A Two-Level Energy Management Strategy for Multi-Microgrid Systems With Interval Prediction and Reinforcement Learning

Xiong, Luolin; Tang, Yang; Mao, Shuai; Liu, Hangyue; Meng, Ke; Dong, Zhaoyang; Qian, Feng

doi:10.1109/tcsi.2022.3141229

Cited by 36 publications

(9 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Proof. Property 1 shows that robust output regulation problem is equivalent to the robust stabilization problem for the augmented system ( 14)- (15). Theorem 1 has proved that the proposed robust optimal feedback controller can stabilize the augmented system.…”

Section: Algorithm 1 Robust Actor-critic Learning Algorithmmentioning

confidence: 92%

“…This property can be easily verified by (13), and it means that the hypersurface {(z, x, 𝜂, s)|z = z(s, 𝜔), x = x(s, 𝜔), 𝜂 = 𝜽(s, 𝜔)} represents the output zeroing manifold of the close-loop system with control input u = u(s, 𝜔) = Ψ𝜂. Therefore, the robust output regulation problem has been successfully transformed into the robust stabilizing problem about the augmented system ( 14)- (15). However, 𝜛 and 𝜗 are uncertainties unavailable for feedback control, which takes additional challenges.…”

Section: Problem Transformationmentioning

confidence: 99%

“…However, due to the intractability of HJB equation, it is hard or even impossible to get the analytic solution directly 11,12 . To solve this problem, reinforcement learning (RL) was introduced, see References 13‐15 and the references therein.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Reinforcement learning‐based robust optimal output regulation for constrained nonlinear systems with static and dynamic uncertainties

Jin

Zhou

et al. 2022

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

This article investigates the robust optimal output regulation problem for the constrained uncertain nonlinear systems. A two‐step design framework is proposed to overcome the difficulties brought by uncertainties, constraint and performance optimization. First, the feedforward controller is designed by the internal model principle, and the robust output regulation problem is transformed into the robust stabilization problem. Then, the optimal control problem with input saturation is further considered in the robust feedback controller design process. With the help of a non‐quadratic cost functional, actor‐critic algorithm and robust redesign technique are brought together to design the constrained robust optimal feedback controller. Finally, stability analysis based on Lyapunov method shows that all the signals of the closed‐loop system remain bounded, and the tracking error is uniformly ultimately bounded with arbitrarily small ultimate bound. Simulation results illustrate the effectiveness of the proposed methodology.

show abstract

Section: Algorithm 1 Robust Actor-critic Learning Algorithmmentioning

confidence: 92%

Section: Problem Transformationmentioning

confidence: 99%

See 1 more Smart Citation

Reinforcement learning‐based robust optimal output regulation for constrained nonlinear systems with static and dynamic uncertainties

Jin

Zhou

et al. 2022

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

show abstract

“…Meanwhile, for the stable and economic operation of MMG, a multi-microgrid energy management system is required to manage and coordinate dispatchable distributed generators, controllable loads, and energy trading among networked MGs. The operation objectives of MMG can be summarized as follows: 1) to minimize the overall operation cost of MMG in the grid-connected mode [17] and islanded mode [18]; 2) to maximize the distributed renewable energy penetration with the influence of uncertainties from various DREs, loads and electricity price [19][20][21]; 3) to minimize energy transmission loss from energy exchanges with the main-grid and among networked MGs [22]; 4) to maximize the economic goals of different subjects by designing multimicrogrids cluster architecture and its energy transaction mechanism [23]; 5) to minimize the communication delay between MMGs and improve the security and reliability of communication system [24].…”

Section: Figure1 the Global Microgrid Market Size (2021-2027)mentioning

confidence: 99%

A Review on Optimal Energy Management of Multimicrogrid System Considering Uncertainties

Zhang

2022

IEEE Access

View full text Add to dashboard Cite

Microgrid (MG) is one of the most effective solution to integrate distributed renewable energy into power system. However, modern MG has several technical challenges such as migration to multi vector energy system, increasing renewable energy penetration, and the uncertainties that arise from the large-scale incorporation of renewable energy. Recent development of multi-microgrid (MMG) could potentially mitigate these challenges. MMG has obvious advantages in improving the system stability, reliability, economy, and energy efficiency of power grid operation through autonomous management and coordinated control among networked MGs. In the meantime, uncertainties from many elements and operators in the MMG system also pose huge challenges in modeling. This paper will present and review typical architecture of MMG, including physical layer, information layer and application layer. Moreover, this paper will critically review and analyze challenges in uncertainty modelling and solution in MMGs. Finally, the paper will also discuss future research areas and development trends of MMG.

show abstract

“…Accordingly, the community, which is the owner of several flexible units, seeks to maximize its profit at the upper level of the problem, while consumers attempt to minimize their utility bills at the lower level. A market-based framework that handles the energy trading between the DSO and several microgrids at the local distribution level has been proposed in [26]. To this end, a two-level approach has been employed, in which, at the first level, the DSO sets the energy exchange price in a way to increase its earnings from the trading.…”

mentioning

confidence: 99%

Modeling a Local Electricity Market for Transactive Energy Trading of Multi-Aggregators

2022

View full text Add to dashboard Cite

The present article aims at modeling a day-ahead local electricity market (DA LEM) for transactive energy trading at the distribution level. In this regard, a wide range of distributed energy resources (DERs) in the form of multiple aggregators (AGs) participates in the DA LEM in order to trade energy with the distribution system operator (DSO), the operator of the market. On the other hand, the DSO, as the owner of the system, has the responsibility to procure the required energy of its customers with respect to the technical constraints of the distribution network. To settle the designed local market, a Stackelberg game-based approach is exploited in this research work. In the raised Stackelberg scheme, the leader of the game, the DSO, seeks to maximize its expected profit, while followers of the game, DER AGs, tend to minimize their operating costs. Ultimately, to evaluate the proposed framework, a typical case study is implemented on a modified IEEE-33 bus test system.INDEX TERMS DER aggregator, distribution system operator, local electricity market, Stackelberg game, transactive energy trading.

show abstract

A Two-Level Energy Management Strategy for Multi-Microgrid Systems With Interval Prediction and Reinforcement Learning

Cited by 36 publications

References 33 publications

Reinforcement learning‐based robust optimal output regulation for constrained nonlinear systems with static and dynamic uncertainties

Reinforcement learning‐based robust optimal output regulation for constrained nonlinear systems with static and dynamic uncertainties

A Review on Optimal Energy Management of Multimicrogrid System Considering Uncertainties

Modeling a Local Electricity Market for Transactive Energy Trading of Multi-Aggregators

Contact Info

Product

Resources

About