论文标题
部分可观测时空混沌系统的无模型预测
Decentralized Load Management in HAN: An IoT-Assisted Approach
论文作者
论文摘要
储层计算是预测湍流的有力工具，其简单的架构具有处理大型系统的计算效率。然而，其实现通常需要完整的状态向量测量和系统非线性知识。我们使用非线性投影函数将系统测量扩展到高维空间，然后将其输入到储层中以获得预测。我们展示了这种储层计算网络在时空混沌系统上的应用，该系统模拟了湍流的若干特征。我们表明，使用径向基函数作为非线性投影器，即使只有部分观测并且不知道控制方程，也能稳健地捕捉复杂的系统非线性。最后，我们表明，当测量稀疏、不完整且带有噪声，甚至控制方程变得不准确时，我们的网络仍然可以产生相当准确的预测，从而为实际湍流系统的无模型预测铺平了道路。
A Home Area Network (HAN) is considered to be a significant component of Advanced Metering Infrastructure (AMI) and has been studied well in many works. It binds all the electrical components installed in a defined premise together for their close monitoring and management. However, HAN has been realized so far mostly as a centralized system. Therefore, like any other centralized system, the traditional realization of HAN also suffers from various well-known problems, such as single-point-of-failure, susceptibility to attacks, requirement of specialized infrastructure, inflexibility to easy expansion, etc. To address these issues, in this work, we propose a decentralized design of HAN. In particular, we propose an IoT based design where instead of a central controller, the overall system operation is controlled and managed through decentralized coordination among the the electrical appliances. We leverage Synchronous-Transmission (ST) based data-sharing protocols in IoT to accomplish our goal. To demonstrate the efficacy of the proposed decentralized framework, we also design a real-time intra-HAN load-management strategy and implement it in real IoT-devices. Evaluation of the same over emulation platforms and IoT testbeds show upto 62% reduction of peak load over a wide variety of load profiles.
