A Modified Boltzmann Machine for Solving Distribution System Expansion Planning in Malaysia

Siti Hajar Mohd Tahar, Shamshul Bahar Yaakob, Amran Ahmed


This paper proposes an effective technique to solve Distribution System Expansion Planning (DSEP) problem by using the artificial neural network. The proposed technique will be formulated by using mean-variance analysis (MVA) approach in the form of mixed-integer quadratic programming problem. It consists of two layers neural network which combine Hopfield network and Boltzmann machine (BM) in upper and lower layer respectively named as Modified BM. The originality of the proposed technique is it will delete the unit of the second layer, which is not selected in the first layer in its execution. Then, the second layer is restructured using the selected units. Due to this feature, the proposed technique will improve time consuming and accuracy of solution. Referring to the case study demonstrated in this paper, the significance outputs obtained are the improvement in computational time and accuracy of solution provided. As the solution provided various of options, the proposed technique will help decision makers in solving DSEP problem. As a result, the performance of strategic investment planning in DSEP certainly enhanced.


Boltzmann machine, Hopfield network, Neural network, Mean-variance analysis, Distribution System Expansion Planning

Full Text:


DOI: http://doi.org/10.11591/ijeecs.v12.i1.pp193-200


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

shopify stats IJEECS visitor statistics