The widespread adoption of Electric Vehicles (EVs) requires an efficient charging infrastructure. Using data connection-based charging equipment, smart charging, and vehicle-to-grid (V2G) charging technologies allow electric vehicles to connect to the electrical grid. This enables the exchange of information and instructions. However, this ecosystem is susceptible to physical or cyberattacks, just like any other cyber-physical system. In this paper, we investigate load-altering (LA) attacks that impact the functionality of the smart grid. We propose a two-phase strategy to avoid, detect, and mitigate attacks. Our first step is scheduling charging station operations to normalize system utilization to avert future simultaneous attacks. Therefore, a distributed Deep Reinforcement Learning (DRL) model is used to establish the ON/OFF status of each charging station. To maintain the system's power stability during the charging process, the system uses an event-based method to respond to the abrupt change in charging/discharging behavior. To detect attacks, a second multi-agent deep-reinforcement learning model is created. This enables the system to recognize and neutralize the effects of LA attacks on the power grid. After the compromised entities are located, they are isolated and the demands of certain backup charging stations either completely or partially replace the canceled power demands. The performance study shows that the suggested strategy minimizes the impact of LA attacks and delivers good results in terms of detection accuracy.

With the widespread adoption of Electrical Vehicles (EVs), EV charging infrastructure has become more advanced. Unfortunately, this cyber-physical system is vulnerable to physical or cyberattacks. In this work, we focus on load-altering (LA) attacks that affect the operation of the power grid. We propose a distributed multi-agent Deep Reinforcement Learning (DRL) based solution to detect, identify, and mitigate LA attacks. The defense system responds to the sudden change in charging/discharging behavior using an event-based approach to preserve power stability throughout the charging process. The proposed approach allows the system to identify and counteract the impact of LA attacks on the electrical grid. After the compromised entities are identified, they are isolated, and a backup charging strategy is applied to fully or partially recover the operation of the charging system. According to the performance evaluation, the proposal reduces the effect of LA attacks while producing good detection accuracy rates.

The term Industrial Internet of Things (IIoT) was created to describe a specific area of the Internet of Things (IoT) that integrates information and communication technologies (ICTs) like cloud/edge computing, wireless sensor/actuator networks, and connected objects to enable and accelerate the development of Industry 4.0. IIoT applications (e.g., smart manufacturing, remote control of industrial machinery, and critical system monitoring) have various levels of criticality and Quality-of-Service (QoS) requirements. However, the characteristics of data collected by interconnected devices complicate the task of guaranteeing the QoS requirements in terms of latency and reliability in addition to the huge amount of energy consumption. As a potential solution, edge computing offers additional powerful resources in the proximity of the IIoT devices. Hence, the required QoS can be achieved by offloading computation-intensive tasks to edge servers. Moreover, the offloading process needs to be optimized to take full advantage. Unlikely, conventional optimization methods are very complex to be applied in the IIoT context. To overcome this issue, we propose a computation offloading approach based on deep reinforcement learning (DRL) to minimize long-term energy consumption and maximize the number of tasks completed before their tolerant deadlines. We introduce a system with multiple agents to deal with the increasing dimension of the action space, where each IIoT device is represented by its own DRL model. The goal of the model is to maximize a flexible and long-term reward. In addition, the DRL models are trained in the cloud and make decisions online in the edge servers, allowing quick decision making by avoiding iterative online optimization procedures. The performance of the proposed approach is evaluated through simulation. The proposal shows promising results compared to other approaches.

With the expansion of connected devices used for industrial purposes, the Industrial Internet of Things (IIoT) has emerged as a specific branch of the Internet of Things (IoT) for Industry 4.0. Its applications in industrial domains include monitoring, smart manufacturing, and virtual and augmented reality. However, the huge amount of data generated by IIoT devices with limited computing resources makes it challenging to guarantee the different required quality of service (QoS) of the applications while minimizing the computation cost in terms of energy consumption. especially in terms of latency. In this paper, we opt for the offloading of dependent computation-intensive tasks to edge and cloud servers with more powerful computation capacities. Our proposed model aims to minimize the energy consumption of each IIoT device while respecting the maximal tolerant deadline of task completion. We propose to cluster the IIoT devices that have dependent tasks together to better handle this dependency. Moreover, we propose a distributed cooperative game that allows each device to decide whether it is beneficial for it and for its cluster, in terms of task completion and energy consumption, to offload its task or execute it locally. We prove that the Nash Equilibrium exists by proving that our game is a weighted potential game. Finally, we propose a practical distributed offloading algorithm to implement the cooperative game. The performance evaluation results show that the proposal optimizes energy consumption whilst increasing the number of tasks completed on time.

The term ‘’Industrial Internet of Things’’ (IIoT) was created to describe a specific area of the Internet of Things (IoT) that integrates Information and Communication Technologies (ICT) like cloud/edge computing, wireless sensor/actuator networks, connected objects, etc. to enable and accelerate the development of industry 4.0. Industry standards for IoT device connectivity and operation set it apart. A few of the properties of Industrial IoT include its high levels of resilience, communication availability, enormous data collecting, security, accuracy, automation, and interoperability. IIoT is also used for complicated task delegation, data-driven decision-making, and remote control of equipment. The IIoT applications also have various levels of criticality and quality of service requirements. Hence, it is very challenging to respect the specificity of each application and guarantee the required QoS. In this paper, we offload computationally demanding tasks to edge and cloud servers with stronger computational capabilities. Our suggested model tries to maximize the number of tasks completed before their tolerant deadlines while minimizing each IIoT device’s energy consumption. Furthermore, we introduce a distributed cooperative game that enables each device to choose whether to offload its tasks or locally execute them based on task completion and energy consumption. We demonstrate the existence of the Nash equilibrium by demonstrating that the proposed game is a weighted potential game. We also propose a practical implementation of the game using a distributed mechanism. Finally, we evaluate the proposal using simulation to show the benefits of computation offloading in terms of latency and energy consumption.

The advent of smart grid technologies provides new tools and services to optimally manage the electricity grids. One of the most interesting services that emerged with the development of Information and Communication Technologies (ICTs) is energy demand management. This service permits us to face the issues caused by the ever-increasing energy demand such as grid congestion during peak hours, increasing energy generation costs, and even blackouts. In this paper, we investigate the problem of consumer-side optimization of residential energy demand. Our main aim is to better distribute the energy consumption over a day to avoid or reduce the demand during peak hours. Hence, we propose a fog computing-based model for energy demand scheduling using energy consumption cost as an incentive. In this model, the fog nodes schedule the appliances’ operations in order to reduce the individual and global energy bills whilst respecting consumers’ preferences. The proposed approach performs a multi-agent system-based cooperative scheduling game with minimal interactions between the nodes. Moreover, we present a fog nodes’ assignment scheme to decide which node will handle which appliances’ schedules. The nodes’ assignment strategy aims to optimize the use of fog nodes’ resources whilst reducing the scheduling process latency. The performance evaluation shows that the use of fog computing can achieve interesting results in terms of the reduction of energy consumption cost. For instance, the energy consumption during peak hour decreases by more than 25% from 670 kWh to 500 kWh when the scheduling game is performed. As a consequence, the energy consumption cost decreases by 7% from 806 € to 750 € .

Wireless Sensor/Actuator Networks (WSANs) enable prominent services in different domains including smart cities, industry, and agriculture. These services may demand high quality of service (QoS) requirements in terms of data rate, throughput, latency, which can be challenging regarding the specific characteristics of such networks (e.g., a huge number of connected devices, the communication mode, limited resources, etc.). In this paper, we focus on the transmission power allocation problem to match the QoS requirements in terms of data rate maximization and interference minimization. We propose a game theory-based channel selection and transmission power determination scheme in WSANs. As a first step, we formulate the problem as a constrained multi-objective optimization problem. This problem is a tradeoff between the maximization of the data rate of each node and the minimization of the transmission power to reduce the interference ratio. The second step consists of the proposition of a multi-leader-follower game model to determine the transmission channel and power with consideration of data rate, packet deadlines, and fairness between nodes. Finally, we perform extensive simulations to evaluate the proposed scheme performance.

In this paper, we investigate the concept of reputation to improve the resistance of vehicular networks against malicious and misbehaving vehicles. We propose a robust reputation management system, which consists of a model for reputation calculation and a credibility model to enhance network efficiency. The reputation score or value reflects the behavior of a vehicle towards other vehicles and network services (selfish, cooperative, malicious, misbehaving, etc.); while the credibility of vehicles is used to determine whether a reputation score given by a vehicle is correct to deal with malicious vehicles that use reputation calculation to spoil the network operation. We first describe how the reputation score of each vehicle is determined. Then, we introduce a non-cooperative game, where each vehicle aims to maximize its credibility. The effectiveness of the proposed model is demonstrated through extensive simulations.

The demand-side management is considered as an interesting functionality offered by the recent smart grid. This functionality allows the control and scheduling of consumer energy demand, which helps avoiding the problems of offer-demand gap and consumption peaks. The cloud is considered as a powerful tool that ensures scheduling appliances' energy demand in centralized manner. However, the distance between the end users and the cloud might be a problem for latency. In addition, the more and more increasing number of connected objects, generating a huge amount of data that must be transmitted over the communication network, worsens the situation. Fortunately, the novel paradigm of fog computing came to mitigate these issues. In this paper, we propose a cloud-fog computing architecture for the energy demand scheduling. We propose to use this architecture to improve the consumption distribution over the day to reduce the total energy cost for smart buildings. Our work includes two parts: a distributed game-based approach for demand scheduling, and a model for the selection of fog nodes that will perform this distributed approach. The simulation results of the two proposals show that the integration of the fog architecture helps to considerably reduce the energy scheduling delay while determining the optimal demand schedule.

One of the most interesting challenges in the modern grids is the consumer demand management and optimization. However, the Information and Communication Technologies (ICTs) can offer promising solutions for this challenge. In this paper, we introduce a distributed multi-level solution for the energy consumption optimization. The proposed solution offers an automated demand control mechanism, using a Wireless Sensor Actuator Network (WSAN), to reduce the energy consumption of each consumer. Moreover, we propose a scheduling scheme that minimizes the total cost of a building energy demand based on a cooperative game model to achieve the collective goal. We introduce also a mechanism that improves the consumer satisfaction when the available energy is insufficient. The performance evaluation shows that the proposed approach reduces the energy demand, the total consumption cost, and the peak to average ratio.

The advent of smart grids offers us the opportunity to better manage the electricity grids. One of the most interesting challenges in the modern grids is the consumer demand management. Indeed, the development in Information and Communication Technologies (ICTs) encourages the development of demand-side management systems. In this paper, we propose a distributed energy demand scheduling approach that uses minimal interactions between consumers to optimize the energy demand. We formulate the consumption scheduling as a constrained optimization problem and use game theory to solve this problem. On one hand, the proposed approach aims to reduce the total energy cost of a building's consumers. This imposes the cooperation between all the consumers to achieve the collective goal. On the other hand, the privacy of each user must be protected, which means that our distributed approach must operate with a minimal information exchange. The performance evaluation shows that the proposed approach reduces the total energy cost, each consumer's individual cost, as well as the peak to average ratio.

Wireless sensor networks (WSNs) are widely used nowadays in various domains. In general, the applications in which the WSN is deployed need that this network presents a minimal degree of reliability, effectiveness and robustness. However, the specificity of the nodes deployed in this type of networks makes them prone to failures. In this paper, we discuss the recovery from simultaneous failures for a large scale WSN in a multichannel context. Indeed, we propose a deployment scenario which uses thousands of sensor nodes and relay nodes. Then, we propose Simultaneous Failure Recovery based on Relay Node Relocation (SFR-RNR) approach which aims to recover from simultaneous failures. These failures lead to the damage of a whole segment of the WSN, and hence, the loss of the monitored field coverage and/or connectivity. SFR-RNR rearranges a minimal set of relay nodes to restore, partially, the coverage and improve or restore the connectivity; then it reallocates the channels to minimize the interferences. The performance of the proposed approach is evaluated by simulation.

Wireless sensor networks (WSNs) are widely used nowadays and in a various domains. However, the specificity of the nodes deployed in this type of networks makes them prone to failures. To overcome this problem and guarantee the continuity of the network functioning even in the presence of node failure, fault tolerance mechanisms need to be designed and integrated to the operation of those networks. These fault tolerance mechanisms will more precisely deal with recovering from a failures and resuming the correct functioning of a WSN. With that aim, we propose in this paper a new centralized curative approach, called Rotating Nodes based Failure Recovery (RNFR), dedicated to restore connectivity in multi-channel WSNs. The proposed solution targets the failure of particular nodes designated as articulation nodes, which leads to the partitioning of the WSN into many segments isolated from each other and leading to connectivity loss. Therefore, the main tasks of RNFR are the restoration of the connectivity after an articulation node failure using reorganization and reallocation of channels. Moreover, the solution uses a node rotation technique to communicate the recovery information to all the disjoint parts of the network. The proposed approach proved to be interesting by giving motivating results while evaluated through simulation.

One of the common challenges in Wireless Sensor Networks (WSNs) is the degradation of the performance due to several factors. In one hand, the interference between concurrent transmissions can affect the efficiency of the network and considerably degrades its performance. The exploitation of the multiple channels available in sensor technology and the development of protocols for WSNs can be a solution to mitigate this interference. In this case, the way the channels are assigned has a significant impact on the performance of multi-channel communication. In the other hand, the faults occurred in WSNs are another factor that degrades the WSN performance. In this paper, we propose a distributed energy-efficient solution for multi-channel allocation based on the routing. This solution implements a fault recovery mechanism to reconnect the network after an articulation node failure. A main task of the proposed approach is to minimize the number of interferences when allocating the limited number of available channels. As a second task, the approach minimizes the energy consumption by defining a sleeping/activity strategy. The fault recovery mechanism aims to restore the network connectivity and reallocate channels without affecting the whole WSN. The performance of the proposed solution is evaluated by simulation.

One of the most common needs in wireless sensor networks (WSNs) is the continuity of network function even in the presence of some node failures. This is called fault tolerance. In general, fault tolerant solutions can be preventive or reactive: the preventive techniques aim to prevent the failure by minimizing and balancing the energy consumption in each node, while the reactive techniques intervene after a failure was detected. In this paper, we propose a new preventive/reactive fault tolerant scheme dedicated to manage the energy consumption and reconnect the WSN in case of articulation node failure. The specificity of this scheme is the use of multichannel communications, allowing simultaneous data transmission, which decreases the interferences between nodes and then decreases data retransmissions. The second task of this scheme targets the reorganization of the network after a network portioning episode. Such episode means that the WSN is partitioned in many segments after an articulation node failure. More precisely, we present here two heuristics for channel allocation/reallocation and WSN reorganization after a network failure. The performances of the proposed scheme is evaluated and proved through simulation.