As an archipelagic country, the Philippines’ seaports play a vital role in mobility and economic activities. As a timely and strategic undertaking to complement the nationwide thrust on infrastructure planning and development, this research investigates the Philippines’ seaport system as a network design problem. From an existing system of ports, hubs which leverage economies of scale are identified as ports for development. These identified hubs should be developed as trans-shipment, consolidation, and distribution ports. In the context of planning, future demand was represented in the solution through demand forecast values for all origin-destination pairs using Grey model and support vector machine (SVM). The forecast values are the data inputs to solve the p-hub median in minimizing network flow cost. p-hub median ensures that each node has access and is accessible by other nodes through node-to-hub and hub-to-hub links, therefore, sufficing the integration requirement. To include accessibility in the model, an important criteria in public transportation, cover constraint was introduced. The network of ports (n=135 for cargo and n=101 for passenger) was solved through Tabu search (TS) algorithm with optimality gap of 0.36% in comparison to benchmark results. The findings on hub locations, links/routes, and hub and link capacity will provide the strategic layer for decision makers in port infrastructure planning. Port management can use the strategic insights from this research as a backbone for a comprehensive planning solution that extends to tactical and operational layers.

As an archipelagic country, the Philippines’ seaports play a vital role in mobility and economic activities. As a timely and strategic undertaking to complement the nationwide thrust on infrastructure planning and development, this research investigates the Philippines’ seaport system as a network design problem. From an existing system of ports, hubs which leverage economies of scale are identified as ports for development. These identified hubs should be developed as trans-shipment, consolidation, and distribution ports. In the context of planning, future demand was represented in the solution through demand forecast values for all origin-destination pairs using Grey model and support vector machine (SVM). The forecast values are the data inputs to solve the p-hub median in minimizing network flow cost. p-hub median ensures that each node has access and is accessible by other nodes through node-to-hub and hub-to-hub links, therefore, sufficing the integration requirement. To include accessibility in the model, an important criteria in public transportation, cover constraint was introduced. The network of ports (n=135 for cargo and n=101 for passenger) was solved through Tabu search (TS) algorithm with optimality gap of 0.36% in comparison to benchmark results. The findings on hub locations, links/routes, and hub and link capacity will provide the strategic layer for decision makers in port infrastructure planning. Port management can use the strategic insights from this research as a backbone for a comprehensive planning solution that extends to tactical and operational layers.

Abdelhamid, B., Berrajaa, A., Boukachour, J., Oudani, M., 2018. Solving the Uncapacitated Single Allocation p-Hub Median Problem on GPU. Bioinspired Heuristics for Optimization. Springer. Vol 774 (27-42).
Abyazi-Sani, R. , Ghanbari, R. , 2016. An efficient tabu search for solving the uncapac- itated single allocation hub location problem. Computers in Industrial Engineering. 93, 99–109.
Akgun I. and Tansel B.C., 2018. p -hub median problem for non-complete networks. Computers and Operations Research. 95 (56-72).
AP data. http://users.monash.edu/~andrease/Downloads Accessed May 13, 2019
Benítez, R.B.C, Paredes, R.B.C, Lodewijks G., Nabais, J.L., Damp trend Grey Model forecasting method for airline industry. Expert Systems with Applications 40(2013) 4915–4921.
Cao, L. J. and Tay F. E. H., 2003. Support Vector Machine With Adaptive Parameters in Financial Time Series Forecasting. IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 14, NO. 6, NOVEMBER 2003
Chang, S.-C., Lai, H.-C., Yu, H.-C., A variable P value rolling Grey forecasting model for Taiwan semiconductor industry production Technological Forecasting & Social Change 72 (2005) 623–640
Chiou, H-K, Tzeng, G-H, Cheng, C-K, Liu, G-S, 2004. Grey prediction model for forecasting the planning material of equipment spare parts in Navy of Taiwan. IEEE Proceedings World Automation Congress. Print ISBN: 1-889335-21-5. Date Added to IEEE Xplore: 20 June 2005
Dangeti, P., Statistics for Machine Learning, Packt Publishing Ltd., 224-232.
Daskin, M.S. 2010, Service Science, John Wiley and Sons, 214 – 215.
Flyvbjerg, B., Measuring inaccuracy in travel demand forecasting: methodological considerations regarding ramp up and sampling. Transportation Research Part A 39 (2005) 522–530.
Gilliland, M., The Business Forecasting Deal: Exposing Myths, Eliminating Bad Practices, Providing Practical Solutions. John Wiley & Sons, Inc. 2010. p.196.
Guan, J., Lin, G., Feng H-B, 2018. A learning-based probabilistic tabu search for the uncapacitated single allocation hub location problem. Computers and Operations Research. 98(1-12)
Ilic, A., Uroševic, D., Brimberg, J., Mladenovic, N., 2010. A general variable neighborhood search for solving the uncapacitated single allocation p-hub median problem. European Journal of Operational Research. 206 (289–300).
International Chamber of Shipping (ICS) (2016) [online] http://www.ics-shippinp.org (accessed 15 April 2018).
Kratica, J., Stanimirović, Z., Tošić, D., Filipović, V., 2007. Two genetic algorithms for solving the uncapacitated single allocation p-hub median problem. European Journal of Operational Research, 182(1), 15-28.
Liu, S, Yang, Y., Forrest, J., 2017. Grey Data Analysis: Methods, Models and Applications. Springer Science+Business Media Singapore, pp. 13-16.
The Manila Times. “The Philippines as an archipelagic state: advantages and challenges”, 2015, http://www.manilatimes.net/the-philippines-as-an-archipelagic-state-advantages-and-challenges/219455/ (accessed 15 April 2018)
The Manila Times. “Port infrastructure development ongoing”, 2017 https://www.manilatimes.net/port-infrastructure-development-ongoing/348640/ (accessed 15 April 2018)
Maldonado, S., González, A., Crone, S., Automatic time series analysis for electric load forecasting via support vector regression. Applied Soft Computing Journal 83 (2019) 105616.
Maric, M. , Stanimirovic, Z. , Stanojevic, P. , 2013. An efficient memetic algorithm for the uncapacitated single allocation hub location problem. Soft Computing. 17 (3), 445–466.
Mokhtar, H., Perwira Redi, A .A .N., Krishnamoorthy, M., Ernst, A. T. 2018. An intermodal hub location problem for container distribution in Indonesia. Computer and Operations Research 16(14).
AL-Musaylh, M.S., Deo, R.C., Li, Y., Adamowski, J.F., Two-phase particle swarm optimized-support vector regression hybrid model integrated with improved empirical mode decomposition with adaptive noise for multiple-horizon electricity demand forecasting. Applied Energy (217) 1 May 2018, pp 422-439.
National Economic and Development Authority. http://www.neda.gov.ph/infrastructure-flagship-projects/ (accessed 15 April 2018)
Odchimar, A., Hanaoka, S., 2016, Intermodal freight network incorporating hub-and-spoke and direct calls for the archipelagic Philippines, Maritime Economics and Logistics, 1479 -2931
Oxford Business Group, 2015. “New port infrastructure and better domestic connections to aid Philippine transport”. https://oxfordbusinessgroup.com/analysis/island-hopping-new-port-infrastructure-and-better-domestic-connections (accessed 15 April 2018)
Philippine Development Plan, 2017-2022. http://pdp.neda.gov.ph/wp-content/uploads/2017/01/PDP-2017-2022-07-20-2017.pdf (accessed 15 April 2018)
Philippine Statistics Authority, 2018. https://psa.gov.ph/statistics/administrative-based/domestic-trade-statistics
Plakandaras, V., Papadimitriou V., Gogas P., Forecasting transportation demand for the U.S. market. Transportation Research Part A 126 (2019) 195–214
Presidential Decree 857 (1987) Office of the President of the Philippines. http://www.ppa.com.ph/sites/default/files/transparency_docs/PD_857.pdf
Schobel, Anita, 2006. Optimization in Public Transportation: Stop Location, Delay Management and Tariff Zone Design in a Public Transportation. Springer, p. 2.
Shabania, S., Yousefia, P., Naser, G., Support vector machines in urban water demand forecasting using phase space reconstruction. XVIII International Conference on Water Distribution Systems Analysis, WDSA2016, Procedia Engineering 186 ( 2017 ) 537 – 543
Skorin-Kapov D., Skorin-Kapov J. 1994. On tabu search for the location of interacting hub facilities. Euro Journal of Operations Research. 73 (502-509).
Suh, D.Y., Ryerson, M.S., Forecast to grow: Aviation demand forecasting in an era of demand uncertainty and optimism bias. Transportation Research Part E 128 (2019) 400–416.
Villegas, M.A., Pedregala, D.J., Traperob, J.R., A support vector machine for model selection in demand forecasting applications. Computers & Industrial Engineering 121 (2018) 1–7.
Wang, S.-J., Wang, W.-L., Huang, C.-T., Chen, S.-C. Improving inventory effectiveness in RFID-enabled global supply chain with Grey forecasting model. Journal of Strategic Information Systems 20 (2011) 307–322.
Zhao, M., Zhao, C., Yu, L., Li, G., Huang, J. Zhu, H., He, W., Prediction and analysis of WEEE in China based on the gray model. The Tenth International Conference on Waste Management and Technology (ICWMT), Procedia Environmental Sciences 31 ( 2016 ) 925 – 934.
Zhou, J-J, 2013, The application of grey forecasting model based on excel modeling and solving in logistics demand forecast, IEEE 2013 10th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), DOI: 10.1109/ICCWAMTIP.2013.6716667.