With recent advancements in communications and sensor technologies, the Internet of Things (IoT) has been experiencing rapid growth. It is estimated that billions of objects will be connected, which would create a vast amount of data. Cloud computing has been the predominant choice for monitoring connected objects and delivering data-based intelligence, but high response time and network load of cloud-based solutions are limiting factors for IoT deployment. In order to cope with this challenge, this paper proposes a novel approach to provide low-level intelligence for IoT applications through an IoT edge controller that is leveraging the Fuzzy Logic Controller along with edge computing. This low-level intelligence, together with cloud-based intelligence, forms the distributed IoT intelligence. The proposed controller allows distributed IoT gateway to manage input uncertainties; besides, by interacting with its environment, the learning system can enhance its performance over time, which leads to improving the reliability of the IoT gateway. Therefore, such a controller is able to offer different context-aware reasoning to alleviate the distributed IoT. A simulated smart home scenario has been done to prove the plausibility of the low-level intelligence concerning reducing latency and more accurate prediction through learning experiences at the edge

The introduction of distributed-reasoning through ubiquitous instrumentation within the distributed Internet of Things (IoT) leads to outstanding improvements in real-time monitoring, optimization, fault-tolerance, traffic, healthcare, so on. Using a ubiquitous controller to interconnect devices in the IoT, however monumental, is still in its embryonic stage, it has the potential to create distributed-intelligent IoT solutions that are more eclient and safer than centric intelligence. It is essential to step in a new direction for designing a distributed intelligent controller for task scheduling as a means to, first, dynamically interact with a smart environment in eclient real-time data processing and, second, react to flexible changes. To cope with these issues, we outline a two-level intelligence schema, using edge computing to enhance distributed IoT. The edge schema pushes the streaming processing capability from cloud to edge devices to better support timely and reliable streaming analytics to improve the performance of smart IoT applications. In this paper, in order to provide better, reliable, and flexible streaming analytics and overcome the data uncertainties, we proposed an IoT gateway controller to provide low-level intelligence by employing a fuzzy abductive reasoner. Numerical simulations support the feasibility of our proposed approaches.

The development of the Internet of Things over the last decade has led to large amounts of data being generated at the network edge. This highlights the importance of local data processing and reasoning. Machine learning is most commonly used to automate tasks and perform complex data processing and reasoning. Collecting such data in a centralized location has become increasingly problematic in recent years due to network bandwidth and data privacy concerns. The easy-to-change behavior of edge infrastructure enabled by software-defined networking (SDN) allows IoT data to be gathered on edge servers and gateways, where federated learning (FL) can be performed: creating a centralized model without uploading data to the cloud. In this paper, we analyze the use of edge computing and federated learning, a decentralized machine learning methodology that increases the amount and variety of data used to train deep learning models. To the best of our knowledge, this paper reports the first use of federated learning to help the Microgrid Energy Management System (EMS) predict load and obtain promising results. Simulations were performed using TensorFlow Federated with data from a modified version of the Dataport site

Over the past decade, the Internet of Things (IoT) has undergone a paradigm shift away from centralized cloud computing towards edge computing. Hundreds of billions of things are estimated to be deployed in the rapidly advancing IoT paradigm, resulting in enormous amounts of data. Transmitting all these data to the cloud has recently proven to be a performance bottleneck, as it causes many network issues relating to latency, power consumption, security, privacy, etc. However, existing paradigms do not use edge devices for decision making. The use of distributed intelligence could strengthen the IoT in several ways by distributing decision-making tasks to edge devices within the network, rather than sending all data to a central server. In this approach, all computational tasks and data are shared among edge devices. To achieve efficient distribution of IoT intelligence and utilization of network resources, it is necessary to integrate the transport network control with distributed edge and cloud resources to provide dynamic and efficient IoT services. This challenge can be overcome by equipping an edge IoT gateway with the intelligence required to extract information from raw data and to decide whether to actuate itself or to outsource complex tasks to the cloud. Distributed intelligence refers to a collaboration between the cloud and the edge. In this context, we first introduce a distributed SDN-based architecture for IoT that enables IoT gateways to perform IoT processing dynamically at the edge of the network, based on the current state of network resources. Next, we propose an algorithm for selecting clients for the training process of Federated Learning Applications, based on the context information of the network. In the last step, we deploy Federated Learning Applications in our distributed SDN-based architecture, using the gateways to provide distributed intelligence at the edge of the network, and conduct a comprehensive and detailed evaluation of the system from several perspectives.

Edge-based distributed intelligence techniques, such as federated learning (FL), have recently been used in many research fields thanks, in part, to their decentralized model training process and privacy-preserving features. However, because of the absence of effective deployment models for the radio access network (RAN), only a tiny number of FL apps have been created for the latest generation of public mobile networks (e.g., 5G and 6G). There is an attempt, in new RAN paradigms, to move toward disaggregation, hierarchical, and distributed network function processing designs. Open RAN (O-RAN), as a cutting-edge RAN technology, claims to meet 5G services with high quality. It includes integrated, intelligent controllers to provide RAN with the power to make smart decisions. This paper proposes a methodology for deploying and optimizing FL tasks in O-RAN to deliver distributed intelligence for 5G applications. To accomplish model training in each round, we first present reinforcement learning (RL) for client selection for each FL task and resource allocation using RAN intelligence controllers (RIC). Then, a slice is allotted for training depending on the clients chosen for the task. Our simulation results show that the proposed method outperforms state-of-art FL methods, such as the federated averaging algorithm (FedAvg), in terms of convergence and number of communication rounds.

The rapid advancement in sensors and communications has led to the expansion of the Internet of Things (IoT) services, where many devices need access to the transport network using fixed or wireless access technologies and mobile Radio Access Networks (RAN). However, supporting IoT in RAN is challenging as IoT services may produce many short and variable sessions, impacting the performance of mobile users sharing the same RAN. To address this issue, network slicing is a promising solution to support heterogeneous service segments sharing the same RAN, which is a crucial requirement of the upcoming fifth-generation (5G) mobile network. This paper proposes a two-level network slicing mechanism for enhanced mobile broadband (eMBB) and Ultra-Reliable and Low Latency communications (URLLC) in order to provide end-to-end slicing at the core and edge of the network with the aim of reducing latency for IoT services and mobile users sharing the same core and RAN using the O-RAN architecture. The problem is modeled at both levels as a Markov decision process (MDP) and solved using hierarchical reinforcement learning. At a high level, an SDN controller using an agent that has been trained by a Double Deep Q-network (DDQN) allocates radio resources to gNodeBs (next-generation NodeB, a 5G base station) based on the requirements of eMBB and URLLC services. At a low level, each gNodeB using an agent that has been trained by a DDQN allocates its pre-allocated resources to its end-users. The proposed approach has been demonstrated and validated through a real testbed. Notably, it surpasses the prevalent approaches in terms of end-to-end latency.