Learning-based synchronous approach from forwarding nodes to reduce the delay for Industrial Internet of Things

Minrui Wu, Yanhui Wu, Xiao Liu, Ming Ma, Anfeng Liu, Ming Zhao

Industrial Internet of Things (IIoT) applications demand high reliability and low latency. In wireless sensor networks (WSNs) that form the backbone of IIoT, nodes often employ duty cycling to conserve energy. However, this creates a "sleep delay" where a sender must wait for a receiver to wake up, significantly increasing end-to-end latency.

Existing solutions like global synchronization are too resource-intensive for large-scale deployments. This paper introduces the Learning-based Synchronous (LS) approach, which utilizes "partial synchronization" to reduce delays by up to 11.6% while improving energy efficiency by up to 17.5%.

The Challenge of Asynchronous Networks

In asynchronous duty-cycled networks, nodes alternate between sleep and active states. A sender node must wait for a potential receiver to transition to an active state before data transmission can commence. This waiting period, known as sleep delay, accumulates at every hop, posing a major risk for time-sensitive industrial processes.

Figure 1: Timeline of the baseline FFSC approach, illustrating the sleep delay between sender and receiver.

The Learning-based Synchronous (LS) Approach

The LS approach moves away from global synchronization, focusing instead on local, sender-relay coordination through three key mechanisms:

  1. Self-Learning for Partial Synchronization: Nodes undergo a learning phase where they observe the wake-up patterns of neighboring nodes. A sender then synchronizes its duty cycle specifically with a subset of candidate relays that are closer to the data sink.
  2. Leveraging Residual Energy: In many WSNs, nodes far from the sink (non-hotspot areas) have excess energy because they handle less traffic. The LS approach tasks these peripheral nodes with the energy-intensive learning and synchronization phases, effectively balancing the network's energy consumption.
  3. Optimized Forwarding Sets: To minimize the number of hops, the algorithm uses a geometric approach to select the most efficient forwarding nodes within a specific range, defined by the intersection of a circle and an arc.
Figure 3: Geometric representation of the optional range for selecting the optimal forwarder set.

Performance and Results

The LS approach was evaluated against existing protocols like FFSC and ORW through extensive simulations involving 700 sensors. Key findings include:

  • Reduced Latency: End-to-end delay decreased by 5.13% to 11.64% compared to the FFSC baseline.
  • Enhanced Energy Efficiency: Energy utilization improved by 14.29% to 17.53% under the same network lifetime constraints.
  • Scalability: The system performs better as node density increases, as the probability of finding a synchronized relay improves.

Conclusion

By localizing synchronization and intelligently utilizing residual energy, the LS approach offers a scalable solution for the latency-energy trade-off in IIoT. While the authors acknowledge the risk of duplicate packets, the significant gains in delay reduction make it a promising candidate for future IoT-based edge networks.

Summary updated

Abstract

The Industrial Internet of Things (IIoTs) is creating a new world which incorporates machine learning, sensor data, and machine-to-machine (M2M) communications. In IIoTs, the length of the transmission delay is one of the pivotal performance because dilatory communication will cause heavy losses to industrial applications. In this paper, a learning-based synchronous (LS) approach from forwarding nodes is proposed to reduce the delay for IIoTs. In an asynchronous Media Access Control protocol, when senders need to send data, they always require to wait for their corresponding receiver to wake up. Thus, the delay here is greater than in the synchronous network. However, the synchronization cost of the whole network is enormous, and it is difficult to maintain. Therefore, LS mechanism uses a partial synchronization approach to reduce synchronization costs while effectively reducing delay. In LS approach, instead of synchronizing the nodes in the entire network, only sender nodes and part of the nodes in their forwarding node set are synchronized by self-learning methods, and accurate synchronization is not required here. Thus, the delay can be effectively reduced under the low cost. Secondly, the nodes near sink maintain the original duty cycle, while the nodes in the regions away from the sink use their remaining energy and perform synchronization operations, so as not to damage the network lifetime. Finally, because the synchronization in this paper is based on different synchronization periods among different nodes, it can improve the network performance by reducing the conflict between simultaneous data transmission. The theoretical analysis results show that compared with the previous approach FFSC, LS approach can reduce the end-to-end delay by 5.13–11.64% and increase the energy efficiency by 14.29–17.53% under the same lifetime with a more balanced energy utilization.
BibTeX
@article{wu2018learning,
  author = {Minrui Wu and Yanhui Wu and Xiao Liu and Ming Ma and Anfeng Liu and Ming Zhao},
  title = {{Learning-based synchronous approach from forwarding nodes to reduce the delay for Industrial Internet of Things}},
  journal = {EURASIP J. Wirel. Commun. Netw.},
  year = {2018},
  doi = {10.1186/s13638-017-1015-z},
}
Figure