Optimized power control using adaptive bus encoding technique in data transmission. (September 2019)

• Record Type: Journal Article
• Authors: Chintaiah, N.; Reddy, G. Umamaheswara
• Is Part Of: Computers & electrical engineering. Volume 78(2019)
• Page Start: 463
• Page End: 471
• Publication Date: 2019-09
• Subjects: Transition -- Probability -- Encoding -- Buses -- Window -- Low power; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2019.08.007
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Data bits are switched around by using bus wires when data transmission is conducted on an on-chip bus. The data is transmitted through the capsule network, but due to the long routing path, the power is wasted and the data transmission causes a delay. The data bits are transmitted in the capsule network, using wires by switching technique. This switching causes discharging and charging of the capacitance that is associated with the wires. Thus, the delay is increased and then dynamic power dissipation takes place. Sending or receiving data is required to modify data values which are transmitted on the buses for decreasing the switching movement in that way the amount of power consumed by the bus falls and the delay of the on-chip bus. Bus encoding is most commonly used for reducing this bus transition activity. In this study, a probability adaptive bus encoding technique is applied based on a proposed fixed window. The entire window was applied to the transition probability. The average transitional probability condition is used to form a cluster with highly correlated switching patterns. The clustered information is transformed into a grey code. Temporal redundancy in time is utilized in the proposed method for prevent the information loss that occurs during data retrieval. There is an additional power cost because of the circuitry of the encoder and decoder. The cluster efficiency for the proposed encoding technique has been improved by up to 75%. The dynamic power saving is now up to 5%.