A fast water level optimal control method based on two stage analysis for long term power generation scheduling of hydropower station

He, Zhongzheng; Zhou, Jianzhong; Hui, Qing; Jia, Benjun; He, Feifei; Liu, Guangbiao; Feng, Kuaile

doi:10.1016/j.energy.2020.118531

Cited by 13 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Case Study [283] Develop an improved optimal method to control water levels, considering the two-stage analysis of LTHS and adjustable policy for the target outflow.…”

Section: Ref Main Goalmentioning

confidence: 99%

Dam System and Reservoir Operational Safety: A Meta-Research

Badr,

Li,

El-Dakhakhni

2023

Water

View full text Add to dashboard Cite

Dams are critical infrastructure necessary for water security, agriculture, flood risk management, river navigation, and clean energy generation. However, these multiple, and often conflicting, objectives introduce complexity in managing dam operations. In addition, dam infrastructure has been evolving as complex systems-of-systems with multiple interacting components and subsystems, all susceptible to a wide range of uncertainties. Such complexities and uncertainties have triggered extensive research initiatives focused on dam systems and reservoir operational safety. Focusing on the latter, this paper meta-researches (conducts research-on-research) previously published studies to identify the critical research gaps and propose future research directions. In this respect, this paper first performs a quantitative analysis of the pertinent literature, using text mining and subsequent topic modeling, to identify and classify major and uncover latent topics in the field. Subsequently, qualitative analysis is conducted to critically review the identified topics, exploring the concepts, definitions, modeling tools, and major research trends. Specifically, the study identified seven topics: optimization models; climate change; flood risk; inflow forecasting; hydropower generation; water supply management; and risk-based assessment and management. The study also presents three main research gaps associated with the limitations in modeling concepts, modeling tools capabilities, and the lack of resilience-guided management of dam operational safety. Overall, this study presents a road map of the currently available dam and reservoir operational safety research and associated knowledge gaps, as well as potential future research directions to ensure the resilience of such critically important infrastructure, especially in the age of climate change.

show abstract

“…Case Study [283] Develop an improved optimal method to control water levels, considering the two-stage analysis of LTHS and adjustable policy for the target outflow.…”

Section: Ref Main Goalmentioning

confidence: 99%

Dam System and Reservoir Operational Safety: A Meta-Research

Badr,

Li,

El-Dakhakhni

2023

Water

View full text Add to dashboard Cite

show abstract

“…Pumped storage hydroelectric (PSH) is related to hydroturbine conversion efficiency, water flow rate, and water height. The output of the PSH unit [43] is expressed as follows:…”

Section: Pumped Storage Hydro Modelmentioning

confidence: 99%

“…Pumped storage hydroelectric (PSH) is related to hydroturbine conversion efficiency, water flow rate, and water height. The output of the PSH unit [43] is expressed as follows:

P_{h} = K η_{j} Q_{j} h_{j}

where

P_{h}

is the output of the PSH, K is the hydroturbine conversion efficiency,

η_{j}

is the efficiency of the PSH station,

Q_{j}

is the water flow rate passing through the turbine j , and

h_{j}

is the net water height of the power station.…”

Section: Re Generation Model and Load Modelmentioning

confidence: 99%

A novel deep reinforcement learning enabled agent for pumped storage hydro‐wind‐solar systems voltage control

Huang

Zhang

et al. 2021

IET Renewable Power Gen

View full text Add to dashboard Cite

With the large‐scale penetration of wind and solar energies in the power system, the randomness of this renewable energy increases the non‐linear characteristics and uncertainty of the system, which causes a mismatch between renewable energy generation and load demand and it will badly affect the bus voltage control of distribution network. In this context, this study applies pumped storage hydroelectric (PSH) which tracks the load variation rapidly, operate flexibly and reliably to balance the power of the system to minimize the bus voltage deviation. Moreover, to obtain the optimal control policy of PSH, a deep‐reinforcement‐learning algorithm, that is, deep deterministic policy gradient, is utilized to train the agent to address the continuous transformation of the pumped storage hydro‐wind‐solar (PSHWS) system. The performance of a well‐trained agent was evaluated on the IEEE 30‐bus power system. Simulation results show that the proposed method achieves an improvement of 21.8% in cumulative deviation per month, which implies that it can keep the system operating in a safe voltage range more effectively.

show abstract

“…Advanced methods like artificial intelligence (AI), machine learning (ML), and deep reinforcement learning (DRL) may be used to analyze massive data in the best possible ways to make the best conclusion. The aforementioned methods take a long-term goal into account and can provide the best or nearly best control decisions [5]. By increasing the amount of training data, the aforementioned methodologies' accuracy and precision may be f urther improved, as can the effectiveness of automated decision -making [6].…”

Section: Introductionmentioning

confidence: 99%

Smart Cities Using Machine Learning and Intelligent Applications (ITALIC)

Prawiyogi¹,

Purnama

Meria

2022

ITALIC

View full text Add to dashboard Cite

The goal of smart cities is to properly manage to expand urbanization, Reduce energy usage, Enhance the economic and quality of life of the locals while also preserving the environment conditions, and improve people's ability to use and adapt modern technology used in information and communication efficiently (ICT). Information and communication technology (ICT) is central to the concept of smart cities because it facilitates the development of policies, decision-making, implementation, and, eventually, the provision of useful services. This review's main objective is to examine how machine learning, deep reinforcement learning (DRL), and artificial intelligence are advancing smart cities. The previous strategies are effectively utilized to provide the best policies possible for a number of challenging issues relating to smart cities. The uses of the earlier methods are thoroughly discussed in this survey. in intelligent transportation systems (ITSs), Cybersecurity, as well as smart grid energy efficiency (SGs), ensuring the best 5G and beyond 5G (B5G) networking service, as well as a smart city with a smart health system, by effectively using unmanned aerial vehicles (UAVs). Finally, we list a number of the above-mentioned research problems and potential future directions approaches can be extremely helpful in bringing the idea of a smart city to life.

show abstract

A fast water level optimal control method based on two stage analysis for long term power generation scheduling of hydropower station

Cited by 13 publications

References 43 publications

Dam System and Reservoir Operational Safety: A Meta-Research

Dam System and Reservoir Operational Safety: A Meta-Research

A novel deep reinforcement learning enabled agent for pumped storage hydro‐wind‐solar systems voltage control

Smart Cities Using Machine Learning and Intelligent Applications (ITALIC)

Contact Info

Product

Resources

About