Search Sites

Transactions of the Institute of Systems, Control and Information Engineers Vol. 18 (2005), No. 3

ISIJ International
belloff
ONLINE ISSN: 2185-811X
PRINT ISSN: 1342-5668
Publisher: THE INSTITUTE OF SYSTEMS, CONTROL AND INFORMATION ENGINEERS (ISCIE)

Backnumber

  1. Vol. 36 (2023)

  2. Vol. 35 (2022)

  3. Vol. 34 (2021)

  4. Vol. 33 (2020)

  5. Vol. 32 (2019)

  6. Vol. 31 (2018)

  7. Vol. 30 (2017)

  8. Vol. 29 (2016)

  9. Vol. 28 (2015)

  10. Vol. 27 (2014)

  11. Vol. 26 (2013)

  12. Vol. 25 (2012)

  13. Vol. 24 (2011)

  14. Vol. 23 (2010)

  15. Vol. 22 (2009)

  16. Vol. 21 (2008)

  17. Vol. 20 (2007)

  18. Vol. 19 (2006)

  19. Vol. 18 (2005)

  20. Vol. 17 (2004)

  21. Vol. 16 (2003)

  22. Vol. 15 (2002)

  23. Vol. 14 (2001)

  24. Vol. 13 (2000)

  25. Vol. 12 (1999)

  26. Vol. 11 (1998)

  27. Vol. 10 (1997)

  28. Vol. 9 (1996)

  29. Vol. 8 (1995)

  30. Vol. 7 (1994)

  31. Vol. 6 (1993)

  32. Vol. 5 (1992)

  33. Vol. 4 (1991)

  34. Vol. 3 (1990)

  35. Vol. 2 (1989)

  36. Vol. 1 (1988)

Transactions of the Institute of Systems, Control and Information Engineers Vol. 18 (2005), No. 3

Distributed Reinforcement Learning based on α-domination Strategy and its Application to Shared Resource Problems

Kei AOKI, Kokolo IKEDA, Hajime KIMURA, Sigenobu KOBAYASHI

pp. 81-88

Abstract

In the distributed systems in which information cannot be exchanged directly among agents, we deal with problems of deciding how each agent holds the shared resource. To achieve a lot of tasks greedily, agents tend to attempt to hold the resources for a long term. However the system performance decreases consequentially because it competes with the processing of other agents' tasks. To acquire cooperative policies that avoid above competition, we formulate the shared resource problems to multi-criteria decision making problems with the priority level by using the domain knowledge. We propose autonomous distributed control using distributed reinforcement learning that narrows the choice of action space by using the α-domination strategy based on value functions for the performance and the cooperation. The proposed method is applied to the distributed database systems, and simulation results shows that our method acquires cooperative policies and improves the throughput performance of the system.

Bookmark

Share it with SNS

Article Title

Distributed Reinforcement Learning based on α-domination Strategy and its Application to Shared Resource Problems

Expansion to a Multi-item Production Planning System for Implementing Mass Customization

Nobuyuki UENO, Kyozo FURUTA, Koji OKUHARA, Hiroaki SHIBUKI, Toshiaki KURAMOTO

pp. 89-99

Abstract

With the diversification of the customer need, there is an issue for a business model to realize mass customization in the automobile industry. A new production planning system of implementing mass customization, which is concerned with a single-item production planning system, has already been presented. This paper proposes a multi-item production and inventory planning model of the mass customization that considers the restriction of daily manufacturing capacity. This model becomes a stochastic programming problem of which sub problem is a linear programming problem. An efficient and practical solution algorithm for the multi-item model is developed.

Bookmark

Share it with SNS

Article Title

Expansion to a Multi-item Production Planning System for Implementing Mass Customization

A Solution for Optimal Order Splitting Policy of Make-to-Order Manufacturing Systems Based on Penalty for Delay in Appointed Date of Delivery

Yasuhiko TAKEMOTO, Ikuo ARIZONO

pp. 100-107

Abstract

Manufacturing systems are classified into make-to-stock (MTS) systems and make-to-order (MTO) systems. In particular, the MTO manufacturing systems have been applied to many enterprises in order to react to consumer's uncertain demands and various requirements. Until now, in the studies for the order splitting policy to some original equipment manufacturers (OEMs) under the MTO manufacturing systems, the expectation of the lead time has been mainly considered. In general, the lead-time has the variability because of the fluctuations of the processing time and the demand. Therefore, when the optimal operation of the MTO manufacturing systems is investigated, we should consider the possibility of the delay for the appointed date of delivery of products. In this study, taking the penalty of the delay of delivery into consideration, we investigate the order splitting policy to two OEMs having the difference in the processing cost and the capacity.

Bookmark

Share it with SNS

Article Title

A Solution for Optimal Order Splitting Policy of Make-to-Order Manufacturing Systems Based on Penalty for Delay in Appointed Date of Delivery

On a Method to Estimate Worst Case Effectiveness of the System for Process Optimization under Uncertainty

Eiki YAMAKAWA, Hiroko SHIMASE, Genichi EMOTO

pp. 108-117

Abstract

At the phase of feasibility study on the system for process optimization, effectiveness of the system is often estimated in terms of a mathematical program formulated from the regional analysis of the operating results. A two-level mathematical programming is presented, which predicts the optimal cost in the worst case caused by the error involved in the process model. In particular, nonlinear inequality constraints of the upper level problem are proposed to give a limit on the acceptable error range. In order to examine the efficiency of the proposed method, a case study on the operation optimizing system of the electric power plant is reported.

Bookmark

Share it with SNS

Article Title

On a Method to Estimate Worst Case Effectiveness of the System for Process Optimization under Uncertainty

Delayed Feedback Control of Linear Systems with State Jump

Kentaro HIRATA, Hideki KOKAME

pp. 118-125

Abstract

The effect of the delayed feedback control on the stability of periodic solutions of linear systems with sate jump is studied. Although the stability of the open-loop and the OGY feedback cases can be analyzed via matrix representations (Poincare map), the system with DFC requires an operator representation of the state transition on a certain function space due to the infinite-dimensionality caused by the time delay element in the controller. A stability condition is given in terms of the spectrum of this operator. Also an analytic formula and a numerical method for the computation of the spectrum are provided.

Bookmark

Share it with SNS

Article Title

Delayed Feedback Control of Linear Systems with State Jump

You can use this feature after you logged into the site.
Please click the button below.

Advanced Search

Article Title

Author

Abstract

Journal Title

Year

Please enter the publication date
with Christian era
(4 digits).

Please enter your search criteria.