inputs. This novel attack paradigm provides the adversary with greater control over the target model, thereby exposing, in a wide range of scenarios, threats against deep learning models that cannot be conducted by the conventional paradigms. We introduce four different strategies to efficiently generate such attacks, and illustrate our approach by extending multiple adversarial attack algorithms. We also experimentally validate our approach for the spoken command classification task and the Tweet emotion classification task, two exemplary machine learning problems in the audio and text domain, respectively. Our results demonstrate that we can closely approximate any probability distribution for the classes while maintaining a high fooling rate and even prevent the attacks from being detected by label-shift detection methods.
Hyperparameter optimization (HPO) is paragon to maximize performance when designing machine learning models. Among different HPO methods, Genetic Algorithm (GA) based optimization is considered effective because it al...
详细信息
ISBN:
(数字)9798350308365
ISBN:
(纸本)9798350308372
Hyperparameter optimization (HPO) is paragon to maximize performance when designing machine learning models. Among different HPO methods, Genetic Algorithm (GA) based optimization is considered effective because it allows a wide and diverse range of solutions to be explored. However, GA's exploratory nature makes this type of algorithm to evaluate many solutions that do not improve the overall performance. This is specially costly when the objective function to be evaluated is time-consuming, like in the HPO field. In this paper, we propose an efficient hybrid algorithm that is able to reduce computational cost by combining deep reinforcement learning with the Biased Random Key Genetic Algorithm (BRKGA), a variant of genetic algorithms. Our reinforcement learning agent has a decision-making role during the population's fitness calculation, in which it filters out chromosomes that would not improve the overall fitness of the population. The agent uses small amounts of pre-trained data to identify trends in potentially good solutions, and carry out its decision process. We conduct experiments on eight different datasets to assess the effectiveness of the proposed method, and the results show that the proposed method can significantly reduce the computation time of hyperparameter search using BRKGA (up to 44% reduction in computational time) without compromising the quality of the solution (no statistically difference in results).
Aiming at the problems of high cost and difficult maintenance in the practical application of the traditional "vehicle-ground cooperation" train positioning technology in special section railway projects. In...
详细信息
ISBN:
(数字)9798350351033
ISBN:
(纸本)9798350351040
Aiming at the problems of high cost and difficult maintenance in the practical application of the traditional "vehicle-ground cooperation" train positioning technology in special section railway projects. In this paper, a method for autonomous positioning of railway trains based on multisource information fusion is proposed. First, develop a kilometer mark detection thread based on VINS Fusion, and build a lightweight optical symbol recognition system to identify the character area of the kilometer mark to obtain the position information of the electronic map. Secondly, based on the LSD line detection algorithm combined with the way of dynamically expanding the line, the coordinates of the vertex coordinates of the kilometer mark are extracted. Then, a global optimization objective function containing the position information constraints of the kilometer mark is established, and the global positioning accuracy is improved through the graph optimization method. This solves the problem that existing intelligent positioning of railway trains cannot eliminate accumulated errors in the absence of loop closure detection. Finally, the semi-physical simulation results show that the positioning error of the original positioning system can be reduced by more than 57%.
In modern power systems, photovoltaic (PV) and battery energy storage systems (BESS) must be adopted appropriately due to their complicated inherent characteristics. This paper has constructed a multi-objective optimi...
详细信息
ISBN:
(数字)9798350354379
ISBN:
(纸本)9798350354386
In modern power systems, photovoltaic (PV) and battery energy storage systems (BESS) must be adopted appropriately due to their complicated inherent characteristics. This paper has constructed a multi-objective optimization problem to balance technical, economic, and environmental objectives related to PV-BESS unit allocation and power factor (pf) in the radial distribution system (RDS). A complete review of all three planning factors aids in effective and dependable PV modules, BESS units, and RDS energy management strategy (EMS) planning. A novel multi-objective Greylag Goose Optimization (MOGGO) technique is used to minimize total active power loss, net annual cost, and environmental emissions in order to obtain optimal decision variables within operational constraints. The proposed technique is validated on an IEEE 33 bus RDS, and extensive study shows its benefits. The findings demonstrate that MOGGO's effective and competent solutions improve RDS's technical, economic, and environmental benefits when combined with PV and BESS.
Recent theoretical results on adversarial multi-class classification showed a similarity to the multi-marginal formulation of Wasserstein-barycenter in optimal transport. Unfortunately, both problems suffer from the c...
详细信息
Effective out-of-distribution (ODD) detection is crucial for the safe deployment of machine learning models in real-world scenarios. However, recent work has shown that ODD detection methods are vulnerable to adversar...
详细信息
ISBN:
(数字)9798331517113
ISBN:
(纸本)9798331517120
Effective out-of-distribution (ODD) detection is crucial for the safe deployment of machine learning models in real-world scenarios. However, recent work has shown that ODD detection methods are vulnerable to adversarial attacks, potentially leading to critical failures in high-stakes applications. This discovery has motivated work on robust ODD detection methods that are capable of maintaining performance under various attack settings. Prior approaches have made progress on this problem but face a number of limitations: often only exhibiting robustness to attacks on ODD data or failing to maintain strong clean performance. In this work, we adapt an existing robust classification framework, TRADES, extending it to the problem of robust ODD detection and discovering a novel objective function. Recognising the critical importance of a strong clean/robust trade-off for ODD detection, we introduce an additional loss term which boosts classification and detection performance. Our approach, called HALO (Helper-based Adver-sariaL ODD detection), surpasses existing methods and achieves state-of-the-art performance across a number of datasets and attack settings. Extensive experiments demonstrate an average AUROC improvement of 3.15 in clean settings and 7.07 under adversarial attacks when compared to the next best method. Furthermore, HALO exhibits resistance to transferred attacks, offers tuneable performance through hyperparameter selection, and is compatible with existing ODD detection frameworks out-of-the-box, leaving open the possibility of future performance gains. Code is available at: https://***/hugo0076/HALO.
暂无评论