NEURAL-NET BASED COORDINATED CONTROL OF CAPACITORS AND ULTC TRANSFORMER IN DAILY OPERATION OF RADIAL-DISTRIBUTION SYSTEMS

In this paper the problem of coordinated VAR/VOLT control of general r adial distribution systems with lateral branches, in daily operations is considered, by using mechanically switched shunt capacitors and und er-load tap-changing (ULTC) source transformers, feeding the radial ne twork. Control variables are switchable, fixed or regulated capacitors and tap positions of the ULTC transformer, assuming the no-load tap-c hanging (NLTC) transformers within the network remain in fixed tap pos itions. In the first stage of the proposed approach, the training patt erns required for the neural-net supervised learning process are gener ated by using a decoupled model for the coordinated VAR/VOLT control. The corresponding optimal daily schedules are used in the second stage , within the unsupervised/supervised concept, to synthesise complex ma pping relating input load and source-voltage data to control variables . If discrepancy between forecasted and measured variables is greater than the prespecified tolerance threshold, the iterative decoupled alg orithm for coordinated VAR/VOLT control is initiated to perform the co rrection of the schedule. The effectiveness of the proposed method is verified on the real 110 kV/35 kV/10 kV distribution system with 53 no des. It has been demonstrated by this case study that the proposed app roach preserves the optimization accuracy provided by the decoupled mo del for coordinated VAR/VOLT control and overcomes unnecessary calcula tions for similar load profiles. (C) 1997 Elsevier Science S.A.