{"title":"Network engineering 2000","authors":"D.J.Y. Lee, WuSeong Lee","doi":"10.1109/ICMMT.2000.895712","DOIUrl":null,"url":null,"abstract":"Introduction of location technology shifts the paradigm of network engineering. It opens the door for providing a revolutionary approach for network engineering. The algorithm discussed in this paper provides a way of combining parameters made available through location technology and currently available system parameters for future network engineering and operation. The \"continuous\" snapshots of the network can be parsed and intelligently stored into the network performance data warehouse as images. These images can be analyzed off-line to select certain \"troubled\" instances of the network (this can be site specific). These instances can, then, be analyzed through simulation and/or engineer intervention. Optimized solution can be developed. These \"troubled\" instance and associated solutions can be fed back into the \"virtual network engineer\" simulated by the AI engine to increase its knowledge base. Later, the intelligent pseudo \"network engineer\" can identify \"troubled\" network instance and compare with the existing images and associated solution in the data warehouse. The existing solution then can be applied to perform real time automated network engineering. This is done through image processing by selecting the most similar network instance and associated solution. By saving more and more \"troubled\" instances and developed associated solutions, the \"virtual network engineer\" increases its knowledge bases and becomes more and more \"intelligent\" and can handle future \"troubled\" instance based on the \"experience\". For example, the dynamic power allocation and individual specific dedicated dynamic SHO thresholds for each mobile can be combined to efficiently engineer the network performance once the mobile location and associated network characteristics can be identified.","PeriodicalId":354225,"journal":{"name":"ICMMT 2000. 2000 2nd International Conference on Microwave and Millimeter Wave Technology Proceedings (Cat. No.00EX364)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2000-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ICMMT 2000. 2000 2nd International Conference on Microwave and Millimeter Wave Technology Proceedings (Cat. No.00EX364)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICMMT.2000.895712","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Introduction of location technology shifts the paradigm of network engineering. It opens the door for providing a revolutionary approach for network engineering. The algorithm discussed in this paper provides a way of combining parameters made available through location technology and currently available system parameters for future network engineering and operation. The "continuous" snapshots of the network can be parsed and intelligently stored into the network performance data warehouse as images. These images can be analyzed off-line to select certain "troubled" instances of the network (this can be site specific). These instances can, then, be analyzed through simulation and/or engineer intervention. Optimized solution can be developed. These "troubled" instance and associated solutions can be fed back into the "virtual network engineer" simulated by the AI engine to increase its knowledge base. Later, the intelligent pseudo "network engineer" can identify "troubled" network instance and compare with the existing images and associated solution in the data warehouse. The existing solution then can be applied to perform real time automated network engineering. This is done through image processing by selecting the most similar network instance and associated solution. By saving more and more "troubled" instances and developed associated solutions, the "virtual network engineer" increases its knowledge bases and becomes more and more "intelligent" and can handle future "troubled" instance based on the "experience". For example, the dynamic power allocation and individual specific dedicated dynamic SHO thresholds for each mobile can be combined to efficiently engineer the network performance once the mobile location and associated network characteristics can be identified.