Artificial emotional reinforcement learning for automatic generation control of large‐scale interconnected power grids

Yin, Linfei; Yu, Tao; Zhou, Lv; Huang, Linni; Zhang, Xiaoshun; Zheng, Baomin

doi:10.1049/iet-gtd.2016.1734

Cited by 59 publications

(37 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automatic Generation Control (AGC) and Load-Frequency Control (LFC) were considered in [35,[37][38][39][41][42][43][44][45][46] (the objective is to keep frequency in a narrow range around nominal value, for example in Europe [49.8 − 50.2]Hz). AGC and LFC differs in that AGC includes LFC together with generation dispatch function for control of so called area control error that is a parameterized sum of frequency deviation and active power flows over so-called tie-lines (the lines connecting subsystems within a larger interconnection).…”

Section: Control In Normal Operating Statementioning

confidence: 99%

“…Integral RL [23] for load frequency regulation in multi-area electric power systems was suggested in [45]. Emotional RL was proposed in [46] for AGC where the controller integrates two parts: RL and artificial emotion (this part is a function of the elements of RL (control, learning rate, reward) and essentially allows embedding domain knowledge).…”

Section: Control In Normal Operating Statementioning

confidence: 99%

See 1 more Smart Citation

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

Glavić

2019

Annual Reviews in Control

111

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%

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

Glavić

2019

Annual Reviews in Control

111

View full text Add to dashboard Cite

show abstract

“…The old machine learning model expresses state changes for action in the first law's physical formula or statistical/probabilistic relations, whereas reinforcement learning does not define the relations between action and state in the learning process. The learning methods of reinforcement learning, called artificial intelligence, are similar to those of humans, attracting attention from many sectors in recent years [54][55][56][57][58][59][60][61][62][63][64][65][66][67][68][69][70].…”

Section: Reinforcement Learningmentioning

confidence: 99%

“…Note, however, that these reinforcement learning algorithms and inquiry and utilization algorithms are dependent on large amounts of learning data and domain information. As a result, they depend on hardware and incur large computation costs [69][70][71][72][73][74][75][76].…”

Section: Reinforcement Learningmentioning

confidence: 99%

A Novel on Transmission Line Tower Big Data Analysis Model Using Altered K-means and ADQL

Jung

2019

Sustainability

View full text Add to dashboard Cite

This study sought to propose a big data analysis and prediction model for transmission line tower outliers to assess when something is wrong with transmission line tower big data based on deep reinforcement learning. The model enables choosing automatic cluster K values based on non-labeled sensor big data. It also allows measuring the distance of action between data inside a cluster with the Q-value representing network output in the altered transmission line tower big data clustering algorithm containing transmission line tower outliers and old Deep Q Network. Specifically, this study performed principal component analysis to categorize transmission line tower data and proposed an automatic initial central point approach through standard normal distribution. It also proposed the A-Deep Q-Learning algorithm altered from the deep Q-Learning algorithm to explore policies based on the experiences of clustered data learning. It can be used to perform transmission line tower outlier data learning based on the distance of data within a cluster. The performance evaluation results show that the proposed model recorded an approximately 2.29%~4.19% higher prediction rate and around 0.8% ~ 4.3% higher accuracy rate compared to the old transmission line tower big data analysis model.

show abstract

“…The conventional reinforcement learning-based AGC controller can achieve a high control performance in large-scale interconnected power systems in normal situations [12,13,15], but it experiences a low control performance in emergency situations. To obtain a better control performance from an AGC controller in large-scale interconnected power systems during an emergency situation, the dimension of many parameters (e.g., Q-value matrix Q, probability distribution matrix P, action set A, and state set S) of conventional reinforcement learning must be increased [25].However, increasing the dimension of these parameters can lead to the overflow of calculation memory, i.e., the curse of dimensionality [26].…”

Section: Introductionmentioning

confidence: 99%

Deep Forest Reinforcement Learning for Preventive Strategy Considering Automatic Generation Control in Large-Scale Interconnected Power Systems

Yin

Zhao

et al. 2018

Applied Sciences

Self Cite

View full text Add to dashboard Cite

To reduce occurrences of emergency situations in large-scale interconnected power systems with large continuous disturbances, a preventive strategy for the automatic generation control (AGC) of power systems is proposed. To mitigate the curse of dimensionality that arises in conventional reinforcement learning algorithms, deep forest is applied to reinforcement learning. Therefore, deep forest reinforcement learning (DFRL) as a preventive strategy for AGC is proposed in this paper. The DFRL method consists of deep forest and multiple subsidiary reinforcement learning. The deep forest component of the DFRL is applied to predict the next systemic state of a power system, including emergency states and normal states. The multiple subsidiary reinforcement learning component, which includes reinforcement learning for emergency states and reinforcement learning for normal states, is applied to learn the features of the power system. The performance of the DFRL algorithm was compared to that of 10 other conventional AGC algorithms on a two-area load frequency control power system, a three-area power system, and the China Southern Power Grid. The DFRL method achieved the highest control performance. With this new method, both the occurrences of emergency situations and the curse of dimensionality can be simultaneously reduced.

show abstract

Artificial emotional reinforcement learning for automatic generation control of large‐scale interconnected power grids

Cited by 59 publications

References 33 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

A Novel on Transmission Line Tower Big Data Analysis Model Using Altered K-means and ADQL

Deep Forest Reinforcement Learning for Preventive Strategy Considering Automatic Generation Control in Large-Scale Interconnected Power Systems

Contact Info

Product

Resources

About