Energy-Efficient Air Pollution Monitoring with Optimum Duty-Cycling on a Sensor Hub
01 Feb 2018-
TL;DR: It is demonstrated that temporal correlation of pollutant concentration can be exploited to select optimum sampling period of an energy-intensive sensor to reduce sensing energy consumption without losing much information.
Abstract: Air pollution monitoring systems with energy-intensive sensors cannot afford to sample frequently in order to maximize time between successive recharges. In this paper, we propose an energy-efficient machine learning based sensor duty-cycling method for a sensor hub receiving data from the air-pollution sensors. In particular, we demonstrate that temporal correlation of pollutant concentration can be exploited to select optimum sampling period of an energy-intensive sensor to reduce sensing energy consumption without losing much information. Support Vector Regression is used to predict the missing samples during the period sensor is turned off.
Citations
More filters
TL;DR: IoT data driven unique communication approaches and optimization techniques to reduce the data handling footprint, leading to communication bandwidth, cloud storage, and energy saving, without compromising the service quality are presented.
Abstract: Internet of Things (IoT) has gained tremendous popularity with the recent fast-paced technological advances in embedded programmable electronic and electro-mechanical systems, miniaturization, and their networking ability. IoT is expected to change the way of human activities by extensively networked monitoring, automation, and control. However, widespread application of IoT is associated with numerous challenges on communication and storage requirements, energy sustainability, and security. Also, IoT data traffic as well as the service quality requirements are application-specific. Through a few practical example cases, this article presents IoT data driven unique communication approaches and optimization techniques to reduce the data handling footprint, leading to communication bandwidth, cloud storage, and energy saving, without compromising the service quality. Subsequently, it discusses newer challenges that are needed to be tackled, to make the IoT applications practically viable for their wide-ranging adoption.
8 citations
Cites background from "Energy-Efficient Air Pollution Moni..."
...Also, a field sensor node is normally equipped with a set of sensing elements mounted on a hub, for monitoring multiple environmental parameters [26]....
[...]
DOI•
08 Sep 2021TL;DR: In this paper, a change in the duty-cycle operation of PM sensors impacts aggregated data, in order to evaluate the loss of information, and the calibration adopted is a Multivariate Linear Regression using Relative Humidity as an independent variable.
Abstract: Air pollution is a critical phenomenon of the era we live in. Traditional approaches to monitor this phenomenon involve the use of a sparse network of high-cost, high-precision fixed devices. Thanks to the decreasing cost of low-end sensors, it is now possible to implement much cheaper air pollution monitoring devices with respect to the past. Despite having lower accuracy, these devices are able to correctly monitor quantities such as Particulate Matter (PM). However, devices operating within the Internet of Things (IoT) framework still present several issues, such as power supply constraint, logging of redundant information, aging of sensors. To address these issues, this paper analyses how a change in the duty-cycle operation of PM sensors impacts aggregated data, in order to evaluate the loss of information. This analysis has been applied to both raw and calibrated values. The calibration adopted is a Multivariate Linear Regression using Relative Humidity as an additional independent variable. Results show that, in certain circumstances, even a great reduction of the active time does not significantly increase the information loss. The adoption of a duty-cycle operation mode enables a significant reduction of power consumption, slows the aging of sensors, and reduces logging and transmission of redundant information. Furthermore, since a reduced number of samples are generally required in a single location, mobile continuous sampling strategies can be adopted in order to increase the coverage of PM sensors.
4 citations
Posted Content•
13 Dec 2019TL;DR: This article presents low-cost sensor technologies, and it survey and assess machine learning-based calibration techniques for their calibration, and presents open questions and directions for future research.
Abstract: In recent years, interest in monitoring air quality has been growing. Traditional environmental monitoring stations are very expensive, both to acquire and to maintain, therefore their deployment is generally very sparse. This is a problem when trying to generate air quality maps with a fine spatial resolution. Given the general interest in air quality monitoring, low-cost air quality sensors have become an active area of research and development. Low-cost air quality sensors can be deployed at a finer level of granularity than traditional monitoring stations. Furthermore, they can be portable and mobile. Low-cost air quality sensors, however, present some challenges: they suffer from crosssensitivities between different ambient pollutants; they can be affected by external factors such as traffic, weather changes, and human behavior; and their accuracy degrades over time. Some promising machine learning approaches can help us obtain highly accurate measurements with low-cost air quality sensors. In this article, we present low-cost sensor technologies, and we survey and assess machine learning-based calibration techniques for their calibration. We conclude by presenting open questions and directions for future research.
3 citations
Cites background from "Energy-Efficient Air Pollution Moni..."
...The sensors are mostly very low-power [93]....
[...]
...LSPs are small, low-cost sensing units that are widely used to detect particulate matter [82, 84, 92, 93, 94]....
[...]
TL;DR: In this paper , the authors conduct a survey to explore enhanced AI-based solutions to achieve energy sustainability in IoT applications, which is relevant through the integration of various Machine Learning (ML) and Swarm Intelligence (SI) techniques in the design of existing protocols.
Abstract: The massive number of Internet of Things (IoT) devices connected to the Internet is continuously increasing. The operations of these devices rely on consuming huge amounts of energy. Power limitation is a major issue hindering the operation of IoT applications and services. To improve operational visibility, Low-power devices which constitute IoT networks, drive the need for sustainable sources of energy to carry out their tasks for a prolonged period of time. Moreover, the means to ensure energy sustainability and QoS must consider the stochastic nature of the energy supplies and dynamic IoT environments. Artificial Intelligence (AI) enhanced protocols and algorithms are capable of predicting and forecasting demand as well as providing leverage at different stages of energy use to supply. AI will improve the efficiency of energy infrastructure and decrease waste in distributed energy systems, ensuring their long-term viability. In this paper, we conduct a survey to explore enhanced AI-based solutions to achieve energy sustainability in IoT applications. AI is relevant through the integration of various Machine Learning (ML) and Swarm Intelligence (SI) techniques in the design of existing protocols. ML mechanisms used in the literature include variously supervised and unsupervised learning methods as well as reinforcement learning (RL) solutions. The survey constitutes a complete guideline for readers who wish to get acquainted with recent development and research advances in AI-based energy sustainability in IoT Networks. The survey also explores the different open issues and challenges.
2 citations
2 citations
References
More filters
TL;DR: An exhaustive evaluation of 24 identical units of a commercial low-cost sensor platform against CEN (European Standardization Organization) reference analyzers, evaluating their measurement capability over time and a range of environmental conditions shows that their performance varies spatially and temporally.
607 citations
"Energy-Efficient Air Pollution Moni..." refers background in this paper
...Authors in [13], [15] built a case for using low cost pollution sensors despite the values sensed being indicative only....
[...]
TL;DR: The drivers behind current rises in the use of low-cost sensors for air pollution management in cities are illustrated, while addressing the major challenges for their effective implementation.
591 citations
"Energy-Efficient Air Pollution Moni..." refers background in this paper
...Authors in [13], [15] built a case for using low cost pollution sensors despite the values sensed being indicative only....
[...]
11 Aug 2013
TL;DR: A vehicular-based mobile approach for measuring fine-grained air quality in real-time and two cost effective data farming models -- one that can be deployed on public transportation and the second a personal sensing device are proposed.
Abstract: Traditionally, pollution measurements are performed using expensive equipment at fixed locations or dedicated mobile equipment laboratories. This is a coarse-grained and expensive approach where the pollution measurements are few and far in-between. In this paper, we present a vehicular-based mobile approach for measuring fine-grained air quality in real-time. We propose two cost effective data farming models -- one that can be deployed on public transportation and the second a personal sensing device. We present preliminary prototypes and discuss implementation challenges and early experiments.
332 citations
"Energy-Efficient Air Pollution Moni..." refers background in this paper
...Different solutions proposed earlier for reducing energy cost of continuous context sensing with rechargable wireless sensor networks tried to find heuristics to adapt sampling rate of the energy-intensive sensors or reducing number of sensing reads for energy harvesting nodes [5], [6], [7], [10]....
[...]
TL;DR: This paper designs a data gathering optimization algorithm for dynamic sensing and routing (DoSR), and proposes a distributed sensing rate and routing control (DSR2C) algorithm to jointly optimize data sensing and data transmission, while guaranteeing network fairness.
Abstract: In rechargeable sensor networks (RSNs), energy harvested by sensors should be carefully allocated for data sensing and data transmission to optimize data gathering due to time-varying renewable energy arrival and limited battery capacity. Moreover, the dynamic feature of network topology should be taken into account, since it can affect the data transmission. In this paper, we strive to optimize data gathering in terms of network utility by jointly considering data sensing and data transmission. To this end, we design a data gathering optimization algorithm for dynamic sensing and routing (DoSR), which consists of two parts. In the first part, we design a balanced energy allocation scheme (BEAS) for each sensor to manage its energy use, which is proven to meet four requirements raised by practical scenarios. Then in the second part, we propose a distributed sensing rate and routing control (DSR2C) algorithm to jointly optimize data sensing and data transmission, while guaranteeing network fairness. In DSR2C, each sensor can adaptively adjust its transmit energy consumption during network operation according to the amount of available energy, and select the optimal sensing rate and routing, which can efficiently improve data gathering. Furthermore, since recomputing the optimal data sensing and routing strategies upon change of energy allocation will bring huge communications for information exchange and computation, we propose an improved BEAS to manage the energy allocation in the dynamic environments and a topology control scheme to reduce computational complexity. Extensive simulations are performed to demonstrate the efficiency of the proposed algorithms in comparison with existing algorithms.
237 citations
TL;DR: The root causes of energy overhead in continuous sensing are examined and it is shown that energy-efficient continuous sensing can be achieved through proper system design.
Abstract: Today's mobile phones come with a rich set of built-in sensors such as accelerometers, ambient light sensors, compasses, and pressure sensors, which can measure various phenomena on and around the phone. Gathering user context such as user activity, geographic location, and location type requires continuous sampling of sensor data. However, such sampling shortens a phone's battery life because of the associated energy overhead. This article examines the root causes of this energy overhead and shows that energy-efficient continuous sensing can be achieved through proper system design.
179 citations
"Energy-Efficient Air Pollution Moni..." refers background in this paper
...For Smartphone based mobile participatory-sensing, continuous sensing tasks were offloaded to a low-power sensing coprocessor called sensor hub so that energy hungry system-onchip (SoC) may sleep whenever possible [4]....
[...]