TY - JOUR
T1 - Machine Learning methods in tasks load balancing between IoT devices and the Cloud
AU - Tishin, Mikhail
AU - Mavromoustakis, Constandinos X.
AU - Batalla, Jordi Mongay
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2024
Y1 - 2024
N2 - Nowadays, with the ongoing, wide scale digitization and development of AI in pursuit of automation, the IoT industry becomes one of the very important parts in this process. The development of IoT devices computational capabilities, as well as the massive amounts of data which is being generated by them, create a need for methods to load balance workloads efficiently. Since the IoT devices are receiving more processing power, it becomes important to leverage that power for executing curtain tasks inside an IoT ecosystem itself, rather than delegating to the Cloud. One of the main goals of the research is to understand, to what extent an IoT ecosystem can be self reliant in managing various tasks. In particular, what mechanism would allow to load balance tasks among IoT devices and Cloud servers. The paper focuses on exploration of the existing solutions and offers an alternative concept of such mechanism, which includes application of Machine Learning methods to load balance the workloads. It proposes tasks distribution based on runtime complexity estimated by Machine Learning and historical data from the previous tasks.
AB - Nowadays, with the ongoing, wide scale digitization and development of AI in pursuit of automation, the IoT industry becomes one of the very important parts in this process. The development of IoT devices computational capabilities, as well as the massive amounts of data which is being generated by them, create a need for methods to load balance workloads efficiently. Since the IoT devices are receiving more processing power, it becomes important to leverage that power for executing curtain tasks inside an IoT ecosystem itself, rather than delegating to the Cloud. One of the main goals of the research is to understand, to what extent an IoT ecosystem can be self reliant in managing various tasks. In particular, what mechanism would allow to load balance tasks among IoT devices and Cloud servers. The paper focuses on exploration of the existing solutions and offers an alternative concept of such mechanism, which includes application of Machine Learning methods to load balance the workloads. It proposes tasks distribution based on runtime complexity estimated by Machine Learning and historical data from the previous tasks.
KW - Cloud computing
KW - Internet of Things (IoT)
KW - task load balancing
UR - http://www.scopus.com/inward/record.url?scp=85204204305&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2024.3460056
DO - 10.1109/ACCESS.2024.3460056
M3 - Article
AN - SCOPUS:85204204305
SN - 2169-3536
JO - IEEE Access
JF - IEEE Access
ER -