Demand Forecasting Application with Regression and IoT Based Inventory Management System: A Case Study of a Semiconductor Manufacturing Company

Abstract:

The accuracy of demand forecasting has a significant impact on the supply chain system's performance, which in turn has a major effect on company performance. Accurate forecasting will allow the organization to make the best use of its resources. The synchronization of customer orders to support production is critical for on-time order fulfillment. However, In fact many organizations report that their forecasting method is not working as effectively as they had hoped because orders regularly alter due to client demands. The purpose of this paper is to present an Internet of Things (IoT)-based inventory management system (IMS) that combines a causal method of multiple linear regressions (MLR) with genetic algorithms (GA) to improve the accuracy of demand forecasting in the future period by the customer as closely as feasible and enable smart inventory for Industry 4.0. Based on the data gathered from a semiconductor company that specializes in low-volume, high-mix contract manufacturing equipment and services integration, the suggested IoT-based IMS indicates that inventory productivity and efficiency could be enhanced, and it is resilient to order fluctuation.

• Periodical: International Journal of Engineering Research in Africa (Volume 60)
• Pages: 189-210
• DOI: https://doi.org/10.4028/p-8ntq24
• Online since: May 2022
• Authors: Asmae El Jaouhari*, Zineb Alhilali, Jabir Arif, Soumaya Fellaki, Mohamed Amejwal, Khaoula Azzouz
• Keywords: Demand Forecasting, Genetic Algorithm, Industry 4.0, Internet of Things, Inventory Management System, Multiple Linear Regressions

References

[1] A. P. de Barros, C. S. Ishikiriyama, R. C. Peres, et C. F. S. Gomes, « Processes and Benefits of the Application of Information Technology in Supply Chain Management: An Analysis of the Literature », Procedia Computer Science, vol. 55, p.698‑705, janv. 2015,.

DOI: 10.1016/j.procs.2015.07.077

[2] A. Jayaram, « An IIoT quality global enterprise inventory management model for automation and demand forecasting based on cloud », mai 2017, p.1258‑1263.

DOI: 10.1109/ccaa.2017.8230011

[3] C. J. Bartodziej, « Introduction », in The Concept Industry 4.0 : An Empirical Analysis of Technologies and Applications in Production Logistics, C. J. Bartodziej, Éd. Wiesbaden: Springer Fachmedien, 2017, p.1‑6.

[4] J. Lee, H.-A. Kao, et S. Yang, « Service Innovation and Smart Analytics for Industry 4.0 and Big Data Environment », Procedia CIRP, vol. 16, p.3‑8, janv. 2014,.

DOI: 10.1016/j.procir.2014.02.001

[5] J. Qin, Y. Liu, et R. Grosvenor, « A Categorical Framework of Manufacturing for Industry 4.0 and Beyond », Procedia CIRP, vol. 52, p.173‑178, janv. 2016,.

DOI: 10.1016/j.procir.2016.08.005

[6] K.-C. Tan, «A Framework of Supply Chain Management Literature», European Journal of Purchasing & Supply Management, vol. 7, p.39‑48, mars 2001,.

DOI: 10.1016/S0969-7012(00)00020-4

[7] R. Handfield, P. Cousins, B. Lawson, et K. Petersen, « How Can Supply Management Really Improve Performance? A Knowledge-Based Model of Alignment Capabilities », Journal of Supply Chain Management, vol. 51, oct. 2014,.

DOI: 10.1111/jscm.12066

[8] B. Scholz-Reiter, E. M. Frazzon, et T. Makuschewitz, « Integrating manufacturing and logistic systems along global supply chains », CIRP Journal of Manufacturing Science and Technology, vol. 2, no 3, p.216‑223, janv. 2010,.

DOI: 10.1016/j.cirpj.2010.03.003

[9] G. C. Stevens, « Integrating the Supply Chain », International Journal of Physical Distribution & Materials Management, vol. 19, no 8, p.3‑8, janv. 1989,.

[10] M. Peng, Y. Peng, et H. Chen, « Post-seismic supply chain risk management: A system dynamics disruption analysis approach for inventory and logistics planning », Computers & Operations Research, vol. 42, p.14‑24, févr. 2014,.

DOI: 10.1016/j.cor.2013.03.003

[11] T. Lee et H. Nam, « An Empirical Study on the Impact of Individual and Organizational Supply Chain Orientation on Supply Chain Management », The Asian Journal of Shipping and Logistics, vol. 32, p.249‑255, déc. 2016,.

DOI: 10.1016/j.ajsl.2016.12.009

[12] D. L. Cooke et T. R. Rohleder, « Inventory evaluation and product slate management in large-scale continuous process industries », Journal of Operations Management, vol. 24, no 3, p.235‑249, avr. 2006,.

DOI: 10.1016/j.jom.2004.08.009

[13] K. Ryu, I. Moon, S. Oh, et M. Jung, « A fractal echelon approach for inventory management in supply chain networks », International Journal of Production Economics, vol. 143, no 2, p.316‑326, juin 2013,.

DOI: 10.1016/j.ijpe.2012.01.002

[14] L. Chen, Ş. Yücel, et K. Zhu, « Inventory management in a closed-loop supply chain with advance demand information », Operations Research Letters, vol. 45, no 2, p.175‑180, mars 2017,.

DOI: 10.1016/j.orl.2017.02.002

[15] M. G. Matsebatlela et K. Mpofu, « Inventory Management Framework to minimize supply and demand mismatch on a manufacturing organization », IFAC-PapersOnLine, vol. 48, no 3, p.260‑265, janv. 2015,.

DOI: 10.1016/j.ifacol.2015.06.091

[16] M. Udenio, K. Hoberg, et J. C. Fransoo, « Inventory agility upon demand shocks: Empirical evidence from the financial crisis », Journal of Operations Management, vol. 62, p.16‑43, sept. 2018,.

DOI: 10.1016/j.jom.2018.08.001

[17] V. Lukinskiy, V. Lukinskiy, et B. Sokolov, « Control of inventory dynamics: A survey of special cases for products with low demand », Annual Reviews in Control, vol. 49, p.306‑320, janv. 2020,.

DOI: 10.1016/j.arcontrol.2020.04.005

[18] T. Iida, « Benefits of leadtime information and of its combination with demand forecast information », International Journal of Production Economics, vol. 163, p.146‑156, mai 2015,.

DOI: 10.1016/j.ijpe.2015.02.010

[19] R. M. van Steenbergen et M. R. K. Mes, « Forecasting demand profiles of new products », Decision Support Systems, vol. 139, p.113401, déc. 2020,.

DOI: 10.1016/j.dss.2020.113401

[20] B. Zhang, D. Duan, et Y. Ma, « Multi-product expedited ordering with demand forecast updates », International Journal of Production Economics, vol. 206, p.196‑208, déc. 2018,.

DOI: 10.1016/j.ijpe.2018.09.034

[21] E. Wilhelmsson et H. Persson, « The impact of omni-channel retailing on demand planning for new products at IKEA », 2018, Consulté le: nov. 20, 2021. [En ligne]. Disponible sur: http://lup.lub.lu.se/student-papers/record/8957979.

[22] E. Balugani, F. Lolli, R. Gamberini, B. Rimini, et A. Regattieri, « Clustering for inventory control systems », IFAC-PapersOnLine, vol. 51, no 11, p.1174‑1179, janv. 2018,.

DOI: 10.1016/j.ifacol.2018.08.431

[23] O. Al-Khazali et A. Mirzaei, « Stock market anomalies, market efficiency and the adaptive market hypothesis: Evidence from Islamic stock indices », Journal of International Financial Markets, Institutions and Money, vol. 51, p.190‑208, nov. 2017,.

DOI: 10.1016/j.intfin.2017.10.001

[24] N. Wang, J. Guo, X. Liu, et T. Fang, « A service demand forecasting model for one-way electric car-sharing systems combining long short-term memory networks with Granger causality test », Journal of Cleaner Production, vol. 244, p.118812, janv. 2020,.

DOI: 10.1016/j.jclepro.2019.118812

[25] C.-Y. Lee et M.-C. Chiang, « Aggregate demand forecast with small data and robust capacity decision in TFT-LCD manufacturing », Computers & Industrial Engineering, vol. 99, p.415‑422, sept. 2016,.

DOI: 10.1016/j.cie.2016.02.013

[26] J. Cano-Belmán et H. Meyr, « Deterministic allocation models for multi-period demand fulfillment in multi-stage customer hierarchies », Computers & Operations Research, vol. 101, p.76‑92, janv. 2019,.

DOI: 10.1016/j.cor.2018.09.002

[27] Z. Li et Q. (Grace) Fu, « Robust inventory management with stock-out substitution », International Journal of Production Economics, vol. 193, p.813‑826, nov. 2017,.

DOI: 10.1016/j.ijpe.2017.09.011

[28] Y. Rekik, C. H. Glock, et A. A. Syntetos, « Enriching demand forecasts with managerial information to improve inventory replenishment decisions: Exploiting judgment and fostering learning », European Journal of Operational Research, vol. 261, no 1, p.182‑194, août 2017,.

DOI: 10.1016/j.ejor.2017.02.001

[29] R. Fildes, K. Nikolopoulos, S. Crone, et A. Syntetos, « Forecasting and operational research: A review », Journal of The Operational Research Society - J OPER RES SOC, vol. 59, p.1150‑1172, mai 2008,.

DOI: 10.1057/palgrave.jors.2602597

[30] R. Chen, Z. Rao, G. Liu, Y. Chen, et S. Liao, « The long-term forecast of energy demand and uncertainty evaluation with limited data for energy-imported cities in China: a case study in Hunan », Energy Procedia, vol. 160, p.396‑403, févr. 2019,.

DOI: 10.1016/j.egypro.2019.02.173

[31] W. Puchalsky, G. T. Ribeiro, C. P. da Veiga, R. Z. Freire, et L. dos Santos Coelho, « Agribusiness time series forecasting using Wavelet neural networks and metaheuristic optimization: An analysis of the soybean sack price and perishable products demand », International Journal of Production Economics, vol. 203, p.174‑189, sept. 2018,.

DOI: 10.1016/j.ijpe.2018.06.010

[32] A. Sardinha-Lourenço, A. Andrade-Campos, A. Antunes, et M. S. Oliveira, « Increased performance in the short-term water demand forecasting through the use of a parallel adaptive weighting strategy », Journal of Hydrology, vol. 558, p.392‑404, mars 2018,.

DOI: 10.1016/j.jhydrol.2018.01.047

[33] S. Xu, H. K. Chan, et T. Zhang, « Forecasting the demand of the aviation industry using hybrid time series SARIMA-SVR approach », Transportation Research Part E: Logistics and Transportation Review, vol. 122, p.169‑180, févr. 2019,.

DOI: 10.1016/j.tre.2018.12.005

[34] E. M. Burger et S. J. Moura, « Gated ensemble learning method for demand-side electricity load forecasting », Energy and Buildings, vol. 109, p.23‑34, déc. 2015,.

DOI: 10.1016/j.enbuild.2015.10.019

[35] L. Ferbar Tratar, « Forecasting method for noisy demand », International Journal of Production Economics, vol. 161, p.64‑73, mars 2015,.

DOI: 10.1016/j.ijpe.2014.11.019

[36] L. F. Tratar, « Joint optimisation of demand forecasting and stock control parameters », International Journal of Production Economics, vol. 127, no 1, p.173‑179, sept. 2010,.

DOI: 10.1016/j.ijpe.2010.05.009

[37] Y. Zhao, H. Zhang, L. An, et Q. Liu, « Improving the approaches of traffic demand forecasting in the big data era », Cities, vol. 82, p.19‑26, déc. 2018,.

DOI: 10.1016/j.cities.2018.04.015

[38] H. Reinhardt, J.-P. Bergmann, M. Münnich, D. Rein, et M. Putz, « A survey on modeling and forecasting the energy consumption in discrete manufacturing », Procedia CIRP, vol. 90, p.443‑448, janv. 2020,.

DOI: 10.1016/j.procir.2020.01.078

[39] M. E. Khodayar et H. Wu, «Demand Forecasting in the Smart Grid Paradigm: Features and Challenges», The Electricity Journal, vol. 28, no 6, p.51‑62, juill. 2015,.

DOI: 10.1016/j.tej.2015.06.001

[40] F. Lücker et R. W. Seifert, « Building up Resilience in a Pharmaceutical Supply Chain through Inventory, Dual Sourcing and Agility Capacity », Omega, vol. 73, p.114‑124, déc. 2017,.

DOI: 10.1016/j.omega.2017.01.001

[41] C. J. Taylor, D. J. Pedregal, P. C. Young, et W. Tych, « Environmental time series analysis and forecasting with the Captain toolbox », Environmental Modelling & Software, vol. 22, no 6, p.797‑814, juin 2007,.

DOI: 10.1016/j.envsoft.2006.03.002

[42] J.-F. Cordeau et G. Laporte, « The dial-a-ride problem: models and algorithms », Ann Oper Res, vol. 153, no 1, p.29‑46, sept. 2007,.

DOI: 10.1007/s10479-007-0170-8

[43] H. Patil et Brig. R. Divekar, «Inventory Management Challenges for B2C E-commerce Retailers», Procedia Economics and Finance, vol. 11, p.561‑571, janv. 2014,.

DOI: 10.1016/S2212-5671(14)00221-4

[44] J. Dai, S. Peng, et S. Li, «Mitigation of Bullwhip Effect in Supply Chain Inventory Management Model», Procedia Engineering, vol. 174, p.1229‑1234, janv. 2017,.

DOI: 10.1016/j.proeng.2017.01.291

[45] W. Muchaendepi, C. Mbohwa, T. Hamandishe, et J. Kanyepe, « Inventory Management and Performance of SMEs in the Manufacturing Sector of Harare », Procedia Manufacturing, vol. 33, p.454‑461, janv. 2019,.

DOI: 10.1016/j.promfg.2019.04.056

[46] A. Olaru et C. Gratie, « Agent-Based, Context-Aware Information Sharing for Ambient Intelligence », International Journal on Artificial Intelligence Tools, vol. 20, no 6, p.985‑1000, 2011,.

DOI: 10.1142/s0218213011000498

[47] U. D. Atmojo, Z. Salcic, K. I.-K. Wang, et H. Park, « System-level approach to the design of ambient intelligence systems based on wireless sensor and actuator networks », J Ambient Intell Human Comput, vol. 6, no 2, p.153‑169, avr. 2015,.

DOI: 10.1007/s12652-014-0221-3

[48] B. S. S. Tejesh et S. Neeraja, « Warehouse inventory management system using IoT and open source framework », Alexandria Engineering Journal, vol. 57, no 4, p.3817‑3823, déc. 2018,.

DOI: 10.1016/j.aej.2018.02.003

[49] J. Lee, B. Bagheri, et H.-A. Kao, « A Cyber-Physical Systems architecture for Industry 4.0-based manufacturing systems », Manufacturing Letters, vol. 3, p.18‑23, janv. 2015,.

DOI: 10.1016/j.mfglet.2014.12.001

[50] J. Arif, F. Jawab, et Y. MOUZOUNA, « Design on Improvement of Traceability Process in the Outsourcing of Logistics' Activities Using the Internet of Things (IoT) Applications », Maejo international journal of science and technology, vol. 29, p.1093‑1108, janv. (2020).

[51] E. Manavalan et K. Jayakrishna, « A review of Internet of Things (IoT) embedded sustainable supply chain for industry 4.0 requirements », Computers & Industrial Engineering, vol. 127, p.925‑953, janv. 2019,.

DOI: 10.1016/j.cie.2018.11.030

[52] C. Faller et D. Feldmüller, « Industry 4.0 Learning Factory for regional SMEs », Procedia CIRP, vol. 32, p.88‑91, janv. 2015,.

DOI: 10.1016/j.procir.2015.02.117

[53] R. Raghu, « The many dimensions of successful IoT deployment », Network Security, vol. 2018, no 12, p.10‑15, déc. 2018,.

DOI: 10.1016/s1353-4858(18)30126-0

[54] O. Bello, S. Zeadally, et M. Badra, « Network layer inter-operation of Device-to-Device communication technologies in Internet of Things (IoT) », Ad Hoc Networks, vol. 57, p.52‑62, mars 2017,.

DOI: 10.1016/j.adhoc.2016.06.010

[55] J. M. Talavera et al., « Review of IoT applications in agro-industrial and environmental fields », Computers and Electronics in Agriculture, vol. 142, p.283‑297, nov. 2017,.

DOI: 10.1016/j.compag.2017.09.015

[56] J. Mongay Batalla, M. Gajewski, W. Latoszek, P. Krawiec, C. X. Mavromoustakis, et G. Mastorakis, « ID-based service-oriented communications for unified access to IoT », Computers & Electrical Engineering, vol. 52, p.98‑113, mai 2016,.

DOI: 10.1016/j.compeleceng.2016.02.020

[57] H. Elazhary, « Internet of Things (IoT), mobile cloud, cloudlet, mobile IoT, IoT cloud, fog, mobile edge, and edge emerging computing paradigms: Disambiguation and research directions », Journal of Network and Computer Applications, vol. 128, p.105‑140, févr. 2019,.

DOI: 10.1016/j.jnca.2018.10.021

[58] H. El-Sayed et al., « Edge of Things: The Big Picture on the Integration of Edge, IoT and the Cloud in a Distributed Computing Environment », IEEE Access, vol. 6, p.1706‑1717, 2018,.

DOI: 10.1109/access.2017.2780087

[59] M. A. A. da Cruz, J. J. P. C. Rodrigues, P. Lorenz, P. Solic, J. Al-Muhtadi, et V. H. C. Albuquerque, « A proposal for bridging application layer protocols to HTTP on IoT solutions », Future Generation Computer Systems, vol. 97, p.145‑152, août 2019,.

DOI: 10.1016/j.future.2019.02.009

[60] S. N. Swamy, D. Jadhav, et N. Kulkarni, « Security threats in the application layer in IOT applications », in 2017 International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC), févr. 2017, p.477‑480.

DOI: 10.1109/i-smac.2017.8058395

[61] J. Gubbi, R. Buyya, S. Marusic, et M. Palaniswami, « Internet of Things (IoT): A vision, architectural elements, and future directions », Future Generation Computer Systems, vol. 29, no 7, p.1645‑1660, sept. 2013,.

DOI: 10.1016/j.future.2013.01.010

[62] Y. Lv, C. K. M. Lee, H. K. Chan, et W. H. Ip, « RFID-based colored Petri net applied for quality monitoring in manufacturing system », 2012,.

DOI: 10.1007/s00170-011-3568-z

[63] C. B. Tan, M. H. A. Hijazi, Y. Lim, et A. Gani, « A survey on Proof of Retrievability for cloud data integrity and availability: Cloud storage state-of-the-art, issues, solutions and future trends», Journal of Network and Computer Applications, vol. 110, p.75‑86, mai 2018,.

DOI: 10.1016/j.jnca.2018.03.017

[64] M. D. Redel-Macías, C. Hervás-Martínez, P. A. Gutiérrez, S. Pinzi, A. J. Cubero-Atienza, et M. P. Dorado, « Computational models to predict noise emissions of a diesel engine fueled with saturated and monounsaturated fatty acid methyl esters », Energy, vol. 144, p.110‑119, févr. 2018,.

DOI: 10.1016/j.energy.2017.11.143

[65] J. Arif, Y. Mouzouna, et F. Jawab, The Use of Internet of Things (IoT) Applications in the Logistics Outsourcing: Smart RFID Tag as an Example. 2019.Third European Conference on Industrial Engineering and Operations Management IEOM, Pilsen, Czech, July (2019).

[66] L. Cui, J. Deng, F. Liu, Y. Zhang, et M. Xu, « Investigation of RFID investment in a single retailer two-supplier supply chain with random demand to decrease inventory inaccuracy », Journal of Cleaner Production, vol. 142, p.2028‑2044, janv. 2017,.

DOI: 10.1016/j.jclepro.2016.11.081

[67] A. Seba, N. Nouali-Taboudjemat, N. Badache, et H. Seba, « A review on security challenges of wireless communications in disaster emergency response and crisis management situations », Journal of Network and Computer Applications, vol. 126, p.150‑161, janv. 2019,.

DOI: 10.1016/j.jnca.2018.11.010

[68] Q. Wang, X. Zhu, Y. Ni, L. Gu, et H. Zhu, « Blockchain for the IoT and industrial IoT: A review », Internet of Things, vol. 10, p.100081, juin 2020,.

DOI: 10.1016/j.iot.2019.100081

[69] G. Van der Heide, P. Buijs, K. J. Roodbergen, et I. F. A. Vis, « Dynamic shipments of inventories in shared warehouse and transportation networks », Transportation Research Part E: Logistics and Transportation Review, vol. 118, p.240‑257, oct. 2018,.

DOI: 10.1016/j.tre.2018.07.012

[70] M. S. Hossain et G. Muhammad, « Cloud-assisted Industrial Internet of Things (IIoT) – Enabled framework for health monitoring », Computer Networks, vol. 101, p.192‑202, juin 2016,.

DOI: 10.1016/j.comnet.2016.01.009

[71] X. Wang, J. Liu, Y. Wang, X. Chen, et L. Chen, « Efficient missing tag identification in blocker-enabled RFID systems », Computer Networks, vol. 164, p.106894, déc. 2019,.

DOI: 10.1016/j.comnet.2019.106894

[72] K. Azzouz, J. Arif, et M. B. Benboubker, « Exploratory Study of the Role of Logistics Service Providers in Terms of Traceability in the Process of Outsourcing of Logistics' Activities: Case of Moroccan LSP », International Journal of Engineering Research in Africa, vol. 54, p.187‑208, 2021,.

DOI: 10.4028/www.scientific.net/jera.54.187

[73] T. Kawanaka et T. Kudo, « Inventory Satisfaction Discrimination Method Utilizing Images and Deep Learning », Procedia Computer Science, vol. 126, p.937‑946, janv. 2018,.

DOI: 10.1016/j.procs.2018.08.028

[74] T. Fang et R. Lahdelma, « Evaluation of a multiple linear regression model and SARIMA model in forecasting heat demand for district heating system », Applied Energy, vol. 179, p.544‑552, oct. 2016,.

DOI: 10.1016/j.apenergy.2016.06.133

[75] B. M. Brentan, E. Luvizotto Jr., M. Herrera, J. Izquierdo, et R. Pérez-García, « Hybrid regression model for near real-time urban water demand forecasting », Journal of Computational and Applied Mathematics, vol. 309, p.532‑541, janv. 2017,.

DOI: 10.1016/j.cam.2016.02.009

[76] N. J. Johannesen, M. Kolhe, et M. Goodwin, « Relative evaluation of regression tools for urban area electrical energy demand forecasting », Journal of Cleaner Production, vol. 218, p.555‑564, mai 2019,.

DOI: 10.1016/j.jclepro.2019.01.108

[77] G. Guo, W. You, G. Qian, et W. Shao, « Parallel maximum likelihood estimator for multiple linear regression models », Journal of Computational and Applied Mathematics, vol. 273, p.251‑263, janv. 2015,.

DOI: 10.1016/j.cam.2014.06.005

[78] A. J. Hayter, W. Liu, et P. Ah-Kine, « A ray method of confidence band construction for multiple linear regression models », Journal of Statistical Planning and Inference, vol. 139, no 2, p.329‑334, févr. 2009,.

DOI: 10.1016/j.jspi.2008.04.029

[79] J. H. Holland, « Genetic algorithms and classifier systems: Foundations and future directions », Univ. of Michigan, Ann Arbor, MI (United States), LA-UR-87-1863; CONF-870775-1, janv. 1987. Consulté le: nov. 21, 2021. [En ligne]. Disponible sur: https://www.osti.gov/biblio/6277983.

[80] S. Dehuri, S. Patnaik, A. Ghosh, et R. Mall, « Application of elitist multi-objective genetic algorithm for classification rule generation », Applied Soft Computing, vol. 8, no 1, p.477‑487, janv. 2008,.

DOI: 10.1016/j.asoc.2007.02.009

[81] S.-W. Fei et Y. Sun, « Forecasting dissolved gases content in power transformer oil based on support vector machine with genetic algorithm », Electric Power Systems Research, vol. 78, no 3, p.507‑514, mars 2008,.

DOI: 10.1016/j.epsr.2007.04.006

[82] H. Ohtake, K. Shimose, J. G. da S. Foncseca, T. Takashima, T. Oozeki, et Y. Yamada, «Seasonal and Regional Variations of the Range of Forecast Errors of Global Irradiance by the Japanese Operational Physical Model », Energy Procedia, vol. 57, p.1247‑1256, janv. 2014,.

DOI: 10.1016/j.egypro.2014.10.114