中文摘要：

负荷估计和状态估计对于配电网的管理和控制非常重要．文中提出了一种集成的负荷估计和状态估计框架．一方面提出了一种基于连接机制的事例推理新方法（CBCBR）用于解决配电网节点负荷估计问题，分别介绍了CBCBR的原理、结构、混合学习算法和实际应用，CBCBR具有快速、增量式、自适应学习能力；另一方面提出了一种抗差状态估计方法。同时实现了结构空间和量测空间的抗差．抗差状态估计器使用CBCBR的输出作为输入的伪量测量，同时CBCBR可使用抗差估计器的输出改善其自身性能．所提集成的负荷估计和状态估计框架能有效抵御坏数据的影响，并可实现自适应性调节．使用33节点系统测试所提方法，所用节点数据来自实际系统，算例结果证明了该方法的有效性．

英文摘要：

Load and state estimation are very important for the management and control of complex distribution networks. A framework of integrated load and state estimation is proposed. On the one hand, a connectionismbased case-based-reasoning method （CBCBR） is presented for distribution network nodal load estimation. Principle, architecture, hybrid supervised and unsupervised learning algorithm, and practical application of CBCBR are introduced. CBCBR is equipped with quick incremental self-adaptive learning capability. On the other hand, a state estimator robustified synthetically in both factor space and measurement space is employed in the proposed framework. The robust state estimator utilizes CBCBR output as pseudo measurements of input.CBCBR can improve its performance using the output of the robust state estimator. This integrated load and state estimation method can withstand the influence of bad data effectively and has self-adaptive capability. The proposed method is tested on a 33-node system whose nodal load data come from a practical system and test results are very promising.