A deep reinforcement learning method for managing wind farm uncertainties through energy storage system control and external reserve purchasing

Yang, Jierui; Yang, Ming; Wang, M.X.; Du, Puliang; Yu, Yixiao

doi:10.1016/j.ijepes.2020.105928

Cited by 77 publications

(22 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The previously designed penalty goes some way in addressing this by making sure the agent does not purchase more energy than available, but it does not explicitly tell the agent to smooth its load profile, that is buy similar amounts of energy at each time step. To address this explicitly, the reward termed has been designed and is given in Equation (25). This positive reward has a maximum value of 1 when the agent chooses to not buy any energy, and this decreases linearly towards 0 as the amount of energy purchased approaches the demand limit.…”

Section: Relation To the Peak Shifting Domainmentioning

confidence: 99%

“…Bhowmik et al 24 proposed the generative method of the machine learning framework for the monitoring and enhancement of reliability in the predictive design of battery interfaces. Yang et al 25 proposed an approach to the charge/discharge and the purchase schedule for the BSS based on deep reinforcement learning (DRL). Chemali et al 26 proposed a new technique utilizing the DRNN in order to estimate the state of charge (SOC) of the BSS interface, where the battery measurements were charted directly into SOC.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Retracted: Optimal peak shifting of a domestic load connected to utility grid using storage battery based on deep Q‐learning network

Al-Gablawy

2020

Int J Energy Res

View full text Add to dashboard Cite

Summary Peak periods are a result of consumers generally using electricity at similar times and periods as each other, for example, turning lights on when returning home from work, or the widespread use of air conditioners during the summer. Without peak shifting, the grid's system operators are forced to use peaked plants to provide additional energy. This operation is incredibly expensive and harmful to the environment due to its high levels of carbon emissions. Battery storage system (BSS) has been proposed to allow purchasing the energy during off‐peak periods for later use, with the primary objective of realizing peak shifting occurred. Multi‐objective optimization with the reinforcement learning technique has been utilized in order to achieve the primary objective, reduce energy consumption, and minimize the consumers' utility bills. The results revealed that the reduction in energy consumption was more than 20%, the consumers' energy bills were minimized, as well as realizing perfect peak shifting. In addition, the strategy attempted to overcharge the battery with about 7% of the time, and promising methods to address this has been proposed as a direction for future research.

show abstract

Section: Relation To the Peak Shifting Domainmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Retracted: Optimal peak shifting of a domestic load connected to utility grid using storage battery based on deep Q‐learning network

Al-Gablawy

2020

Int J Energy Res

View full text Add to dashboard Cite

show abstract

“…To solve the Wind power problem, this research suggested a solution based on deep learning [60]. According to the method, a statistics controller is prepared that straight maps the input findings, such as forecasted Wind lifetime and energy price, to the Wind farm's control actions, such as the fees schedule of the functional energy storage unit and the reserve buying schedule.…”

Section: Deep Learning Techniquesmentioning

confidence: 99%

Wind, Solar, and Photovoltaic Renewable Energy Systems with and without Energy Storage Optimization: A Survey of Advanced Machine Learning and Deep Learning Techniques

et al. 2022

View full text Add to dashboard Cite

Nowadays, learning-based modeling methods are utilized to build a precise forecast model for renewable power sources. Computational Intelligence (CI) techniques have been recognized as effective methods in generating and optimizing renewable tools. The complexity of this variety of energy depends on its coverage of large sizes of data and parameters, which have to be investigated thoroughly. This paper covered the most resent and important researchers in the domain of renewable problems using the learning-based methods. Various types of Deep Learning (DL) and Machine Learning (ML) algorithms employed in Solar and Wind energy supplies are given. The performance of the given methods in the literature is assessed by a new taxonomy. This paper focus on conducting comprehensive state-of-the-art methods heading to performance evaluation of the given techniques and discusses vital difficulties and possibilities for extensive research. Based on the results, variations in efficiency, robustness, accuracy values, and generalization capability are the most obvious difficulties for using the learning techniques. In the case of the big dataset, the effectiveness of the learning techniques is significantly better than the other computational methods. However, applying and producing hybrid learning techniques with other optimization methods to develop and optimize the construction of the techniques is optionally indicated. In all cases, hybrid learning methods have better achievement than a single method due to the fact that hybrid methods gain the benefit of two or more techniques for providing an accurate forecast. Therefore, it is suggested to utilize hybrid learning techniques in the future to deal with energy generation problems.

show abstract

“…The effectiveness of various DQN-based extensions is verified in many fields [21][22][23][24]. However, as a popular DQN-based version, the rainbow algorithm is not competent for the early exploration and later utilization at the same time, adopting the fixed learning rate strategy.…”

Section: Proposed Modified Rainbow-based Solutionmentioning

confidence: 99%

“…The rainbow algorithm proposed in [21] integrates multiple DQN-based extensions, and it shows remarkable performance in demand response [22], predictive panoramic video delivering [23], and wind farm generation control [24]. However, the adaptive learning ability of the rainbow agent remains to be improved.…”

Section: Introductionmentioning

confidence: 99%

A Modified Rainbow-Based Deep Reinforcement Learning Method for Optimal Scheduling of Charging Station

et al. 2022

View full text Add to dashboard Cite

To improve the operating efficiency and economic benefits, this article proposes a modified rainbow-based deep reinforcement learning (DRL) strategy to realize the charging station (CS) optimal scheduling. As the charging process is a real-time matching between electric vehicles ‘(EVs) charging demand and CS equipment resources, the CS charging scheduling problem is duly formulated as a finite Markov decision process (FMDP). Considering the multi-stakeholder interaction among EVs, CSs, and distribution networks (DNs), a comprehensive information perception model was constructed to extract the environmental state required by the agent. According to the random behavior characteristics of the EV charging arrival and departure times, the startup of the charging pile control module was regarded as the agent’s action space. To tackle this issue, the modified rainbow approach was utilized to develop a time-scale-based CS scheme to compensate for the resource requirements mismatch on the energy scale. Case studies were conducted within a CS integrated with the photovoltaic and energy storage system. The results reveal that the proposed method effectively reduces the CS operating cost and improves the new energy consumption.

show abstract

A deep reinforcement learning method for managing wind farm uncertainties through energy storage system control and external reserve purchasing

Cited by 77 publications

References 19 publications

Retracted: Optimal peak shifting of a domestic load connected to utility grid using storage battery based on deep Q‐learning network

Retracted: Optimal peak shifting of a domestic load connected to utility grid using storage battery based on deep Q‐learning network

Wind, Solar, and Photovoltaic Renewable Energy Systems with and without Energy Storage Optimization: A Survey of Advanced Machine Learning and Deep Learning Techniques

A Modified Rainbow-Based Deep Reinforcement Learning Method for Optimal Scheduling of Charging Station

Contact Info

Product

Resources

About