Edge-Based Missing Data Imputation in Large-Scale Environments

Abstract

Smart cities leverage large amounts of data acquired in the urban environment in the context of decision support tools. These tools enable monitoring the environment to improve the quality of services offered to citizens. The increasing diffusion of personal Internet of things devices capable of sensing the physical environment allows for low-cost solutions to acquire a large amount of information within the urban environment. On the one hand, the use of mobile and intermittent sensors implies new scenarios of large-scale data analysis; on the other hand, it involves different challenges such as intermittent sensors and integrity of acquired data. To this effect, edge computing emerges as a methodology to distribute computation among different IoT devices to analyze data locally. We present here a new methodology for imputing environmental information during the acquisition step, due to missing or otherwise out of order sensors, by distributing the computation among a variety of fixed and mobile devices. Numerous experiments have been carried out on real data to confirm the validity of the proposed method.

Missing Data Imputation in Internet of Things Gateways

“…This method performs better than other methods in the literature that deal with databases with large missing data gaps. The authors in [12] presented a multi-agent system (MAS) technique to impute missing values in an edge environment. More specifically, they consider IoT devices such as ad hoc sensors and mobile devices.…”

“…Furthermore, gateways are on the edge of IoT systems, close to the end device. Hence, imputing data on the edge is essential to real-time applications that need end device actuation [12,13].…”

Embedded Data Imputation for Environmental Intelligent Sensing: A Case Study

“…Guastella et al propose in [ 28 ] an approach based on multi-agent system (MAS), which allows distributing the computation among the local agents grouped in regions for imputing missing environmental data during the data collection process for large-scale systems. The imputation is based on the two-dimensional inverse distance weighting (IDW) interpolation for irregularly spaced data.…”

“…While all the works discussed earlier present interesting and innovative techniques or frameworks to manage the problem of missing data, some important differences arise with respect to our proposal. First, in many works (see, e.g., [ 25 , 26 , 27 , 28 , 30 , 31 , 32 , 33 , 35 , 36 ]), despite the data coming from the IoT, the analysed imputation algorithms actually run on standard computer architectures (e.g., PCs, laptops, etc.). Moreover, the importance of tackling the missing data problem as close as possible to the devices is evident (e.g., at the Edge of the network [ 37 ]); thus, our assessments are carried out straight on the board of the devices.…”

Decentralized optimal management of a large-scale EV fleet: Optimality and computational complexity comparison between an adaptive MAS and MILP

“…Additionally, as the system performs online optimization (mainly reactive), it does not need to go through any training phase and thus no statistical approximations or discretization of the action space of each agent is necessary to tackle the curse of dimensionality or to increase the scalability of the designed complex system for real-time operations. Furthermore, in [30], grid challenges involving two actors i.e., prosumers and DSO are considered. However, in this paper, the constraints and the objectives of prosumers, DSO, and BRP are considered altogether.…”