@article{MAKHILLIJSC201510121263,
    title = {ANN And Gradient Based Optimal Power Flow},
    journal = {International Journal of Soft Computing},
    volume = {10},
    number = {1},
    pages = {87-93},
    year = {2015},
    issn = {1816-9503},
    doi = {ijscomp.2015.87.93},
    url = {https://makhillpublications.co/view-article.php?issn=1816-9503&doi=ijscomp.2015.87.93},
    author = {R. and},
    keywords = {Optimal power flow,gradient descent,artificial neural network,deregulation,error weightage},
    abstract = {Optimal Power Flow (OPF) is essential and is employed to attain desired performance in any field of engineering. It plays an important role in power system operation and planning. In deregulated environment of power sector, it is of increasing importance for determination of electricity prices. Traditional optimization techniques have limitations in obtaining the global solution. With a non-monotonic solution surface, classical methods are highly sensitive to starting points and frequently converge to local optimal solution or diverge altogether. This study describes an artificial neural network-GD based optimal power flow which is highly constrained non convex optimization problems with single objective, the fuel cost and compares its results with well known classical methods in order to prove its validity for present deregulated power system analysis.}
    }