Deep-Reinforcement-Learning-Based Autonomous Voltage Control for Power Grid Operations

Duan, Jiajun; Shi, Di; Diao, Ruisheng; Li, Haifeng; Wang, Zhiwei; Zhang, Bei; Bian, Desong; Yi, Zhehan

doi:10.1109/tpwrs.2019.2941134

Cited by 271 publications

(111 citation statements)

References 7 publications

Supporting

Mentioning

109

Contrasting

Order By: Relevance

“…A subsystem level voltage controls based on RL were considered in [47,48] and DRL in [49] and [50]. References [47,48] considered voltage control through Q-learning used to learn the optimal control law for reactive power control.…”

Section: Control In Normal Operating Statementioning

confidence: 99%

“…A DQN algorithm is deployed at the slower time scale (every hour) to configure a set of shunt capacitors to minimize the longterm discounted voltage deviations. Work presented in [50] considered two DRL methods (DQN and deep deterministic policy gradient (DDPG)) for subsystem level voltage control with observation that DDPG method offered much better performances after a sufficient number of training scenarios.…”

Section: Control In Normal Operating Statementioning

confidence: 99%

“…DQN is most used DRL method (again, its success in other domains is the main reason for it). An exception is work presented in [50] where DDPG offered better performances with respect to DQN.…”

Section: Observationsmentioning

confidence: 99%

“…• More considerations of other DRL methods (other than DQN since it cannot solve the problems with large continuous control space and where te optimal policy is stochastic) is expected. Reference [50] is a good example showing better performances of DDPG with respect to DQN for particular problem. Bayesian DRL is particularly interesting for future considerations.…”

Section: Perspectivesmentioning

confidence: 99%

See 3 more Smart Citations

(Deep) Reinforcement learning for electric power system control and related problems: A short review and perspectives

Glavić

2019

Annual Reviews in Control

100

View full text Add to dashboard Cite

This paper reviews existing works on (deep) reinforcement learning considerations in electric power system control. The works are reviewed as they relate to electric power system operating states (normal, preventive, emergency, restorative) and control levels (local, household, microgrid, subsystem, wide-area). Due attention is paid to the control-related problems considerations (cyber-security, big data analysis, short-term load forecast, and composite load modelling). Observations from reviewed literature are drawn and perspectives discussed. In order to make the text compact and as easy as possible to read, the focus is only on the works published (or "in press") in journals and books while conference publications are not included. Exceptions are several work available in open repositories likely to become journal publications in near future. Hopefully this paper could serve as a good source of information for all those interested in solving similar problems.

show abstract

Section: Control In Normal Operating Statementioning

confidence: 99%

Section: Control In Normal Operating Statementioning

confidence: 99%

Section: Observationsmentioning

confidence: 99%

Section: Perspectivesmentioning

confidence: 99%

See 2 more Smart Citations

(Deep) Reinforcement learning for electric power system control and related problems: A short review and perspectives

Glavić

2019

Annual Reviews in Control

100

View full text Add to dashboard Cite

show abstract

“…In addition, the security conditions of the power grid are also becoming more demanding. Thus, the automatic power grid dispatching system is urgently needed to accomplish the tasks effectively [6,7].…”

Section: Introductionmentioning

confidence: 99%

Flexible automatic detection for security management of dispatching data network

et al. 2020

View full text Add to dashboard Cite

Power grid dispatching is among the forefront issues in the power industry for it can highly influence the efficiency of electricity-related industries. At present, power grid dispatching is usually managed manually, which is quite time-consuming with the continuous growth of scale and complexity of electric power systems. To mitigate the time cost of power grid dispatching, an automatic power grid dispatching system is proposed. The system contains devices configuration detection, flexible and automatic device detection and vertical encryption to ensure the efficiency, adaptability and security of power gird dispatching. In this paper, modeling and algorithm details of the automatic power grid dispatching system are presented, and the effectiveness and efficiency of the proposed system was evaluated with power grid data in Kunming, China.

show abstract

An intelligent load balancing algorithm for 5G‐satellite networks

Bello,

Pillai,

Sadiq

2024

Satell Commun Network

View full text Add to dashboard Cite

SummaryCellular networks are projected to deal with an immense rise in data traffic, as well as an enormous and diverse device, plus advanced use cases, in the nearest future; hence, future 5G networks are being developed to consist of not only 5G but also different radio access technologies (RATs) integrated. In addition to 5G, the user's device (UD) will be able to connect to the network via LTE, WiMAX, WiFi, Satellite and other technologies. On the other hand, Satellite has been suggested as a preferred network to support 5G use cases. However, achieving load balancing is essential to guarantee an equal amount of traffic distributed between different RATs in a heterogeneous wireless network; this would enable optimal utilisation of the radio resources and lower the likelihood of call blocking/dropping. This study presented an artificial intelligent‐based application in heterogeneous wireless networks and proposed an enhanced particle optimisation (EPSO) algorithm to solve the load balancing problem in 5G‐Satellite networks. The algorithm uses a call admission control strategy to admit users into the network to ensure that users are evenly distributed on the network. The proposed algorithm was compared with the Artificial Bee Colony and Simulated Annealing algorithm using three performance metrics: throughput, call blocking and fairness. Finally, based on the experimental findings, results outcomes were analysed and discussed.

show abstract

Deep-Reinforcement-Learning-Based Autonomous Voltage Control for Power Grid Operations

Cited by 271 publications

References 7 publications

(Deep) Reinforcement learning for electric power system control and related problems: A short review and perspectives

(Deep) Reinforcement learning for electric power system control and related problems: A short review and perspectives

Flexible automatic detection for security management of dispatching data network

An intelligent load balancing algorithm for 5G‐satellite networks

Contact Info

Product

Resources

About