Edge computing is proposed to solve the problem of centralized cloud computing caused by a large number of IoT (Internet of Things) devices. The IoT protocols need to be modified according to the edge computing paradigm, where the edge computing devices for analyzing IoT data are distributed to the edge networks. The MQTT (Message Queuing Telemetry Transport) protocol, as a data distribution protocol widely adopted in many international IoT standards, is suitable for cloud computing because it uses a centralized broker to effectively collect and transmit data. However, the standard MQTT may suffer from serious traffic congestion problem on the broker, causing long transfer delays if there are massive IoT devices connected to the broker. In addition, the big data exchange between the IoT devices and the broker decreases network capability of the edge networks. The authors in this paper propose a novel MQTT with a multicast mechanism to minimize data transfer delay and network usage for the massive IoT communications. The proposed MQTT reduces data transfer delays by establishing bidirectional SDN (Software Defined Networking) multicast trees between the publishers and the subscribers by means of bypassing the centralized broker. As a result, it can reduce transmission delay by 65% and network usage by 58% compared with the standard MQTT.

A fire detection system requires accurate and fast mechanisms to make the right decision in a fire situation. Since most commercial fire detection systems use a simple sensor, their fire recognition accuracy is deficient because of the limitations of the detection capability of the sensor. Existing proposals, which use rule-based algorithms or image-based machine learning can hardly adapt to the changes in the environment because of their static features. Since the legacy fire detection systems and network services do not guarantee data transfer latency, the required need for promptness is unmet. In this paper, we propose a new fire detection system with a multifunctional artificial intelligence framework and a data transfer delay minimization mechanism for the safety of smart cities. The framework includes a set of multiple machine learning algorithms and an adaptive fuzzy algorithm. In addition, Direct-MQTT based on SDN is introduced to solve the traffic concentration problems of the traditional MQTT. We verify the performance of the proposed system in terms of accuracy and delay time and found a fire detection accuracy of over 95%. The end-to-end delay, which comprises the transfer and decision delays, is reduced by an average of 72%.

Disaster management systems require accurate disaster monitoring and prediction services to reduce damages caused by natural disasters. Digital twins of natural environments can provide the services for the systems with physics-based and data-driven disaster models. However, the digital twins might generate erroneous disaster prediction due to the impracticability of defining high-fidelity physics-based models for complex natural disaster behavior and the dependency of data-driven models on the training dataset. This causes disaster management systems to inappropriately use disaster response resources, including medical personnel, rescue equipment and relief supplies, to ensure that it may increase the damages from the natural disasters. This study proposes a digital twin architecture to provide accurate disaster prediction services with a similarity-based hybrid modeling scheme. The hybrid modeling scheme creates a hybrid disaster model that compensates for the errors of physics-based prediction results with a data-driven error correction model to enhance the prediction accuracy. The similarity-based hybrid modeling scheme reduces errors from the data dependency of the hybrid model by constructing a training dataset using similarity assessments between the target disaster and the historical disasters. Evaluations in wildfire scenarios show that the digital twin decreases prediction errors by approximately 50% compared with those of the existing schemes.

Time-sensitive networking (TSN) technologies have garnered attention for supporting time-sensitive communication services, with recent interest extending to the wireless domain. However, adapting TSN to wireless areas faces challenges due to the competitive channel utilization in IEEE 802.11, necessitating exclusive channels for low-latency services. Additionally, traditional TSN scheduling algorithms may cause significant transmission delays due to dynamic wireless characteristics, which must be addressed. This paper proposes a wireless TSN model of IEEE 802.11 networks for the exclusive channel access and a novel time-sensitive traffic scheduler, named the wireless intelligent scheduler (WISE), based on deep reinforcement learning. We designed a deep reinforcement learning (DRL) framework to learn the repetitive transmission patterns of time-sensitive traffic and address potential latency issues from changing wireless conditions. Within this framework, we identified the most suitable DRL model, presenting the WISE algorithm with the best performance. Experimental results indicate that the proposed mechanisms meet up to 99.9% under the various wireless communication scenarios. In addition, they show that the processing delay is successfully limited within the specific time requirements and the scalability of TSN streams is guaranteed by the proposed mechanisms.

With the difficulty of collecting desirable training data due to the heterogeneities of IoT sensors in various buildings and the scarcity of fire events, it is time consuming and expensive to apply data-driven deep learning approaches to fire detection systems in specific building environments. Simulation-based learning has been actively researched to mitigate data scarcity problems by reproducing potential fire events. Since simulation-based learning mainly depends on synthetic training data, trained deep learning models may generate erroneous predictions in real-world scenarios that are unlike any of the training samples. In this paper, we propose a trustworthy building fire detection framework based on a multioutput encoder-decoder network, named MEDNet, which is designed for the practical usage of simulation-based learning in building fire detection. The fundamental steps of our approach are (1) modeling and simulating fire events to create realistic synthetic data that reflect data from actual buildings, (2) predicting a fire event and dissimilarities between real input data and synthetic training data based on the trained MEDNet model, and (3) operating a switching mechanism to use a knowledge-based method that does not depend on synthetic training data when dissimilarities exist. Finally, we perform simulation experiments based on a real building compartment where the proposed framework is compared with conventional time-series classification networks on various evaluation datasets. The proposed framework is trustworthy in practical usage because MEDNet with a switching mechanism achieves a 36.65% higher F1-score than conventional time-series classification networks and generates false-positive predictions lower than 0.02% even in unpredictable scenarios.

Hardware bottlenecks can throttle smart device (SD) performance when executing computation-intensive and delay-sensitive applications. Hence, task offloading can be used to transfer computation-intensive tasks to an external server or processor in Mobile Edge Computing. However, in this approach, the offloaded task can be useless when a process is significantly delayed or a deadline has expired. Due to the uncertain task processing via offloading, it is challenging for each SD to determine its offloading decision (whether to local or remote and drop). This study proposes a deep-reinforcement-learning-based offloading scheduler (DRL-OS) that considers the energy balance in selecting the method for performing a task, such as local computing, offloading, or dropping. The proposed DRL-OS is based on the double dueling deep Q-network (D3QN) and selects an appropriate action by learning the task size, deadline, queue, and residual battery charge. The average battery level, drop rate, and average latency of the DRL-OS were measured in simulations to analyze the scheduler performance. The DRL-OS exhibits a lower average battery level (up to 54%) and lower drop rate (up to 42.5%) than existing schemes. The scheduler also achieves a lower average latency of 0.01 to >0.25 s, despite subtle case-wise differences in the average latency.