Nowadays, there is a significant need for maintenance free modern Internet of things (IoT) devices which can monitor an environment. IoT devices such as these are mobile embedded devices which provide data to the internet via Low Power Wide Area Network (LPWAN). LPWAN is a promising communications technology which allows machine to machine (M2M) communication and is suitable for small mobile embedded devices. The paper presents a novel data-driven self-learning (DDSL) controller algorithm which is dedicated to controlling small mobile maintenance-free embedded IoT devices. The DDSL algorithm is based on a modified Q-learning algorithm which allows energy efficient data-driven behavior of mobile embedded IoT devices. The aim of the DDSL algorithm is to dynamically set operation duty cycles according to the estimation of future collected data values, leading to effective operation of power-aware systems. The presented novel solution was tested on a historical data set and compared with a fixed duty cycle reference algorithm. The root mean square error (RMSE) and measurements parameters considered for the DDSL algorithm were compared to a reference algorithm and two independent criteria (the performance score parameter and normalized geometric distance) were used for overall evaluation and comparison. The experiments showed that the novel DDSL method reaches significantly lower RMSE while the number of transmitted data count is less than or equal to the fixed duty cycle algorithm. The overall criteria performance score is 40% higher than the reference algorithm base on static confirmation settings.

This article focuses on applying a deep learning approach to predict daily total solar energy for the next day by a neural network. Predicting future solar irradiance is an important topic in the renewable energy generation field to improve the performance and stability of the system. The forecast is used as a support parameter to control the operation duty-cycle, data collection or communication activities at energy-independent energy harvesting embedded devices. The prediction is based on previous hourly-measured atmospheric pressure values. For prediction, a back-propagation algorithm in combination with deep learning methods is used for multilayer network training. The ability of the proposed system to estimate the daily solar energy is compared to the support vector regression model and to the evolutionary-fuzzy prediction scheme presented in previous research studies. It is concluded that the presented neural network approach gave satisfying predictions in early spring, autumn, and winter. In a particular setting, the proposed solution provides better results than a model using the support vector regression method (e.g., the MAPE value of the proposed algorithm is 0.032 less than the MAPE value of support vector regression method). The time and computational complexity for neural network training is considerable, and therefore it was assumed to train the network on an external computer or a cloud, where only the network parameters have been obtained and transferred to the embedded devices.

Energy harvesting has an essential role in the development of reliable devices for environmental wireless sensor networks (EWSN) in the Internet of Things (IoT), without considering the need to replace discharged batteries. Thermoelectric energy is a renewable energy source that can be exploited in order to efficiently charge a battery. The paper presents a simulation of an environment monitoring device powered by a thermoelectric generator (TEG) that harvests energy from the temperature difference between air and soil. The simulation represents a mathematical description of an EWSN, which consists of a sensor model powered by a DC/DC boost converter via a TEG and a load, which simulates data transmission, a control algorithm and data collection. The results section provides a detailed description of the harvested energy parameters and properties and their possibilities for use. The harvested energy allows supplying the load with an average power of 129.04 μW and maximum power of 752.27 μW. The first part of the results section examines the process of temperature differences and the daily amount of harvested energy. The second part of the results section provides a comprehensive analysis of various settings for the EWSN device’s operational period and sleep consumption. The study investigates the device’s number of operational cycles, quantity of energy used, discharge time, failures and overheads.

Operational cycle control is an attractive field of research which can lead to improvements in the services offered by power-aware monitoring embedded IoT devices. Machine learning (ML) is an infrastructure for operational cycle control and provides many approaches which provide more energyefficient operation. One subfield of ML is Q-learning (QL), which forms the basis of the data-driven self-learning (DDSL) controller. The DDSL algorithm dynamically sets operational duty cycles according to estimates of future collected data values, leading to effective operation of power-aware systems. However, QL performs very poorly in stochastic environments as a result of overestimation of action values. The double estimator implemented in QL therefore applies Double QL (DQL) and forms the basis for a novel Double DDSL (DDDSL). The results of testing a DDDSL controller on historical data showed 42-50 % greater performance than a controller with a fixed duty-cycle, and 2-12 % more performance than a DDSL controller.

No abstract