TY  - JOUR
T1  - Neural Based Generation Scheduling with Environmental Constraints
AU - , T. Sree Renga Raja AU - , N.S. Marimuthu AU - , T. Sree Sharmila 
JO  - International Journal of Soft Computing
VL  - 1
IS  - 2
SP  - 91
EP  - 96
PY  - 2006
DA  - 2001/08/19
SN  - 1816-9503
DO  - ijscomp.2006.91.96
UR  - https://makhillpublications.co/view-article.php?doi=ijscomp.2006.91.96
KW  - Artificial neural network
KW  -cascade correlation
KW  -economic dispatch
KW  -generation scheduling
KW  -optimization and unit commitment
AB  - Reliable power production is critical to the profitability of electricity utilities. Power generators need
to be scheduled efficiently to meet electricity demand. This dissertation develops a solution method to schedule
units for producing electricity while determining the estimated amount of surplus power each unit should
produce taking into consideration the stochasticity of the load and its correlation structure. This scheduling
problem is known as the dispatch problem in the power industry. A general formulation and the development
of cascade correlation algorithm to solve the environmentally constrained dispatch problem are presented. The
objective is the minimization of the cost of operation, subject to all the usual and emissions constraints. The
algorithm handles multiple pollutants and for each pollutant the constraints include the maximum hourly
emission on every unit, the maximum hourly emission on every set of on-line units and the maximum daily
emission for the system constraints. Three closed-form dispatch strategies and two feasibility conditions are
established to eliminate unfeasible unit combinations thus rendering a very efficient commitment algorithm. Test
results are provided to show the efficiency of the proposed method.
ER  -