The topic of microgrids (MGs) is a fast-growing and very promising field of research in terms of energy production quality, pollution reduction and sustainable development. Moreover, MGs are, above all, designed to considerably improve the autonomy, sustainability, and reliability of future electrical distribution grid. At the same time, aspects of MGs energy management, taking into consideration distribution generation systems, energy storage devices, electric vehicles, and consumption components have been widely investigated. Besides, grid architectures including DC, AC, or hybrid power generation systems, energy dispatching problems modelling, operating modes (islanded or grid connected), MGs sizing, simulations and problems solving optimization approaches, and other aspects, have been raised as topics of great interest for both electrical and computer sciences research communities. Furthermore, the United Nations Framework Convention on Climate Change and government policies and incentives have paved the way to massive electric vehicle (EV) deployment. Hence, several research studies have been conducted to investigate the integration of EVs in national power grid and future MGs. Specifically, EV charging stations’ bi-directional power flow control and energy management have been considerably explored. These issues index challenging research topics, which are in most cases still under progress. This paper gives an overview of MGs technology advancement in recent decades, taking into consideration distributed energy generation (DER), energy storage systems (ESS), EVs, and loads. It reviews the main MGs architecture, operating modes, sizing and energy management systems (EMS) and EVs integration.

The vehicle-to-grid concept emerged very quickly after the integration of renewable energy resources because of their intermittency and to support the grid during on-peak periods, consequently preventing congestion and any subsequent grid instability. Renewable energies offer a large source of clean energy, but they are not controllable, as they depend on weather conditions. This problem is solved by adding energy storage elements, implementing a demand response through shiftable loads, and the vehicle-to-grid/vehicle-to-home technologies. Indeed, an electric vehicle is equipped with a high-capacity battery, which can be used to store a certain amount of energy and give it back again later when required to fulfill the electricity demand and prevent an energy shortage when the main-grid power is limited for security reasons. In this context, this paper presents a comparative study between two home microgrids, in one of which the concept of vehicle-to-home is integrated to provide a case study to demonstrate the interest of this technology at the home level. The considered microgrid is composed of renewable energy resources, battery energy storage, and is connected to the main grid. As the vehicle is not available all day, in order to have consistent results, its intervention is considered in the evening, night, and early morning hours. Two case studies are carried out. In the first one, the vehicle-to-home concept is not taken into account. In this case, the system depends only on renewable resources and the energy storage system. Subsequently, the electric vehicle is considered as an additional energy storage device over a few hours. Electric vehicle integration brings an economic contribution by reducing the cost, supporting the other MG components, and relieving the main grid. Simulation results using real weather data for two cities in France, namely Brest and Toulon, show the effectiveness of the vehicle-to-home concept in terms of cost, energy self-sufficiency, and continuity of electrical service.

Privacy-preserving deep neural networks have become essential and have attracted the attention of many researchers due to the need to maintain the privacy and the confidentiality of personal and sensitive data. The importance of privacy-preserving networks has increased with the widespread use of neural networks as a service in unsecured cloud environments. Different methods have been proposed and developed to solve the privacy-preserving problem using deep neural networks on encrypted data. In this article, we reviewed some of the most relevant and well-known computational and perceptual image encryption methods. These methods as well as their results have been presented, compared, and the conditions of their use, the durability and robustness of some of them against attacks, have been discussed. Some of the mentioned methods have demonstrated an ability to hide information and make it difficult for adversaries to retrieve it while maintaining high classification accuracy. Based on the obtained results, it was suggested to develop and use some of the cited privacy-preserving methods in applications other than classification.

No abstract

Project management has a fundamental role in national development, industrial development, and economic growth. Schedule management is also one of the knowledge areas of project management, which includes the processes employed to manage the timely completion of the project. This paper deals with the Resource-Constrained Project Scheduling Problem (RCPSP), which is a part of schedule management. The objective of the problem is to optimize and minimize the project duration while constraining the resource quantities during project scheduling. There are two important constraints in this problem, namely resource constraints and precedence relationships of activities during project scheduling. Many methods such as exact, heuristic, and meta-heuristic have been developed by researchers to solve the problem, but there is a lack of investigation of the problem using methods such as neural networks and machine learning. In this article, we develop a multi-layer feed-forward neural network (MLFNN) to solve the standard single- mode RCPSP. The advantage of this method over evolutionary methods or metaheuristics is that it is not necessary to generate numerous solutions or populations. The developed MLFNN learns based on eight project parameters, namely network complexity, resource factor, resource strength, average work per activity, percentage of remaining work, etc., which are calculated at each step of project scheduling, and identified priority rules, which are the outputs of the developed neural network. Therefore, after the learning process, the network can automatically select an appropriate priority rule to filter out an unscheduled activity from the list of eligible activities and schedule all activities of the project according to the given project constraints. Finally, we investigate the performance of the presented approach using the standard benchmark problems from PSPLIB.