Edge Computing for Industrial Dust Reduction Research Applications

In complex industrial scenarios, faced with limited computational resources, a large amount of data leads to a high latency problem in dust data processing. Considering the threat of dust pollution and dust explosion to life and health, it is important to prioritize dust data processing. Existing dust reduction methods cannot be dynamically adjusted according to the collected dust data, resulting in low dust reduction efficiency, high energy consumption of equipment, and inability to meet the quality requirements for processing dust. To address the above problems, an optimized multi-objective industrial dust reduction processing method using edge computing is proposed, which is modeled as a constrained multi-objective optimization problem. The task priority is set to ensure that dust tasks can be offloaded first in busy industrial tasks. In order to find the optimal offloading strategy that minimizes task latency and energy consumption, the EHA-SP algorithm, which has both global search capability and parameter adaptation according to task changes, is used to maximize processing efficiency. Experimental results show that the algorithm has significant advantages in reducing latency and minimizing energy consumption. Compared with the original two algorithms, the latency is reduced by 11.8% and 54.57%, and the average energy consumption is reduced by 3.18 percentage points and 0.97 percentage points, respectively, when the number of tasks is 500. The application of edge computing in industrial dust reduction can effectively reduce the time delay and equipment energy consumption, optimize the dust reduction efficiency, reduce the environmental pollution caused by dust, reduce the chances of dust explosion, protect the life safety of industrial producers, and extend the service life of the equipment.