arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.03507cs.LGeess.SPstat.ML
收藏

使用强化学习和基于模拟的优化的存储扩展规划框架

A storage expansion planning framework using reinforcement learning and simulation-based optimization

Rutgers University(罗格斯大学);Nanjing University of Science and Technology(南京理工大学);Rutgers Business School(罗格斯大学商学院)

S. Tsianikas, N. Yousefi, J. Zhou, M. Rodgers, D. W. Coit

摘要:

在我们面前的高度电气化的未来之后,在分布式发电丰富的地方,例如在微电网环境中,储能的作用至关重要。鉴于存储选项的多样性变得越来越经济,确定投资哪种类型的存储技术以及适当的时间和容量成为一个关键的研究问题。这些问题今后将不可避免地继续变得越来越重要,需要进行战略规划和建立全面的现代框架,以便加以解决。强化学习算法已经被证明在顺序决策是固有的问题中是成功的。在运营规划领域,这些算法已经被使用,但大多数是在短期问题与明确定义的约束。相反,我们利用无模型算法结合基于模拟的模型,扩展和定制这些技术的长期规划。已经开发了一个模型和扩展计划,以最佳地确定微电网设计,因为它们可以动态地对不断变化的条件做出反应,并利用储能能力。我们表明,有可能获得更好的工程解决方案,这些解决方案将指向可能成为未来微电网应用核心的储能单元类型。另一个关键发现是,系统的最佳存储容量阈值在很大程度上取决于可用存储单元的价格变动。通过利用所提出的方法,它是可能的模型固有的问题的不确定性和优化的顺序投资决策的整个流程。

英文摘要:

In the wake of the highly electrified future ahead of us, the role of energy storage is crucial wherever distributed generation is abundant, such as in microgrid settings. Given the variety of storage options that are becoming more and more economical, determining which type of storage technology to invest in, along with the appropriate timing and capacity becomes a critical research question. It is inevitable that these problems will continue to become increasingly relevant in the future and require strategic planning and holistic and modern frameworks in order to be solved. Reinforcement Learning algorithms have already proven to be successful in problems where sequential decision-making is inherent. In the operations planning area, these algorithms are already used but mostly in short-term problems with well-defined constraints. On the contrary, we expand and tailor these techniques to long-term planning by utilizing model-free algorithms combined with simulation-based models. A model and expansion plan have been developed to optimally determine microgrid designs as they evolve to dynamically react to changing conditions and to exploit energy storage capabilities. We show that it is possible to derive better engineering solutions that would point to the types of energy storage units which could be at the core of future microgrid applications. Another key finding is that the optimal storage capacity threshold for a system depends heavily on the price movements of the available storage units. By utilizing the proposed approaches, it is possible to model inherent problem uncertainties and optimize the whole streamline of sequential investment decision-making.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑