Scheduling, Case-based Reasoning Reservoir

Case-Based Reasoning is a memory-based method which utilizes old cases and experience to solve new problems, and it can be seen as analogism from a case to another case. Because CBR has much merit such as easily learning and using, facilitated knowledge acquirement, strong adaptability etc, it gets highly regard of artificial intelligence researcher and is an important reasoning technique rising in artifical intelligence field.In this paper, we have made a detailed introduction to the casebase in the Case-Based Reasoning, and in turn introduces correlative knowledge on case description and an Object Oriented representation, the aim and tenet of casebase organizing, the acquirement of adjustment knowledge, the classification of adjustment methods, a transform adjustment model, evaluate method of new case and learning and maintenance of casebase, etc.In this paper, we propose a method using fuzzily gathering the kind to carry on the organization index— the method which is used to fuzzily gather the kind for the cases in the casesbase, to converge each typical case in each kind to form the sub- casebase, to take a kind center as the index of this kind of cases. This kind of index might reduce retrieval scope of the cases greatly, and enhance the retrieval efficiency to a great degree.We adopt two levels of Retrieval method which unifies the fuzzy classification and the "Nearest Neighbors method", avoiding the comparision of all cases in casebase when the cases are retrieved,so that the retrieval scope of the cases are reduced greatly and the retrieval efficiency is enhanced as well. Meanwhile the attributes weights determination method based on the Immunity Algorithm CBR is proposed, and the Immune Algorithm is introduced to the deduction system based on the CBR. Then the superiority under the whole conditionis explored among the weight eigenvector of the cases, in order to enhance the efficiency and quality of retrieving the large-scale complex casebase.Lastly we discuss the application of CBR technology in reservoir regulation system, expatiating on practical realization of "reservoir regulation system", and carrying on the experiment and analysis on reasoning the efficiency and the veracity, as well as doing primary exploring for the practical application of CBR technology in "reservoir regulation system". However, the technology is not mature on some aspects, such as automatization adjustment of cases, and further-combination of CBR and other technologies, so our further research aim is how to develop more perfect CBR system.