当前位置: X-MOL 学术arXiv.cs.SY › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
HydroPower Plant Planning for Resilience Improvement of Power Systems using Fuzzy-Neural based Genetic Algorithm
arXiv - CS - Systems and Control Pub Date : 2021-06-16 , DOI: arxiv-2106.12042
Akbal Rain, Mert Emre Saritac

This paper will propose a novel technique for optimize hydropower plant in small scale based on load frequency control (LFC) which use self-tuning fuzzy Proportional- Derivative (PD) method for estimation and prediction of planning. Due to frequency is not controlled by any dump load or something else, so this power plant is under dynamic frequency variations that will use PD controller which optimize by fuzzy rules and then with neural deep learning techniques and Genetic Algorithm optimization. The main purpose of this work is because to maintain frequency in small-hydropower plant at nominal value. So, proposed controller means Fuzzy PD optimization with Genetic Algorithm will be used for LFC in small scale of hydropower system. The proposed schema can be used in different designation of both diesel generator and mini-hydropower system at low stream flow. It is also possible to use diesel generator at the hydropower system which can be turn off when Consumer demand is higher than electricity generation. The simulation will be done in MATLAB/Simulink to represent and evaluate the performance of this control schema under dynamic frequency variations. Spiking Neural Network (SNN) used as the main deep learning techniques to optimizing this load frequency control which turns into Deep Spiking Neural Network (DSNN). Obtained results represented that the proposed schema has robust and high-performance frequency control in comparison to other methods.

中文翻译:

使用基于模糊神经的遗传算法提高电力系统弹性的水电站规划

本文将提出一种基于负荷频率控制 (LFC) 的小规模水电站优化新技术,该技术使用自调整模糊比例微分 (PD) 方法进行规划估计和预测。由于频率不受任何卸荷或其他东西的控制,因此该电厂处于动态频率变化下,将使用 PD 控制器通过模糊规则进行优化,然后使用神经深度学习技术和遗传算法优化。这项工作的主要目的是为了将小水电站的频率维持在额定值。因此,所提出的控制器意味着具有遗传算法的模糊局部放电优化将用于小规模水电系统的 LFC。所提出的方案可用于柴油发电机和小水电系统在低流量下的不同指定。也可以在水电系统中使用柴油发电机,当消费者需求高于发电量时,可以关闭柴油发电机。仿真将在 MATLAB/Simulink 中完成,以表示和评估该控制方案在动态频率变化下的性能。尖峰神经网络 (SNN) 用作主要的深度学习技术来优化这种负载频率控制,从而转变为深度尖峰神经网络 (DSNN)。获得的结果表明,与其他方法相比,所提出的模式具有鲁棒性和高性能的频率控制。也可以在水电系统中使用柴油发电机,当消费者需求高于发电量时,可以关闭柴油发电机。仿真将在 MATLAB/Simulink 中完成,以表示和评估该控制方案在动态频率变化下的性能。尖峰神经网络 (SNN) 用作主要的深度学习技术来优化这种负载频率控制,从而转变为深度尖峰神经网络 (DSNN)。获得的结果表明,与其他方法相比,所提出的模式具有鲁棒性和高性能的频率控制。也可以在水电系统中使用柴油发电机,当消费者需求高于发电量时,可以关闭柴油发电机。仿真将在 MATLAB/Simulink 中完成,以表示和评估该控制方案在动态频率变化下的性能。尖峰神经网络 (SNN) 用作主要的深度学习技术来优化这种负载频率控制,从而转变为深度尖峰神经网络 (DSNN)。获得的结果表明,与其他方法相比,所提出的模式具有鲁棒性和高性能的频率控制。尖峰神经网络 (SNN) 用作主要的深度学习技术来优化这种负载频率控制,从而转变为深度尖峰神经网络 (DSNN)。获得的结果表明,与其他方法相比,所提出的模式具有鲁棒性和高性能的频率控制。尖峰神经网络 (SNN) 用作主要的深度学习技术来优化这种负载频率控制,从而转变为深度尖峰神经网络 (DSNN)。获得的结果表明,与其他方法相比,所提出的模式具有鲁棒性和高性能的频率控制。
更新日期:2021-06-25
down
wechat
bug