Distributed Learning Strategies for Collaborative Agents in Adaptive Decentralized Power Systems
Distributed Learning Strategies for Collaborative Agents in Adaptive Decentralized Power Systems
复制标题
自适应分散电力系统中协作代理的分布式学习策略
DOI：
--
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
O. Krause
中科院分区：
文献类型：
--
作者：
H. Wedde;S. Lehnhoff;K. Moritz;E. Handschin;O. Krause
对于再生电力，传统的自上而下和长期的电力管理是过时的，这是由于基于风能和太阳能的电力设施的广泛分散和高度不可预测性。在研发DEZENT1项目中，我们开发了一个多层次的自下而上的解决方案，自主软件代理代表消费者和生产者团体协商可用的能源数量和需求。我们在假设恒定的需求和供应的非常短的时间间隔内操作，在我们的情况下为0.5秒（灯泡的开关延迟）。我们证明了对各种相关的恶意攻击的安全性。在本文中，主要的贡献是使谈判策略本身适应跨时期。我们采用了强化学习方法来定义和讨论协作自主代理的学习策略，这些策略明显上级以前的（静态）程序。我们简要报告广泛的比较模拟。
For regenerative electric power the traditional top- down and long-term power management is obsolete, due to the wide dispersion and high unpredictability of wind and solar based power facilities. In the R&D DEZENT1 project we developed a multi-level bottom- up solution where autonomous software agents negotiate available energy quantities and needs on behalf of consumers and producer groups. We operate within very short time intervals of assumedly constant demand and supply, in our case 0.5 sec (switching delay for a light bulb). We prove security against a relevant variety of malicious attacks. In this paper the main contribution is to make the negotiation strategies themselves adaptive across periods. We adapted a reinforcement Learning approach for defining and discussing learning strategies for collaborative autonomous agents that are clearly superior to previous (static) procedures. We report briefly on extensive comparative simulation.