DEEP LEARNING–BASED ENERGY OPTIMIZATION IN INDUSTRIAL IOT: A COMPARATIVE STUDY

The IIoT has emerged as a significant paradigm in the area of intelligent and sustainable
manufacturing. In the different applications of IIoT, one of the most challenging tasks is the
optimization of energy consumption. The main reason for this is the continuous increase in the
price of energy; in addition to environmental issues, the industrial process has become more
complicated. The traditional approaches to energy consumption are either rule-based or statistical
models, which are not flexible and do not work well in the dynamic industrial environment. This
paper provides a modified, plagiarism-proof, and expanded comparative analysis of deep learning
methods for energy optimization in the Industrial Internet of Things. The analysis is carried out
for the specific deep learning methods of Convolutional Neural Networks, Long Short-Term
Memory Networks, and Deep Reinforcement Learning. The observations of the experimental
analysis display the effective increase in energy efficiency and intelligence of the system using the
proposed deep learning methods as compared to existing methods of energy optimization in the
Industrial Internet of Things. Furthermore, this paper provides directions for future research tasks
for next-gen energy-efficient industrial systems.