Sleep–Wake Sensor Scheduling for Minimizing AoI-Penalty in Industrial Internet of Things

Wang, Jia; Cao, Xianghui; Yin, Bo; Cheng, Yu

doi:10.1109/jiot.2021.3112211

Cited by 13 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A genetic algorithm was proposed to solve the decision-making process for flight path planning of UAVs in [21]. The author in [22] analyzed scheduling in a sleep-wake sensor network and proposed a max-weight-based scheduling policy to achieve the asymptotically optimal AoI lower limit while reducing energy consumption. As a promising method, deep reinforcement learning has been applied to network resource management many times.…”

Section: Related Workmentioning

confidence: 99%

AoI-Aware Resource Scheduling for Industrial IoT with Deep Reinforcement Learning

Li,

Tang,

Chen

et al. 2024

Electronics

View full text Add to dashboard Cite

Effective resource scheduling methods in certain scenarios of Industrial Internet of Things are pivotal. In time-sensitive scenarios, Age of Information is a critical indicator for measuring the freshness of data. This paper considers a densely deployed time-sensitive Industrial Internet of Things scenario. The industrial wireless device transmits data packets to the base station with limited channel resources under the constraints of Age of Information. It is assumed that each device has the capacity to store the packets it generates. The device will discard the data to alleviate the data queue backlog when the Age of Information of the data packet exceeds the threshold. We developed a new system utility equation to represent the scheduling problem and the problem is expressed as a trade-off between minimizing the average Age of Information and maximizing network throughput. Inspired by the success of reinforcement learning in decision-processing problems, we attempt to obtain an optimal scheduling strategy via deep reinforcement learning. In addition, a reward function is constructed to enable the agent to achieve improved convergence results. Compared with the baseline, our proposed algorithm can achieve better system utility and lower Age of Information violation rate.

show abstract

Section: Related Workmentioning

confidence: 99%

AoI-Aware Resource Scheduling for Industrial IoT with Deep Reinforcement Learning

Li,

Tang,

Chen

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Recently, information timeliness has become a novel and very critical metric for the newly emerged status update applications, including hazard monitoring, autonomous driving, and AR services, because outdated information may result in serious impacts, such as production accidents and economic loss or even casualties. In order to enhance the information timeliness for IIoT, age of information (AoI), which is defined as the time interval from the time a data packet is generated to the current time, has been presented and widely studied in various systems network scenarios [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], [14], [15].…”

Section: Introductionmentioning

confidence: 99%

AoI-Minimal Power Adjustment in RF-EH-Powered Industrial IoT Networks: A Soft Actor-Critic-Based Method

Ge,

Xiong,

Wang

et al. 2024

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

This paper investigates the radio-frequency-energy-harvesting-powered (RF-EH-powered) wireless Industrial Internet of Things (IIoT) networks, where multiple sensor nodes (SNs) are first powered by a wireless power station (WPS), and then collect status updates from the industrial environment and finally transmit the collected data to the monitor with their harvested energy. To enhance the timeliness of data, age of information (AoI) is used as a metric to optimize the system. Particularly, an expected sum AoI (ESA) minimization problem is formulated by optimizing the power adjustment policy for the SNs under multiple practical constraints, including the EH, the minimal signal-to-noise-plus-interference ratio (SINR) and the battery capacity constraints. To solve the non-convex problem with no explicit AoI expression, we transform it into a Markov decision problem (MDP) with continuous state space and action space. Then, inspired by the Soft Actor-Critic (SAC) framework in deep reinforcement learning, a SAC-based age-aware power adjustment (SAPA) method is proposed by modeling the power adjustment as a stochastic strategy. Furthermore, to reduce the communication overhead of SAPA, a multi-agent version of SAPA, i.e., MSAPA, is proposed, with which each SN is able to adjust its transmit power based on its local observations. The communication overhead of SAPA and MSAPA is also analyzed theoretically. Simulation results show that the proposed SAPA and MSAPA converge well with different numbers of SNs. It is also shown that the ESA achieved by the proposed SAPA and MSAPA is lower than that achieved by the baseline methods.

show abstract

Advanced Wireless Technologies for Industrial Automation

Lyu

Guan²,

Cheng³

et al. 2023

Wireless Networks

View full text Add to dashboard Cite

Sleep–Wake Sensor Scheduling for Minimizing AoI-Penalty in Industrial Internet of Things

Cited by 13 publications

References 34 publications

AoI-Aware Resource Scheduling for Industrial IoT with Deep Reinforcement Learning

AoI-Aware Resource Scheduling for Industrial IoT with Deep Reinforcement Learning

AoI-Minimal Power Adjustment in RF-EH-Powered Industrial IoT Networks: A Soft Actor-Critic-Based Method

Advanced Wireless Technologies for Industrial Automation

Contact Info

Product

Resources

About