A Dynamic Price Model with Demand Prediction and Task Classification in Grid

In the market-oriented grid systems, price management is one of the significant parts, which is used to balance the resource load and adjust the profits of resource providers. This paper proposes a dynamic price model based on demand prediction and task classification. We apply Markov chain to predict the future demands of grid resources and propose a resource price-adjusting mechanism based on the future demands, which takes into the interdependence of price and demand into consideration. Therefore, the mechanism can balance resource loads and guarantee the profits of resource providers at the same time. In addition, we classified the tasks into two categories: exclusive tasks and shared tasks. According to the differences between them, we provide two different task-pricing strategies. Based on these, we introduce a novel task-pricing mechanism, which takes serving time, the workload and the type of the task into consideration at the same time. Compared with time-based pricing model, it is more reasonable and more feasible. Simulation results show the applicability and effectiveness of our work.

[1]  Qian Pei-de.  Server Load Prediction Based on Time Series , 2006 .

[2]  Jingyan Song,et al.  A novel networked traffic parameter forecasting method based on Markov chain model , 2003, SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483).

[3]  Sajal K. Das,et al.  A game theory based pricing strategy for job allocation in mobile grids , 2004, 18th International Parallel and Distributed Processing Symposium, 2004. Proceedings..

[4]  M.A. Teixeira,et al.  Fuzzy hidden Markov predictor in electric load forecasting , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[5]  Wei Sun,et al.  Predicting Running Time of Grid Tasks based on CPU Load Predictions , 2006, 2006 7th IEEE/ACM International Conference on Grid Computing.

[6]  Peter A. Dinda,et al.  The statistical properties of host load , 1999, Sci. Program..

[7]  R. V. van Nieuwpoort,et al.  The Grid 2: Blueprint for a New Computing Infrastructure , 2003 .

[8]  Rajkumar Buyya,et al.  Economic-based Distributed Resource Management and Scheduling for Grid Computing , 2002, ArXiv.

[9]  Yang Jin,et al.  An autonomous pricing strategy toward market economy in computational grids , 2005, International Conference on Information Technology: Coding and Computing (ITCC'05) - Volume II.

[10]  Lulai Yuan,et al.  A Grid Resource Price-adjusting Strategy Based on Price Influence Model , 2006, 2006 Fifth International Conference on Grid and Cooperative Computing (GCC'06).

[11]  Michael Schwind,et al.  Dynamic Resource Prices in a Combinatorial Grid System , 2006, The 8th IEEE International Conference on E-Commerce Technology and The 3rd IEEE International Conference on Enterprise Computing, E-Commerce, and E-Services (CEC/EEE'06).

[12]  David Abramson,et al.  The Grid Economy , 2005, Proceedings of the IEEE.

[13]  D. Gan,et al.  Price forecasting using an integrated approach , 2004, 2004 IEEE International Conference on Electric Utility Deregulation, Restructuring and Power Technologies. Proceedings.

[14]  T.Q.D. Khoa,et al.  Application of hidden Markov and Bayes for demand forecasting , 2006, 2006 IEEE Power India Conference.