N OWADAYS, billions of devices are connected to the In-ternet, enabling Internet of Things (IoT) systems widely deployed, such as smart city, smart healthcare and intelligent plant, to capture a great quantity of sensing data. Consequently, the data transmission, processing and analysis in IoT applications bring a great pressure to the central server. Fortunately, distributed intelligence becomes one of the potential solutions. Distributed intelligence can greatly relieve server pressures via plenty of terminal devices, and these devices collaboratively perceive and handle the mass data to improve the reliability, s-calability and security of industrial IoT systems. As future IoT system will embrace more wireless sensors and devices, the high-performance computing, high-bandwidth and low-latency communication are excessively required, many new research opportunities and challenges for distributed intelligence over Internet of things have arisen. To promote the development of distributed intelligence technology, this special section (SS) focuses on various technologies and platforms regarding industrial IoT systems. This special section received nearly 50 submitted manuscripts, out of which 10 of them have been accepted after a rigorous peer review. Each manuscript is reviewed by multiple rounds of review with at least three or four reviewers, the problems to be solved and the innovation of each manuscript are mainly concerned. Then the accepted papers are summarized as follows in details. Considering the joint optimization of the offloading decision and resource allocation under limited resource constraints in collaborative edge computing networks with multiple IIoT devices and MEC servers, an improved differential evolution algorithm [7] is proposed to minimize the weighted sum of cost of energy consumption and time delay, which can effectively reduce the system delay and energy consumption. In order to improve the performance of task scheduling in cloud computing, Attiya et al. [1] propose a novel hybrid swarm intelligence method MRFOSSA, which uses a modified Manta-Ray Foraging Optimizer (MRFO) and the Salp Swarm Algorithm (SSA). MRFOSSA is superior to other methods in terms of makespan time and cloud throughput. The research goal of the paper [5] is to design an intelligent computing offloading strategy for industrial applications in order to optimize costs and mitigate energy losses. Then the paper proposes to combine a fog controller and AI-based learning techniques so that the fog controller can intelligently assign tasks to the most appropriate fog devices and find the appropriate path to the target. Considering the resource utilization efficiency under dynamic overload requests and network states in IIoT, Chen et al. [2] propose DRL-based intelligent SFC orchestration scheme and jointly optimize the VNF deployment and SFC embedment by the improved DDQN algorithm, which can improve the performance of resource utilization rate, execution cost and delay compared with other representative schemes. To solve the problem of resource allocation and energy cost in Internet of Vehicles, Kong et al. [8] design a joint computing and caching framework and formulate the problem as a reinforcement learning problem to minimize the energy cost. On this basis, the optimization algorithm based on DDPG is proposed, which can effectively decrease energy costs. To reduce the query numbers of the object model when constructing adversarial examples, Zhang et al. [10] propose generating adversarial examples with shadow model (GASM), i.e., transfering the query operations to the designed shadow model, which can achieve high attack success rates. Chen et al. [3] revise a Decentralized-Wireless-Federated-Learning algorithm (DWFL) which utilizes the superposition property of the analog scheme. It can solve the problem of single failure, limited bandwidth resource and privacy protection in wireless federated learning algorithm, which can be applied widely in wireless IoT networks. To reduce the resource consumption in CNN-based applications, Jia et al. [6] propose the CNN-based Resource Optimization APProach which utilizes model compression and computation sharing to optimize inner-model and inter-model respectively, and the comparison results show the superior performance in scalability and the decrease of resource cost. In mobile crowdsensing activities, Gao et al. [4] propose a differential Location Privacy-preserving Mechanism based on Trajectory obfuscation (LPMT) to protect the location privacy of mobile users, which includes three operations: stay points extraction, stay points obfuscation and stay points sampling. In order to mimic the task-free bottom-up visual attention process by predicting salient regions on natural images, Umer et al. [9] propose a Pseudo Knowledge Distillation (PKD) model based on knowledge distillation and pseudo labelling technique, which is computationally efficient and suitable for real-time on-device saliency prediction.

中文翻译：

---

客座社论：物联网分布式智能特别章节


如今，数十亿设备连接到互联网，使得物联网（IoT）系统广泛部署，例如智慧城市、智慧医疗和智能工厂，以捕获大量传感数据。因此，物联网应用中的数据传输、处理和分析给中央服务器带来了巨大的压力。幸运的是，分布式智能成为潜在的解决方案之一。分布式智能可以通过大量的终端设备极大地缓解服务器压力，这些设备协同感知和处理海量数据，提高工业物联网系统的可靠性、可扩展性和安全性。随着未来的物联网系统将采用更多的无线传感器和设备，对高性能计算、高带宽和低延迟通信的需求越来越大，物联网分布式智能出现了许多新的研究机会和挑战。为了促进分布式智能技术的发展，本专题（SS）重点关注工业物联网系统的各种技术和平台。本专题栏目共收到近50篇投稿稿件，其中10篇经过严格的同行评审后已被接收。每篇稿件均经过多轮评审，至少有三到四位审稿人，主要关注每篇稿件需要解决的问题和创新点。现将录用论文详细总结如下。 考虑到在具有多个IIoT设备和MEC服务器的协作边缘计算网络中有限资源约束下的卸载决策和资源分配的联合优化，提出了一种改进的差分进化算法[7]，以最小化能耗和时间成本的加权和延迟，可以有效降低系统延迟和能耗。为了提高云计算中任务调度的性能，Attiya等人。 [1]提出了一种新颖的混合群体智能方法 MRFOSSA，该方法使用改进的蝠鲼觅食优化器（MRFO）和 Salp 群体算法（SSA）。 MRFOSA 在完工时间和云吞吐量方面优于其他方法。本文[5]的研究目标是为工业应用设计一种智能计算卸载策略，以优化成本并减少能源损失。然后，本文提出将雾控制器与基于人工智能的学习技术相结合，使雾控制器能够智能地将任务分配给最合适的雾设备，并找到到达目标的合适路径。考虑到工业物联网中动态过载请求和网络状态下的资源利用效率，Chen 等人。文献[2]提出基于DRL的智能SFC编排方案，通过改进的DDQN算法联合优化VNF部署和SFC嵌入，与其他代表性方案相比，可以提高资源利用率、执行成本和延迟等性能。为了解决车联网中的资源配置和能源成本问题，Kong等人。 [8]设计了一个联合计算和缓存框架，并将问题表述为强化学习问题，以最小化能源成本。 在此基础上，提出了基于DDPG的优化算法，可以有效降低能源成本。为了减少构建对抗性示例时对象模型的查询次数，Zhang 等人。 [10]提出用影子模型（GASM）生成对抗样本，即将查询操作转移到设计的影子模型上，这样可以获得很高的攻击成功率。陈等人。 [3] 修改了一种利用模拟方案的叠加特性的去中心化无线联合学习算法（DWFL）。它可以解决无线联邦学习算法的单一故障、带宽资源有限和隐私保护等问题，可在无线物联网网络中得到广泛应用。为了减少基于 CNN 的应用程序的资源消耗，Jia 等人。 [6]提出了基于CNN的资源优化方法，利用模型压缩和计算共享分别优化模型内和模型间，比较结果显示在可扩展性和资源成本降低方面具有优越的性能。在移动人群感知活动中，Gao 等人。 [4]提出了一种基于轨迹混淆（LPMT）的差分位置隐私保护机制来保护移动用户的位置隐私，该机制包括三个操作：停留点提取、停留点混淆和停留点采样。为了通过预测自然图像上的显着区域来模拟无任务的自下而上的视觉注意过程，Umer 等人。 [9]提出了一种基于知识蒸馏和伪标记技术的伪知识蒸馏（PKD）模型，该模型计算效率高，适合实时设备上的显着性预测。