Optimal Workflow Scheduling in Critical Infrastructure Systems with Neural Networks

 

S. Vukmirović*, A. Erdeljan, L. Imre, D. Čapko

 

Faculty of Technical Sciences. University of Novi Sad. Novi Sad, Serbia *srdjanvu@uns.ac.rs.

 

Abstract

Critical infrastructure systems (CISs), such as power grids, transportation systems, communication networks and water systems are the backbone of a country's national security and industrial prosperity. These CISs execute large numbers of workflows with very high resource requirements that can span through different systems and last for a long time. The proper functioning and synchronization of these workflows is essential since humanity's well-being is connected to it. Because of this, the challenge of ensuring availability and reliability of these services in the face of a broad range of operating conditions is very complicated. This paper proposes an architecture which dynamically executes a scheduling algorithm using feedback about the current status of CIS nodes. Different artificial neural networks (ANNs) were created in order to solve the scheduling problem. Their performances were compared and as the main result of this paper, an optimal ANN architecture for workflow scheduling in CISs is proposed. A case study is shown for a meter data management system with measurements from a power distribution management system in Serbia. Performance tests show that significant improvement of the overall execution time can be achieved by ANNs.

Keywords: Critical infrastructure system, neural network, grid computing.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

References

[1] Chandra J., Robust and resilient Critical Infrastructure Systems, Proceedings of the 38th Annual Hawaii, 2005, pp 62-66.         [ Links ]

[2] Polycarpou, M., Ellinas, G., Kyriakides, E., Panayiotou, C., Intelligent Health Monitoring of Critical Infrastructure Systems, Complexity in Engineering, 2010. COMPENG '10, March 2010, pp. 18-20.         [ Links ]

[3] Han C., Liu L., Rong M. et al, Addressing criticality levels in critical infrastructure system, Systems, Man and Cybernetics, October 2009, pp. 3965 - 3970.         [ Links ]

[4] Vukmirović S., Erdeljan A., Lendak I., Čapko D. : A novel software architecture for Smart Metering systems, Journal of Scientific and Industrial Research (JSIR), 2010, Vol. 2010, No 12, pp. 937-941.         [ Links ]

[5] Erdeljan A., Trninić N., Čapko D., An OPC Data Access server designed for large number of items, 6th International Symposium Interdisciplinary Regional Research (Hungary, Romania, Yugoslavia) ISIRR 2002, Novi Sad, 2002.         [ Links ]

[6] Little R., Toward more robust infrastructure: observations on improving the resilience and reliability of critical systems, System Sciences, 2003. Proceedings of the 36th Annual Hawaii, 9 pp.         [ Links ]

[7] Linda, O.,Vollmer, T.,Manic, M., Neural Network based Intrusion Detection System for critical infrastructures, International Joint Conference on Neural Networks, 2009., pp. 1827 - 1834.         [ Links ]

[8] Otavio A.S. Carpinteiro, Rafael C. Lemeb, Antonio C. Zambroni de Souza, Carlos A.M. Pinheiro, Edmilson M. Moreira, "Long-term load forecasting via a hierarchical neural model with time integrators", Electric Power Systems Research 77 (2007) 371-378.         [ Links ]

[9] Yamin HY, Shahidehpour SM, Li Z. "Adaptive short-term electricity price forecasting using artificial neural networks in the restructured power markets", Electrical Power Energy Systems 2004; 26:571-81.         [ Links ]

[10] Paras Mandal, Tomonobu Senjyu, Toshihisa Funabashi, "Neural networks approach to forecast several hour ahead electricity prices and loads in deregulated market", Energy Conversion and Management 47 (2006) 2128-2142.         [ Links ]

[11] Agrawal R. K., Merh B., Fatnani P., Yadav R., Gangopadhyay S., SCADA functionality for control operations of INDUS-2, 10th ICALEPCS Int. Conf. on Accelerator & Large Expt. Physics Control Systems. Geneva, 10 - 14 Oct 2005, PO1.098-8 (2005).         [ Links ]

[12] Qiu B., Gooi H. B., Web-Based SCADA Display Systems (WSDS) for Access via Internet , Power Systems, IEEE Transactions on, May 2000, Issue 2 , pages 681-686.         [ Links ]

[13] Ozdemir E., Karacor M., Mobile phone based SCADA for industrial automation, ISA Transactions, Volume 45, Number 1, January 2006, pages 67-75.         [ Links ]

[14] Vukmirović S., Lukovic S., Erdeljan A., Kulic F., Software architecture for Smart Metering systems with Virtual Power Plant, The 15th IEEE Mediterranean Electrotechnical Conference, Valletta, Malta, April 2010.         [ Links ]

[15] Vukmirović S., Erdeljan A., Čapko D., Lendak I., Nedić N. : Optimization of workflow scheduling in Utility Management System with hierarchical neural network, 2011 Vol. 4, pp. 672-679.         [ Links ]

[16] Vukmirović S., Nedić N., Erdeljan A., Lendak I., Čapko D. : A Genetic Algorithm Approach for Utility Management System Workflow Scheduling, Information technology and control, 2010, Vol. 39, No 4, pp. 310-316.         [ Links ]

[17] Rumelhart D., Hinton G., Williams R. Learning internal representations by error propagation, Parallel Distributed Processing, Vol. 1, Chapter 8, MIT Press, 1986.         [ Links ]