With RBF network, we are formulating combined economic and emission dispatch and comparing results with the help of BPA network and conventional lambda technique. The multi-objective CEED problem is being converted into single optimization problem by introducing price penalty factor, given by Minimize Φ = F + hpd* E. The modified price penalty factor hpd combines the emission with the normal fuel costs.

The general process is described in the following ways: running CEED with conventional lambda technique, generating patterns for training network from above method, initializing RBF network, training of RBF network with proper selection of constants and weight initialization, and comparing results.

The procedure in CEED using RBF includes: Read reqd. data and training patterns, Find centers using Clustering technique, Find corresponding widths for each centre, Intialise weight matrix b/w hidden layer and o/p layer, start weight training and repeat process  until itermax is reached or reqd convergence is attained, and test network and compare results.

Memorizing for training Weight training: First run the process with weights randomised with restrictions on itermax and epsilon, Repeat above step for a few trials say 6 – 9 trials and memorize all the finalised weights and Errorrate after complete training, Choose the best trial that is most successful among all trials, then run process using finalised weights after best run trial as initial set of weights instead of taking randomised weights, Repeation of  above step 4 for itself for a few times improves convergence time.


Combined economic and emission dispatch is formulated by RBF network and centres were different from Memorizing weights and centers that results in faster convergence. Network is tested for 3gen, 6gen, 15gen systems and combined with Unit Commitment Problem for complete study. Hence with the help of RBF network there is a formulation that combines economic and emission dispatch to compare the results.

Download Combined Economic and Emission Dispatch using RBF Neural Network Mech Final Project Report