Fast and efficient power restoration algorithms become necessary for current and future electrical smart grids. In light of that, we propose a Multi-Agent System (MAS) approach for automatic restoration in power distribution networks. Agents in our MAS are categorized into Generator Agents (GA), Zone Agents (ZA) and one Data Base Agent (DBA). GAs have been implemented and negotiation capabilities in order to minimize the cost of the post-restoration configuration. Moreover, as electrical demand fluctuates on the hourly basis, a Least-Square Boosting technique has been used for short-term forecasting of electrical demand. This prediction is incorporated into the restoration algorithm in order to obtain a capacity-based restoration solution. The proposed method has been evaluated in two distribution networks. The forecasting methodology and restoration process are demonstrated in detail through several experiments.

在現今電力系統的發展中，復電演算法的速度及效率已經成為未來智慧型電網研究的趨勢。我們提出一個多重智慧型代理人系統(Multi-Agent System)的架構，將之應用於配電網路端的復電上。代理人被分為發電機代理人(Generator Agents)，區域代理人(Zone Agents)以及資料庫代理人(Data Base Agent )。為了減少復電後配置的成本，發電機代理人被賦與談判的能力。此外，藉由Least-Square Boosting，我們提出一個短程預測電力需求的方法，其中電力需求的變動是按小時為單位。此預測的方法被併入復電演算法中，以得到一個較佳的解法。我們將提出的方法分別於兩個配電網路中進行評估。該預測方法及復電的程序在多次的實驗中得到驗證。

Von-Wun Soo et al. “Coordinating a Society of Agents for Power Distribution Service Restoration in a Smart Grid” Intelligent System Application to Power Systems, 2011.

Aboelsood Zidan, Ehab F. El-Saandany “A Cooperative Multi-Agent Framework for Self-Healing Mechanism in Distribution Systems”, IEEE Transactions on Smart Grid, 2012.

Jignesh M. Solanki, Sarika Khusgalani, Noel N. Schulz “A Multi Agent Solution for Distribution System Restoration” IEEE. Transactions on Power Systems, 2011.

Warodom Khamphanchai et al. “A Multi-Agent System for Restoration of an Electric Power Distribution Network with Local Generation” IEEE Transactions on Power Systems, 2012.

Wang XiaoJing et al. “Research on self-healing restoration strategy of urban power grid Based on multi-agent technology” International conference on Advanced Power System Automation and Protection. 2011.

Yi-Wei Huang, Wan-Yu Yu, Von-Wun Soo, “Stochastic Negotiation with Market Utility for Automated Power Restoration on a Smart Grid” Lectures in Computer Science, 2011.

Youssef Oualmakran et al. “Opportunities and Challenges for smart power restoration and Reconfiguration”, IEEE. 2011.

Vaibhav Donde,Zhenyuan Wang, Fang Yang, James Stoupis,” Short Term Load Forecasting Based Capacity Check for Automated Power Restoration of Electric Distribution Network” ABB Corporate Research Center.

F,J, Marin et al. “Global Mode for Short-Term Load Forecasting Using Artificial Neural Network” IEEE preceding ,2001.

Zainab H. Osman et al. “Neural Network Based Approach for Short-Term Load Forecasting” Power Systems Conference and Exposition, 2009.

Hao-Tian Zhang et al. “Artificial Neural Network for load forecasting in smart grid”, International Conference on machine learning and cybernetics, 2010.

Daniel Zimmerman, Carlos Edmundo Murillo-Sánchez, Robert John Thomas “MATPOWER: Steady-State Operations, Planning, and Analysis Tools for Power, Systems Research and Education” IEEE TRANSACTIONS ON POWER SYSTEMS, 2011

Jerome H Friedman “Greedy Function Approximation: A Gradient Boosting Machine “ February 24, 1999.

Allen J. Wood et al. “Power Generation, Operation and Control”, Third Edition, 2014

Michael Wooldrige “An Introduction to Multi-Agent Systems”, Second Edition, 2009