Optimized Electrical Machine Operation Scheduling using Classification Learning

Abstract

Scheduling electrical machines based on consumer demands improves the efficiency of the purpose through flawless allocations. However, due to peak utilization and maximum run-time of the machines, the chances of schedule mismatch and overlapping are common in large production scales. In this paper, an Operation Scheduling process (OSP) using Classification Learning (CL) is proposed. The proposed process classifies operation schedules based on overlapping and mismatching intervals post-output completion. The classification is performed using interval stoppage and re-scheduling performed between successive completion intervals. This is required to improve the output success rate for simultaneous machine operations. Therefore the scheduling is improved regardless of distinct tasks allocated with better outcomes.