Flight trajectory optimization is a crucial aspect of aircraft design, and the numerical algorithms for trajectory optimization have always been a hot and challenging topic in domestic and international research. Star...
详细信息
This paper investigates the application of Particle Swarm optimization (PSO) in enhancing the Automatic Generation control (AGC) of thermal power and pumped storage units. Pumped storage power stations, recognized for...
详细信息
ISBN:
(纸本)9798350375145;9798350375138
This paper investigates the application of Particle Swarm optimization (PSO) in enhancing the Automatic Generation control (AGC) of thermal power and pumped storage units. Pumped storage power stations, recognized for their flexibility in peak-regulation, play a crucial role in addressing renewable energy fluctuations. Traditional PID control methods, while simple, lack dynamic adaptability, necessitating manual parameter adjustments. The PSO algorithm is introduced to optimize PID parameters, demonstrating improved dynamic performance and robustness. The study establishes a two-area automatic generation control model, incorporating detailed modeling of thermal power and pumped storage components. The PSO optimization process, utilizing the Integral of Time-weighted Absolute Error (ITAE) as a performance metric, is explained. Results from the PSO-optimized system are compared with traditional methods, showcasing superior anti-interference and rapid response capabilities. The study concludes that pumped storage power stations, coupled with intelligent algorithms like PSO, contribute significantly to frequency control systems, offering guidance for future integration of various generating units.
This research aims to solve many problems people face when moving to a new place, such as housing, food, transportation, language differences and optimization. By creating recommendations, it is aimed to provide self-...
详细信息
In two-dimensional space, this paper aims at the problems of slow convergence and poor real-time performance of existing path planning algorithms. A free growing tree algorithm (SOGT) is proposed. The algorithm mainly...
详细信息
This research paper aims to model and simulate the wind turbine emulator (WTE), which is required to build a test rig for wind turbine generator (WTG) condition monitoring. The WTE uses a D.C. machine to imitate wind ...
详细信息
The aim of this article is to address the issues of the load frequency control (LFC) of IMS-HPS comprising SPV, BGTG, and BDEG with BESS. As the presence and the increased RES penetration introduces a high level of ch...
详细信息
In order to improve the transportation efficiency of unmanned underground phosphate ore transport vehicles, ensure safety, and control costs, this paper constructs a vehicle scheduling optimization model based on an i...
详细信息
The wind turbine(WT) adopts the Step Inertia control (SIC) strategy to participate in the frequency regulation of the power grid, which helps to suppress the lowest point of frequency drop, but the SIC strategy will b...
详细信息
ISBN:
(纸本)9798350375145;9798350375138
The wind turbine(WT) adopts the Step Inertia control (SIC) strategy to participate in the frequency regulation of the power grid, which helps to suppress the lowest point of frequency drop, but the SIC strategy will bring a huge power dip in the speed recovery stage, resulting in a secondary drop in the system frequency. In this paper, the Particle Swarm optimization algorithm is used to optimize the power curve of SIC, on this basis, an improved SIC strategy based on the optimal power curve is constructed. The simulation results show that the proposed improved SIC strategy can avoid the secondary frequency drop.
Datasets and models are two key artifacts in machine learning (ML) applications. Although there exist tools to support dataset and model developers in managing ML artifacts, little is known about how these datasets an...
详细信息
ISBN:
(纸本)9798400705915
Datasets and models are two key artifacts in machine learning (ML) applications. Although there exist tools to support dataset and model developers in managing ML artifacts, little is known about how these datasets and models are integrated into ML applications. In this paper, we study how datasets and models in ML applications are managed. In particular, we focus on how these artifacts are stored and versioned alongside the applications. After analyzing 93 repositories, we identified the most common storage location to store datasets and models is the file system, which causes availability issues. Notably, large data and model files, exceeding approximately 60 MB, are stored exclusively in remote storage and downloaded as needed. Most of the datasets and models lack proper integration with the version control system, posing potential traceability and reproducibility issues. Additionally, although datasets and models are likely to evolve during the application development, they are rarely updated in application repositories.
Models based on dynamic neural networks such as DeBERTa and Vision Transformers ViT have disrupted the two fields. However, there is one complication - their performance requires so much computation which limits its r...
详细信息
暂无评论