基于边缘计算的数据无损压缩方法

Lossless Data Compression Method Based on Edge Computing

工业物联网(Industrial Internet of Things,IIoT)可以将各种工业设备、监测仪表以及传感器进行相互连接,设备的运行状态可通过监测仪表与传感器进行全面感知,并根据感知数据对设备状态进行分析与预测。然而要对海量的感知数据进行分析处理需要大量的存储空间与计算能力,将其传送到云平台势必将占用大量的带宽并产生较大的时延,很难满足对设备状态实时分析与诊断的需求。因此,针对工业设备状态感知的数据,提出了基于最优差分和线性拟合降熵变换的无损压缩方法,在数据采集的边缘侧对感知数据进行无损压缩,从而大大提高传输效率,使得感知数据能快速传送到云平台进行分析与处理。该方法根据数据差值序列方差大小和采集频率高低从最优差分和曲线拟合差值中选取有效的降熵变换进行压缩,并采用LZO(Lempel-Ziv-Oberhumer)压缩算法进行二次压缩。在两类不同的数据集上对所提方法进行了测试,实验结果表明,该方法的压缩率最低与最高分别可达77%和93%,同时验证了其无损重构的特性。

Through the Industrial Internet of Things(IIoT),various industrial equipments,monitoring instruments and sensors can be connected to each other.The operating status of equipment can be fully sensed through monitoring instruments and sensors,and the equipment status can be analyzed and predicted based on sensing data.However,the analysis and processing of massive amounts of sensing data requires a lot of storage space and computing power.Sending it to the cloud platform will inevitably take up a lot of bandwidth and cause a large delay.It is difficult to meet the requirements for real-time analysis and diagnosis of device status.Therefore,for the state-aware data of industrial equipment,a lossless compression method based on optimal differential and linear fitting entropy reduction transform is proposed,and the perceptual data is compressed losslessly at the edge of data collection,so that the transmission efficiency is greatly improved and the perceptual data can be quickly transmitted to the cloud platform for analysis and processing.This method selects an effective entropy reduction transform from the optimal difference and curve fitting difference according to the variance of data difference sequence and the acquisition frequency,and uses Lempel-Ziv-Oberhumer(LZO)compression algorithm for secondary compression.The new method is tested on two different data sets.Experimental results show that the lowest and highest compression rate of this method can reach 77%and 93%,respectively.At the same time,the characteristics of its lossless reconstruction are verified.