An Integrated Generation-Compensation optimization Strategy for Enhanced Short-Term Voltage Security of Large-Scale Power Systems Using Multi-Objective Reinforcement Learning Method

2018 ◽  
Author(s):  
Zhuoming Deng ◽  
Mingbo Liu
Keyword(s):  
Reinforcement Learning ◽  
Power Systems ◽  
Large Scale ◽  
Learning Method ◽  
Optimization Strategy ◽  
Short Term ◽  
Voltage Security ◽  
Multi Objective

Multi-objective ant lion optimization algorithm to solve large-scale multi-objective optimal reactive power dispatch problem

2019 ◽  
Vol 38 (1) ◽  
pp. 304-324 ◽  
Author(s):  
Souhil Mouassa ◽  
Tarek Bouktir
Keyword(s):  
Power Systems ◽  
Large Scale ◽  
Reactive Power ◽  
Stability Index ◽  
Active Power ◽  
Power Losses ◽  
Content Type ◽  
Multi Objective ◽  
Ant Lion Optimization ◽  
Active Power Losses

Purpose In the vast majority of published papers, the optimal reactive power dispatch (ORPD) problem is dealt as a single-objective optimization; however, optimization with a single objective is insufficient to achieve better operation performance of power systems. Multi-objective ORPD (MOORPD) aims to minimize simultaneously either the active power losses and voltage stability index, or the active power losses and the voltage deviation. The purpose of this paper is to propose multi-objective ant lion optimization (MOALO) algorithm to solve multi-objective ORPD problem considering large-scale power system in an effort to achieve a good performance with stable and secure operation of electric power systems. Design/methodology/approach A MOALO algorithm is presented and applied to solve the MOORPD problem. Fuzzy set theory was implemented to identify the best compromise solution from the set of the non-dominated solutions. A comparison with enhanced version of multi-objective particle swarm optimization (MOEPSO) algorithm and original (MOPSO) algorithm confirms the solutions. An in-depth analysis on the findings was conducted and the feasibility of solutions were fully verified and discussed. Findings Three test systems – the IEEE 30-bus, IEEE 57-bus and large-scale IEEE 300-bus – were used to examine the efficiency of the proposed algorithm. The findings obtained amply confirmed the superiority of the proposed approach over the multi-objective enhanced PSO and basic version of MOPSO. In addition to that, the algorithm is benefitted from good distributions of the non-dominated solutions and also guarantees the feasibility of solutions. Originality/value The proposed algorithm is applied to solve three versions of ORPD problem, active power losses, voltage deviation and voltage stability index, considering large -scale power system IEEE 300 bus.

scholarly journals Short-Term Master-Slave Forecast Method for Distributed Photovoltaic Plants Based on the Spatial Correlation

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Jia Ning ◽  
Guanghao Lu ◽  
Sipeng Hao ◽  
Aidong Zeng ◽  
Hualei Wang
Keyword(s):  
Power Systems ◽  
Spatial Correlation ◽  
Data Storage ◽  
Power Plants ◽  
Large Scale ◽  
Clustering Algorithm ◽  
Storage Condition ◽  
Support Vector ◽  
Forecast Method ◽  
Short Term

With the large-scale integration of distributed photovoltaic (DPV) power plants, the uncertainty of photovoltaic generation is intensively influencing the secure operation of power systems. Improving the forecast capability of DPV plants has become an urgent problem to solve. However, most of the DPV plants are not able to make generation forecast on their own due to the constraints of the investment cost, data storage condition, and the influence of microscope environment. Therefore, this paper proposes a master-slave forecast method to predict the power of target plants without forecast ability based on the power of DPV plants with comprehensive forecast system and the spatial correlation between these two kinds of plants. First, a characteristics pattern library of DPV plants is established with K-means clustering algorithm considering the time difference. Next, the pattern most spatially correlated to the target plant is determined through online matching. The corresponding spatial correlation mapping relationship is obtained by numerical fitting using least squares support vector machine (LS-SVM), and the short-term generation forecast for target plants is achieved with the forecast of reference plants and mapping relationship. Simulation results demonstrate that the proposed method could improve the overall forecast accuracy by more than 52% for univariate prediction and by more than 22% for multivariate prediction and obtain short-term generation forecast for DPV or newly built DPV plants with low investment.

A Multi-Step Reinforcement Learning Algorithm

2010 ◽  
Vol 44-47 ◽  
pp. 3611-3615 ◽  
Author(s):  
Zhi Cong Zhang ◽  
Kai Shun Hu ◽  
Hui Yu Huang ◽  
Shuai Li ◽  
Shao Yong Zhao
Keyword(s):  
Reinforcement Learning ◽  
Markov Decision Process ◽  
Decision Process ◽  
Large Scale ◽  
Learning Algorithm ◽  
Machine Learning Method ◽  
Learning Method ◽  
K Value ◽  
Markov Decision ◽  
Action Value

Reinforcement learning (RL) is a state or action value based machine learning method which approximately solves large-scale Markov Decision Process (MDP) or Semi-Markov Decision Process (SMDP). A multi-step RL algorithm called Sarsa(,k) is proposed, which is a compromised variation of Sarsa and Sarsa(). It is equivalent to Sarsa if k is 1 and is equivalent to Sarsa() if k is infinite. Sarsa(,k) adjust its performance by setting k value. Two forms of Sarsa(,k), forward view Sarsa(,k) and backward view Sarsa(,k), are constructed and proved equivalent in off-line updating.

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

2018 ◽  
Vol 8 (11) ◽  
pp. 2185 ◽  
Author(s):  
Linfei Yin ◽  
Lulin Zhao ◽  
Tao Yu ◽  
Xiaoshun Zhang
Keyword(s):  
Reinforcement Learning ◽  
Power Systems ◽  
Power System ◽  
Large Scale ◽  
Automatic Generation ◽  
Preventive Strategy ◽  
Emergency Situations ◽  
Interconnected Power Systems ◽  
Deep Forest ◽  
Normal States

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.

Sign in / Sign up

Export Citation Format

Share Document