The increasing gap between limited computing resources and the rapid growth of data has led to the development of low-consumption computing technologies for big data analytics (LCCT-BigDataAna). For small and medium-sized enterprises, as well as research institutions with tight budgets, spending large sums of money to boost computing power for big data analysis is not feasible. Thus, finding ways to overcome the limitations of computing resources and still provide high-quality big data analytics is a key research topic in the field of big data computing, and LCCT-BigDataAna is attracting more and more attention in both industry and academia.

LCCT-BigDataAna involves optimizing and innovating hardware and software to make big data analytics more efficient. This includes pre-processing data, efficiently storing and managing it, and developing novel learning and modeling technologies for big data analytics. However, raw big data often has issues such as missing values, outliers, and noise that make it difficult to use for big data analytics. In addition, cross-regional storage is becoming the norm for big data collection and presentation due to the disadvantages of centralized storage. Hence, designing methods to obtain reliable results from partial data that is consistent with the overall results for the big data is another important problem worthy of exploration. For situations with limited computing resources, it is required to thoroughly update and improve traditional big data computation technologies.

Despite the increasing focus on big data analytics, there are still major limitations and challenges for low-consumption computing technologies. Some key areas of research are training memory-free learning models under the Spark computing framework, managing computing tasks for cross-regional stored big data, leveraging advanced statistical methods to obtain multi-sample computation results, and formalizing the relationship between big data analytics and digital economic activities. Consequently, there is a significant opportunity to explore the latest advancements in Low-Consumption Computing Technologies for Big Data Analytics (LCCT-BigDataAna). 

The topics of interest include, but are not limited to

• Big data adaptive transmission protocols;
• Big data approximate computing algorithms;
• Big data compression and simplification technology;
• Big data dynamic resource allocation algorithms;
• Big data edge computation;
• Big data energy perception scheduling;
• Big data green energy-saving computation;
• Big data message compression and optimization technologies;
• Distributed computing architectures for low-consumption computing;
• Distributed message queue systems for big data analysis;
• Integrated energy-aware systems for the industry;
• Intelligent retransmission mechanisms for big data analysis;
• Low-consumption artificial intelligence applications;
• Low-power processor design;
• Optimization techniques for big data storage and retrieval;
• Power-aware networking technologies;
• Scalable management of distributed data;
• Scalable data mining for big data analytics;
• Simplification and compression techniques for machine learning models;
• Other theories, methods, and algorithms related to big data low-consumption computing.

SUBMISSION GUIDELINES

Authors should prepare papers in accordance with the format requirements of Tsinghua Science and Technology, with reference to the Instruction given at https://www.sciopen.com/journal/1007-0214, and submit the complete manuscript through the online manuscript submission system at https://mc03.manuscriptcentral.com/tst with manuscript type as “Special Issue on LCCT-BigDataAna”.

IMPORTANT DATES

Deadline for submissions: February 28, 2025

GUEST EDITORS

Yulin He (yulinhe@gml.ac.cn), Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),  China

Philippe Fournier-Viger (philfv@szu.edu.cn), Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, China