期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2011
卷号：2
期号：4
页码：1498-1500
出版社：TechScience Publications
摘要：For utilities Meter Data Acquisition System (MDAS) is an overall strategy, or process, for building decision support systems and environments that support both everyday tactical decision-making and long-term business strategy. The MDAS provides a common infrastructure for receiving meter data from sub stations, Distribution Transformers, HT/LT consumers and processes the data. This data is shared with utility applications like billing system, energy audit systems, etc. The MDAS contains two subsystems - Data Acquisition Server (DAS) connected to cellular or telephone network for managing Advanced Metering Infrastructure (AMI) and the Meter Data Management System (MDMS). AMI is the infrastructure within which date and time-stamped meter data are remotely collected and transmitted to a Data Acquisition Server and then to a centralized MDMS. The DAS will use PSTN or cellular network with GPRS to connect to all data sources such as Data Concentrator Units (DCU) installed at sub stations, energy meters installed at Distribution transformers, and HT/LT consumer premises. The AMI systems transmit meter data according to configured parameters to the DAS (Data Acquisition Server) using specified protocols and data transfer structure (common data structure for all types of meters). MDMS Data Warehouse is designed for storing and managing vast amounts of historical interval meter data (5 minute, 15 minute, etc), monthly cycle meter data and monthly profiled meter data along with the required ancillary information needed to effectively “mine” and report useful information. MDMS allows utilities to utilize an enterprise-wide meter data store to link information from diverse sources and make the information accessible for a variety of user purposes such as monitoring system performance, settlement, loss analysis and historical operational reporting. In reporting system, there is a need for precision in the load / demand forecasts. The load forecasting further drives various plans and decisions on investment, construction and conservation. Since electric utilities are basically dedicated to the objective of serving consumer demands, the consumer can place a reasonable demand on the system in terms of quantity of power. Also, the utility can then plan the power purchase requirements so as to meet the demand while maintaining the merit order dispatch to achieve optimization in the use of their resources.
关键词：Load Forecasting; Support Vector Machine; Time;seriesng
