Research on distribution network spare parts demand forecasting and inventory quota

Due to the professionalism and particularity of the power equipment, a reasonable inventory equipment quota forecasting and purchasing plan can guarantee the electrical power construction and maintenance work smoothly. Furthermore, an accurate quota forecasting can also save a large volume of liquid funds for the power companies. This paper establishes a reasonable spare parts demand forecasting and inventory quota model based on SVM algorithm which takes material historical demand, repair schedule, the failure rate of the equipment and operating environment into full consideration. Moreover, the spare parts of electrical equipment in distribution network are divided into Class A, Class B1 and Class B2 through the activity based classification, through which the inventory quota method based on the different types of inventory management model is established. Finally, the calculation results of actual distribution power network show that the proposed SVM model is of high prediction accuracy, providing a simple and effective solution for inventory equipment management of electricity equipment.

[1]  Jie Wang,et al.  Parameters Optimization and Application of v-Support Vector Machine Based on Particle Swarm Optimization Algorithm , 2012, 2012 International Conference on Computing, Measurement, Control and Sensor Network.

[2]  NI Dong-me.  Synthesized model for demand forecasting and its integration with inventory decision , 2013 .

[3]  T. P. M. Pakkala,et al.  A Bayesian approach to a dynamic inventory model under an unknown demand distribution , 2002, Comput. Oper. Res..

[4]  T. Suwanasri,et al.  Failure statistics and inventory management for high voltage circuit breaker using statistical distribution techniques , 2012, 2012 IEEE International Conference on Condition Monitoring and Diagnosis.

[5]  T. Willemain,et al.  A new approach to forecasting intermittent demand for service parts inventories , 2004 .

[6]  Li Hong-yu.  Application of AHP in Sorting Inventory Items , 2005 .

[7]  Liu Yubin,et al.  Incremental Learning Method of Least Squares Support Vector Machine , 2010, 2010 International Conference on Intelligent Computation Technology and Automation.

[8]  Carlos E. Pedreira,et al.  Neural networks for short-term load forecasting: a review and evaluation , 2001 .

[9]  Tong Li,et al.  A Novel Inventory Level Forecast Model Based on Artificial Neural Network , 2008, 2008 International Conference on MultiMedia and Information Technology.

[10]  Ku Ruhana Ku-Mahamud,et al.  Optimizing Support Vector Machine parameters using continuous Ant Colony Optimization , 2012, 2012 7th International Conference on Computing and Convergence Technology (ICCCT).

[11]  Anwaruddin Tanwari,et al.  ABC Analysis as a Inventory Control Technique , 2000 .

[12]  Vladimir Naumovich Vapni.  The Nature of Statistical Learning Theory , 1995 .