Microgrid energy dispatching for industrial zones with renewable generations and electric vehicles via stochastic optimization and learning

Zhang, Kai1; Li, Jingzhi2; He, Zhubin3; Yan, Wanfeng2,4

2018-07

10.1016/j.physa.2018.02.196

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS   影响因子和分区

0378-4371

1873-2119

In this paper, a stochastic optimization framework is proposed to address the microgrid energy dispatching problem with random renewable generation and vehicle activity pattern, which is closer to the practical applications. The patterns of energy generation, consumption and storage availability are all random and unknown at the beginning, and the microgrid controller design (MCD) is formulated as a Markov decision process (MDP). Hence, an online learning-based control algorithm is proposed for the microgrid, which could adapt the control policy with increasing knowledge of the system dynamics and converges to the optimal algorithm. We adopt the linear approximation idea to decompose the original value functions as the summation of each per-battery value function. As a consequence, the computational complexity is significantly reduced from exponential growth to linear growth with respect to the size of battery states. Monte Carlo simulation of different scenarios demonstrates the effectiveness and efficiency of our algorithm. (C) 2018 Elsevier B.V. All rights reserved.

Microgrid energy dispatching Markov decision process Linear approximation approach

SCI ; EI

英语

通讯

National Key research and development plan issue, China[2017YFC0602203]

Physics

Physics, Multidisciplinary

WOS:000430027500032

ELSEVIER SCIENCE BV

20181004884074

Controllers ; Intelligent systems ; Markov processes ; Monte Carlo methods ; Optimization ; Secondary batteries

Secondary Batteries:702.1.2 ; Electric Power Transmission:706.1.1 ; Artificial Intelligence:723.4 ; Control Equipment:732.1 ; Optimization Techniques:921.5 ; Probability Theory:922.1 ; Mathematical Statistics:922.2

PHYSICS

Web of Science

1.Jilin Univ, Dept Math, Changchun 130012, Jilin, Peoples R China
2.Southern Univ Sci & Technol, Dept Math, Shenzhen 518055, Peoples R China
3.Southern Univ Sci & Technol, Dept Mat Sci & Engn, Shenzhen 518055, Peoples R China
4.Banque Pictet & Cie SA, Route Acacias 60, CH-1211 Geneva 73, Switzerland

Zhang, Kai,Li, Jingzhi,He, Zhubin,et al. Microgrid energy dispatching for industrial zones with renewable generations and electric vehicles via stochastic optimization and learning[J]. PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS,2018,501:356-369.

Zhang, Kai,Li, Jingzhi,He, Zhubin,&Yan, Wanfeng.(2018).Microgrid energy dispatching for industrial zones with renewable generations and electric vehicles via stochastic optimization and learning.PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS,501,356-369.

Zhang, Kai,et al."Microgrid energy dispatching for industrial zones with renewable generations and electric vehicles via stochastic optimization and learning".PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 501(2018):356-369.