Replication is an integral technique for distributed data systems. By maintaining multiple copies of the same data over a network, it increases their availability, throughput, and responsiveness. However, this benefit inherently demands increased memory usage for the replicas. This paper presents a novel replica placement policy called ROVN (Replica-over-NVM), which exploits the fact that for cost savings, the performance requirements are disparate across the data nodes in distributed systems. Replicas typically conduct asynchronous writes for rapid responsiveness, and thus it has little impact on user-perceived latency. In this regard, ROVN places replicas in a slow but inexpensive memory (NVM), while maintaining the master in a fast but high-cost memory (DRAM). This policy can reduce the TCO (Total Cost of Ownership) of data centers without compromising user experience. We implement ROVN in Redis, a commercial-level distributed NoSQL database, by addressing a set of challenges that arise during its realization. Performance evaluation with the Memtier benchmark shows that ROVN achieves significant cost savings in distributed data systems, with neither performance loss during normal operation nor a continuous slowdown even in the event of a failure.
In this paper, a 5.67-8.75GHz LC VCO with small gain variation and reconfigurable buffer for 2.4GHz-band WLAN applications is presented and implemented in a Semiconductor Manufacturing International Corporation (SMIC) 55 nm CMOS process. The VCO gain is a strong function of the capacitance. For wide frequency tuning range meaning the large gain variation. The gain calibration scheme is proposed to obtain small gain variation across the frequency range. This letter proposes a reconfigurable buffer with adjustable amplitude, low jitter, and small supply coupling issues. The results show the proposed gain calibration scheme is very effective. The measured phase noise at 6.69MHz offset is -123.2dBc/Hz at 4.9GHz output frequency.
The performance and quality of electric vehicle batteries have an important impact on the user experience of new energy vehicles. The power battery pack needs to go through a strict inspection process before being installed on the vehicle. There is no doubt that the efficiency of battery testing is the key to the production capacity of new energy vehicles. Develop an efficient, practical and stable battery testing system to automate the battery testing process, reduce the misoperation of the testing personnel, ensure the safety of the testing personnel as much as possible and greatly increase the production capacity of new energy vehicles. Nevertheless, the method of general measuring instrument in traditional EOL field test is manual debugging, which has low efficiency and low degree of automation, which cannot meet the increasingly complex field test circuit. Hence, it is very necessary to integrate component automation systems to further improve measurement efficiency. Based on the test content in the EOL test, this paper designs and develops a highly automated test and diagnosis system, introduces several general measuring instruments into the system and discards the VB and MFC in the host computer and replaces it with the introduction of SCPI commands and python. The use of Ethernet to form a path between the physical layer and program control aims to make the automatic testing of general electronic equipment and remote circuit modules a reality. This article introduces the instrument circuit hardware module and host computer language programming module in detail. The final results show that the system has good portability and robustness and is suitable for running on various platforms.
In this paper, a new transition regulation method (TRM) for three-level DC-DC converters is proposed. The conventional asymmetrical control for three-level DC-DC converters induces imbalanced currents in components, and the imbalanced loss would lead to characteristic variation which is harmful to the converter’s reliability. The proposed TRM strategy is analyzed and derived in this paper, and the circuit balance of the TRM is compared with conventional control methods. Finally, a prototype is implemented to verify the feasibility of the TRM, and the equalized operation current and loss of components can be verified by the experimental results.
This letter presents a novel approximate adder that significantly improves computation accuracy by utilizing a dual carry prediction and error reduction scheme. In our experiments, the proposed adder improves mean error distance (MED) and mean relative error distance (MRED) by up to 58.6% and 58.5%, respectively, when compared with existing approximate adders. Also, when implemented in 65-nm CMOS technology, the proposed adder reduces area, delay, and power by 37%, 48%, and 41%, respectively, compared with the traditional adder. Furthermore, the effectiveness of our design over existing adders is investigated using a digital image processing application.