In order to reduce unnecessary data transmissions from Internet of Things (IoT) sensors, this article proposes a multivariate-time-series-prediction-based adaptive data transmission period control (PBATPC) algorithm for IoT networks. Based on the spatio-temporal correlation between multivariate time-series data, we developed a novel multivariate time-series data encoding scheme utilizing the proposed time-series distance measure $\textit {ADMWD}$ . Composed of two significant factors for a multivariate time-series prediction, i.e., the absolute deviation from the mean (ADM) and the weighted differential (WD) distance, the $\textit {ADMWD}$ considers both the time distance from a prediction point and a negative correlation between the time-series data concurrently. Utilizing the convolutional neural network (CNN) model, a subset of IoT sensor readings can be predicted from encoded multivariate time-series measurements, and we compared the predicted sensor values with actual readings to obtain the adaptive data transmission period. Extensive performance evaluations show a substantial performance gain of the proposed algorithm in terms of the average power reduction ratio (approximately 12%) and average data reconstruction error (approximately 8.32% MAPE). Finally, this article also provides a practical implementation of the proposed PBATPC algorithm via the HTTP protocol under the IEEE 802.11-based WLAN network.

Mobile-edge computing (MEC) is expected to play an important role in the next-generation of Internet-of-Things (IoT) services with artificial intelligence (AI) by providing the sustainable computation capability of resource-constrained IoT devices. Since the finite battery lifetime has been a longstanding challenge of the MEC system for IoT services, the wireless power transfer (WPT) technology has been recently developed for the MEC system in order to support the perpetual operation of IoT devices. In this article, we introduce two resource allocation problems for OFDMA-based WPT-MEC systems: 1) a max–min energy fairness (MMEF) problem and 2) a power sum maximization (PSM) problem. These problems ensure high-performance computations for AI-based applications, where the network reliability and the tremendous power consumption may be required. Moreover, we incorporate a logarithmic nonlinear energy harvesting (EH) model into our formulated problems, which lead to nonconvex mixed-integer nonlinear programming (MINLP) problems. In order to resolve these NP-hard problems, we convert the proposed problems into their equivalent convex forms by applying the continuous relaxation method. The near-optimal solutions are thereby obtained in closed-form expressions by leveraging the Lagrangian duality method for each relaxed problem. Numerical results are presented to validate the merits of the proposed algorithms of MMEF&PSM over the alternative benchmark algorithm and provide significant insights on the effects of the key system parameters, including the number of IoT devices and power transmission subcarriers.

With the recent explosive growth of the Internet of Things (IoT), edge computing is emerging as a modern computing paradigm that coexists with the cloud to process massive amounts of data particularly distributed at the edge network. Meanwhile, edge computing directly permits the use of artificial intelligent (AI) models at the edge. Currently in numerous IoT applications, a tremendous amount of data is being measured and transmitted from IoT sensors to monitor surrounding information in real-time. Considering that continuous transmission of sensed data substantially requires high energy consumption of IoT sensors, this paper proposes a PPO-based autonomous transmission period control (PPO-ATPC) system in IoT edge computing that can automatically and adaptively control the transmission period of each IoT sensor. Here, the design of state, action, and reward is shaped in an unprecedented way and furthermore, a proximal policy optimization (PPO), which is one of the most effective model-free deep reinforcement learning (DRL) algorithms, is fully leveraged to achieve an optimal or nearly-optimal policy that can significantly shorten the data volume while maintaining high data quality. The merits of the proposed PPO-ATPC are extensively validated through quantitative comparison with other alternative approaches using three different sensor data collected from real-time environmental monitoring, and in-depth insights into the effectiveness of PPO-ATPC are further provided from diverse perspectives. The performance results show that total data volume for each dataset could be reduced by 73.849%, 89.931%, and 81.310%, with the average RMSE of 0.322, 13.896, and 0.048.

This article proposes a novel deep learning-based robust Internet of Things (IoT) sensor data transmission period control (DL-RDTPC) framework in an IoT edge computing system. In general, as the data transmission period of IoT sensors increases, the energy consumption of IoT sensors is reduced, and contrarily, the amount of un-transmitted data (i.e., missing values) becomes continuously accumulated. Therefore, the IoT server is in charge of accurately imputing these missing data for reliable data analysis. By addressing this issue, we newly design the imputation accuracy prediction (IAP) module, which captures the complicated relationships between the imputation accuracy and the data transmission period, in order to estimate the imputation accuracy, precisely. For constructing the IAP, three submodules, which include a stacked bidirectional long short-term memory (Bi-LSTM) model, a multihead convolutional neural network (CNN), and a neural network-based period information encoding network (PIEN) are leveraged. To balance the tradeoff between the imputation accuracy and energy consumption regarding the data transmission period, the multiobjective optimization problem is formulated for minimizing the maximum value of both: 1) the energy consumption of IoT sensors obtained from the analytical model and 2) the imputation accuracy predicted from IAP module. The optimal solution is consequently obtained by utilizing the bisection search algorithm. Extensive performance evaluations validate the effectiveness of the proposed RDTPC algorithm in terms of both the average energy consumption (maximum 68% reduction) and missing data imputation accuracy (maximum 64% RMSE reduction) over other benchmarks. Finally, this article provides a practical implementation of the proposed RDTPC framework via the HTTP protocol under the IEEE 802.11-based WLAN network, as well as interworking with the commercial cloud server.