Multi-level coordinated energy management for energy hub in hybrid markets with distributionally robust scheduling

Cao, Jiaxin; Yang, Bo; Zhu, Shanying; Chung, C. Y.; Guan, Xinping

doi:10.1016/j.apenergy.2022.118639

Cited by 17 publications

(3 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to overcome the limitations and shortcomings of the above two methods, ambiguity set is adopted to depict the continuous range of probability distributions of random factors in distributionally robust optimization (DRO), and then the optimization is conducted regarding the worst-case distributions within the ambiguity set. Probability information considered in DRO significantly reduces the conservativeness compared with RO [14][15][16].…”

Section: Introductionmentioning

confidence: 99%

“…For example [29] considers power, gas and heat market in day-ahead stage, and considers only power market in real-time stage. In [14], the first stage is dedicated to obtaining more energy arbitrage and operation flexibility by optimizing bidding strategies in day-ahead power, natural gas and carbon trading markets, and only power market is considered in real-time stage. However, research on reinforcement learning based two-timescale energy management is very limited, similar research focuses on the field of Volt/VAR control (VVC) [30][31][32][33].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reinforcement learning based two‐timescale energy management for energy hub

Chen,

Mao,

Sha

et al. 2024

IET Renewable Power Gen

View full text Add to dashboard Cite

Maintaining energy balance and economical operation is significant for energy hub (EH) which serves as the central component. Implementing real‐time regulation for heating and cooling equipment within the EH is challenging due to their slow response time in response to the stochastic fluctuation in renewable energy sources and demands while the opposite is true for electric energy storage equipment (EST), a conventional single timescale energy management strategy is no longer sufficient to take into account the operating characteristics of all equipment. With this motivation, this study proposes a deep reinforcement learning based two‐timescale energy management strategy for EH, which controls heating & cooling equipment on a long timescale of 1 h, and EST on a short timescale of 15 min. The actions of the EST are modelled as discrete to reduce the action spaces, and the discrete‐continuous hybrid action sequential TD3 model is proposed to address the problem of handling both discrete and continuous actions in long timescale policy. A joint training approach based on the centralized training framework is proposed to learn multiple levels of policies in parallel. The case studies demonstrate that the proposed strategy reduces the economic cost and carbon emissions by 1%, and 0.5% compared to the single time‐scale strategy respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Reinforcement learning based two‐timescale energy management for energy hub

Chen,

Mao,

Sha

et al. 2024

IET Renewable Power Gen

View full text Add to dashboard Cite

show abstract

“…The simulations indicate that when the energy price is higher than gas, the operator tends to sell power and purchase gas to obtain a balanced system and maximize revenue [19]. The coordinated management of an energy hub is discussed for participating in DA and RT energy, gas and carbon markets under the uncertainty of renewable energies, loads and prices [20]. In this regard, a two‐stage chance‐constrained distributed robust method is utilized in which the first stage optimizes the bidding strategy in DA hybrid markets and then, the worst‐case expected operation cost is minimized in the second stage.…”

Section: Introductionmentioning

confidence: 99%

Risk‐constrained two‐stage scheduling of a virtual energy hub integrated with intelligent parking lots in the presence of electrical and thermal energy markets and responsive loads

Norouzi,

Tabar,

Ghassemzadeh

et al. 2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

The energy hub applications have been investigated from different perspectives in recent years due to their benefits such as high flexibility and reliability. This paper proposes a two‐stage stochastic programming to enable the participation of a virtual energy hub integrated with parking lots in the electrical and thermal energy markets under the uncertainty of renewable resources, load demands and energy prices. In such modeling, the first stage optimizes the offers of the virtual hub in the day‐ahead markets before realizing uncertain parameters and the second stage minimizes the real‐time imbalanced cost and determines the operation of components considering actual data. In order to evaluate the risk of decisions, the conditional value‐at‐risk metric is utilized and the results are discussed in the risk‐neutral and risk‐averse strategies for a sample day of summer and winter. In the following, a time‐based program is implemented to indicate the influence of responsive loads and a sensitivity analysis is conducted to assess the effectiveness of the flexible units. The simulations approve that although the risk‐averse optimization significantly decreases the profit, the initiative against fluctuations enhances. The outcomes also demonstrate the notable role of flexible units and loads for energy trading in the electrical and thermal markets.

show abstract