This paper surveys the conceptual aspects, as well as recent developments in fault detection, isolation, and service restoration (FDIR) following an outage in an electric distribution system. This paper starts with a discussion of the rationale for FDIR, and then investigates different areas of the FDIR problem. Recently reported approaches are compared and related to discussions on current practices. This paper then addresses some of the often-cited associated technical, environmental, and economic challenges of implementing self-healing for the distribution grid. The review concludes by pointing toward the need and directions for future research.

A system for monitoring and forecasting urban air pollution is presented in this paper. The system uses low-cost air-quality monitoring motes that are equipped with an array of gaseous and meteorological sensors. These motes wirelessly communicate to an intelligent sensing platform that consists of several modules. The modules are responsible for receiving and storing the data, preprocessing and converting the data into useful information, forecasting the pollutants based on historical information, and finally presenting the acquired information through different channels, such as mobile application, Web portal, and short message service. The focus of this paper is on the monitoring system and its forecasting module. Three machine learning (ML) algorithms are investigated to build accurate forecasting models for one-step and multi-step ahead of concentrations of ground-level ozone (O ₃ ), nitrogen dioxide (NO ₂ ), and sulfur dioxide (SO ₂ ). These ML algorithms are support vector machines, M5P model trees, and artificial neural networks (ANN). Two types of modeling are pursued: 1) univariate and 2) multivariate. The performance evaluation measures used are prediction trend accuracy and root mean square error (RMSE). The results show that using different features in multivariate modeling with M5P algorithm yields the best forecasting performances. For example, using M5P, RMSE is at its lowest, reaching 31.4, when hydrogen sulfide (H ₂ S) is used to predict SO ₂ . Contrarily, the worst performance, i.e., RMSE of 62.4, for SO ₂ is when using ANN in univariate modeling. The outcome of this paper can be significantly useful for alarming applications in areas with high air pollution levels.

To accelerate the implementation of network functions/middle boxes and reduce the deployment cost, recently, the concept of network function virtualization (NFV) has emerged and become a topic of much interest attracting the attention of researchers from both industry and academia. Unlike the traditional implementation of network functions, a software-oriented approach for virtual network functions (VNFs) creates more flexible and dynamic network services to meet a more diversified demand. Software-oriented network functions bring along a series of research challenges, such as VNF management and orchestration, service chaining, VNF scheduling for low latency and efficient virtual network resource allocation with NFV infrastructure, among others. In this paper, we study the VNF scheduling problem and the corresponding resource optimization solutions. Here, the VNF scheduling problem is defined as a series of scheduling decisions for network services on network functions and activating the various VNFs to process the arriving traffic. We consider VNF transmission and processing delays and formulate the joint problem of VNF scheduling and traffic steering as a mixed integer linear program. Our objective is to minimize the makespan/latency of the overall VNFs' schedule. Reducing the scheduling latency enables cloud operators to service (and admit) more customers, and cater to services with stringent delay requirements, thereby increasing operators' revenues. Owing to the complexity of the problem, we develop a genetic algorithm-based method for solving the problem efficiently. Finally, the effectiveness of our heuristic algorithm is verified through numerical evaluation. We show that dynamically adjusting the bandwidths on virtual links connecting virtual machines, hosting the network functions, reduces the schedule makespan by 15%-20% in the simulated scenarios.

Traditionally, service-specific network functions (NFs) (e.g., Firewall, intrusion detection system, etc.) are executed by installation-and maintenance-costly hardware middleboxes that are deployed within a datacenter network following a strictly ordered chain. NF virtualization (NFV) virtualizes these NFs and transforms them into instances of plain software referred to as virtual NFs (VNFs) and executed by virtual machines, which, in turn, are hosted over one or multiple industry-standard physical machines. The failure (e.g., hardware or software) of any one of a service chain's VNFs leads to breaking down the entire chain and causing significant data losses, delays, and resource wastage. This paper establishes a reliability-aware and delay-constrained (READ) routing optimization framework for NFV-enabled datacenter networks. READ encloses the formulation of a complex mixed integer linear program (MILP) whose resolution yields an optimal network service VNF placement and traffic routing policy that jointly maximizes the achieved respective reliabilities of supported network services and minimizes these services' respective end-to-end delays. A heuristic algorithm dubbed Greedy-k-shortest paths (GSP) is proposed for the purpose of overcoming the MILP's complexity and develop an efficient routing scheme whose results are comparable to those of READ's optimal counterparts. Thorough numerical analyses are conducted to evaluate the network's performance under GSP, and hence, gauge its merit; particularly, when compared to existing schemes, GSP exhibits an improvement of 18.5% in terms of the average end-to-end delay as well as 7.4% to 14.8% in terms of reliability.

With the smart grid and smart homes development, different data are made available, providing a source for training algorithms, such as deep reinforcement learning (DRL), in smart grid applications. These algorithms allowed the home energy management systems (HEMSs) to deal with the computational complexities and the uncertainties at the end-user side. This article proposes a multi-objective DRL-HEMS: a data-driven solution, which is a trained DRL agent in a HEMS to optimize the energy consumption of a household with different appliances, an energy storage system, a photovoltaic system, and an electric vehicle. The proposed solution reduces the electricity cost considering the resident’s comfort level and the loading level of the distribution transformer. The distribution transformer load is optimized by optimizing its loss-of-life. The performance of DRL-HEMS is evaluated using real-world data, and results show that it can optimize multiple appliances operation, reduce electricity bill cost, dissatisfaction cost, and the transformer loading condition.

Online condition assessment of the power system devices and apparatus is considered vital for robust operation, where partial discharge (PD) detection is employed as a diagnosis tool. PD measurements, however, are corrupted with different types of noises such as white noise, random noise, and discrete spectral interferences. Hence, the denoising of such corrupted PD signals remains a challenging problem in PD signal detection and classification. The challenge lies in removing these noises from the online PD signal measurements effectively, while retaining its discriminant features and characteristics. In this paper, wavelet-based denoising with a new histogram-based threshold function and selection rule is proposed. The proposed threshold estimation technique obtains two different threshold values for each wavelet sub-band and uses a prodigious thresholding function that conserves the original signal energy. Moreover, two signal-to-noise ratio (SNR) estimation techniques are derived to fit with actual PD signals corrupted with real noise. The proposed technique is applied on different acoustic and current measured PD signals to examine its performance under different noisy environments. The simulation results confirm the merits of the proposed denoising technique compared with other existing wavelet-based techniques by measuring four evaluation metrics: 1) SNR; 2) cross-correlation coefficient; 3) mean square error; and 4) reduction in noise level.