MINIMIZING ENERGY COSTS AND TRAIN DELAYS USING AN IMPROVED BRUTE FORCE ALGORITHM Nurshasabila binti Azri #1, Mohamed Faidz Mohamed Said #2 # Universiti Teknologi MARA 70300 Seremban, Negeri Sembilan, MALAYSIA 1 shasawenz@ymail.com 2 mohdfaidz@uitm.edu.my Abstract—This paper exhibits an improved Brute Force calculation application for streamlining the driving velocity bend by exchanging off decreases in vitality utilization against expansions in deferral punishment. A test system is utilized to look at the train operation execution with various train control framework arrangements when actualized on an area of fast line working with two trains, incorporating contrasts in adventure time and prepare vitality utilization. Results are exhibited utilizing six diverse train control framework designs consolidated with three distinctive working needs. Investigation of the results demonstrates that the operation execution can be enhanced by disposing of the collaborations between trains utilizing propelled control frameworks or ideal working needs. The calculation is appeared to accomplish the targets effectively and precisely. Control framework setups with halfway levels of many-sided quality when combined with the improvement procedure have been appeared to be comparable execution to the more propelled control framework. Keyword: Ideal train control, brute force REFERENCES [1] Zhao et al., The application of an enhanced Brute Force algorithm to minimise energy costs and train delays for differing railway train control systems, J Rail and Rapid Transit, 2014, 228(2) 158–168. [2] Bocharnikov YV, Tobias AM, Roberts C, et al. Optimal driving strategy for traction energy saving on DC suburban railways. Electr Power Appl 2007; 1: 675–682. [3] HeeSoo H. Control strategy for optimal compromise between trip time and energy consumption in a highspeed railway. IEEE Trans Syst Man Cybern, Part A:Syst Humans 1998; 28: 791–802. [4] Hansen EA, Bernstein DS and Zilberstein S. Dynamic programming for partially observable stochastic games.In: The nineteenth national conference on artificial intelligence (ed AG Cohn), San Jose, California, USA, 25–29 July 2004, pp.709–715. Palo Alto, California: AAAI Press. [5] Jamal TEA. Metaheuristics for optimal transfer of P2P information in VANETs. MSc Thesis, Faculty of science, technology and communication, University of Luxembourg, UK, 2010. [6] Woodland D. Optimisation of automatic train protection systems. PhD Thesis, Department of Mechanical Engineering, University of Sheffield, UK, 2004. [7] Hicks D. Performance modelling for the National ERTMS Programme (NEP). In: The IEE seminar on railway system modelling - not just for fun (ed R Rawlings), London, UK, 30 September 2004, pp.61–74. Stevenage, England: IEE. [8] Chang CS and Sim SS. Optimising train movements through coast control using genetic algorithms. IEE Proc, Electr Power Appl 1997; 144: 65–73. [9] Acikbas S and Soylemez MT. Coasting point optimization for mass rail transit lines using artificial neural networks and genetic algorithms. IET Electr Power Appl 2008; 2: 172–182. [10] Network Rail. Network Rail monitor - Q4 2008-09 4 January - 31 March 09 and Annual Assessment 2008–09, 2009. London, UK: Network Rail. [11] Gary C. Performance and punctuality. Report for theAssociation of Train Operating Companies, 2010. London,UK: Association of TrainOperatingCompanies [12] Jiang W, Chen X and Zhong Z. The impact of quality of services in Chinese train control system on train delays analysis. In: The IEEE 72nd fall vehicular technology conference, Ottawa, Canada, 6–9 September 2010, pp.1–5. Piscataway, NJ: IEEE press. [13] Bai Y, Ho T and Mao B. Train control to reduce delays upon service disturbances at railway junctions. J Transp Syst Engng Inform Technol 2011; 11: 114–122. [14] Faheem HM. Accelerating motif finding problem using grid computing with Enhanced Brute Force. In: The 12th international conference on 2010 advanced communication technology (ICACT) (ed DY Kim), Gangwon-Do, Korea, 7–10 Febuary 2010, pp.197–202. Piscataway, NJ: IEEE Press.