Abstract
Cloud computing environments provide users with Internet-based services and one of their main challenges is security issues. Hence, using Intrusion Detection Systems (IDSs) as a defensive strategy in such environments is essential. Multiple parameters are used to evaluate the IDSs, the most important aspect of which is the feature selection method used for classifying the malicious and legitimate activities. We have organized this research to determine an effective feature selection method to increase the accuracy of the classifiers in detecting intrusion. A Hybrid Ant-Bee Colony Optimization (HABCO) method is proposed to convert the feature selection problem into an optimization problem. We examined the accuracy of HABCO with BHSVM, IDSML, DLIDS, HCRNNIDS, SVMTHIDS, ANNIDS, and GAPSAIDS. It is shown that HABCO has a higher accuracy compared with the mentioned methods.

Abstract
Cloud computing is becoming a very popular form of distributed computing, in which digital resources are shared via the Internet. The user is provided with an overview of many available resources. Cloud providers want to get the most out of their resources, and users are inclined to pay less for better performance. Task scheduling is one of the most important aspects of cloud computing. In order to achieve high performance from cloud computing systems, tasks need to be scheduled for processing by appropriate computing resources. The large search space of this issue makes it an NP-hard problem, and more random search methods are required to solve this problem. Multiple solutions have been proposed with several algorithms to solve this problem until now. This paper presents a hybrid algorithm called GSAGA to solve the Task Scheduling Problem (TSP) in cloud computing. Although it has a high ability to search the problem space, the Genetic Algorithm (GA) performs poorly in terms of stability and local search. It is therefore possible to create a stable algorithm by combining the general search capacities of the GA with the Gravitational Search Algorithm (GSA). Our experimental results indicate that the proposed algorithm can solve the problem with higher efficiency compared with the state-of-the-art.

Abstract
Cloud Internet of Things (CIoT) environments, as the essential basis for computing services, have been subject to abuses and cyber threats. The adversaries constantly search for vulnerable areas in such computing environments to impose their damages and create complex challenges. Hence, using intrusion detection and prevention systems (IDPSs) is almost mandatory for securing CIoT environments. However, the existing IDPSs in this area suffer from some limitations, such as incapability of detecting unknown attacks and being vulnerable to the single point of failure. In this paper, we propose a novel distributed multi-agent IDPS (DMAIDPS) that overcomes these limitations. The learning agents in DMAIDPS perform a six-step detection process to classify the network behavior as normal or under attack. We have tested the proposed DMAIDPS with the KDD Cup 99 and NSL-KDD datasets. The experimental results have been compared with other methods in the field based on Recall, Accuracy, and F-Score metrics. The proposed system has improved the Recall, Accuracy, and F-Scores metrics by an average of 16.81%, 16.05%, and 18.12%, respectively.

Abstract
This research aims to represent a novel approach to detect malicious nodes in Ad-hoc On-demand Distance Vector (AODV) within the next-generation smart cities. Smart city applications have a critical role in improving public services quality, and security is their main weakness. Hence, a systematic multidimensional approach is required for data storage and security. Routing attacks, especially sinkholes, can direct the network data to an attacker and can also disrupt the network equipment. Communications need to be with integrity, confidentiality, and authentication. So, the smart city and urban Internet of Things (IoT) network, must be secure, and the data exchanged across the network must be encrypted. To solve these challenges, a new protocol using CLustering Multi-Layer Security Protocol (CL-MLSP) with AODV has been proposed. The Advanced Encryption Standard (AES) algorithm is aligned with the proposed protocol for encryption and decryption. The shortest path is obtained by the clustering method based on energy, mobility, and distribution for each node. Ns2 is used to evaluate the CL-MLSP performance, and the parameters are network lifetime, latency, packet loss, and security. We have compared CL-MLPS with ECP-AODV, Probe, and Multi-Path. The proposed method superiority rates in energy consumption, drop rate, delay, throughput, and security performance are 6.54%, 12.87%, 8.12%, 9.46%, respectively.

Abstract
The recent proliferation of sensors and actuators, which is related to the Internet of Things (IoT), provide smart living to the general public in many data-critical areas, from homes and healthcare to power grids and transport [...]

Abstract
In mobile networks, 5G Ultra-Dense Networks (UDNs) have emerged as they effectively increase the network capacity due to cell splitting and densification. A Base Station (BS) is a fixed transceiver that is the main communication point for one or more wireless mobile client devices. As UDNs are densely deployed, the number of BSs and communication links is dense, raising concerns about resource management with regard to energy efficiency, since BSs consume much of the total cost of energy in a cellular network. It is expected that 6G next-generation mobile networks will include technologies such as artificial intelligence as a service and focus on energy efficiency. Using machine learning it is possible to optimize energy consumption with cognitive management of dormant, inactive and active states of network elements. Reinforcement learning enables policies that allow sleep mode techniques to gradually deactivate or activate components of BSs and decrease BS energy consumption. In this work, a sleep mode management based on State Action Reward State Action (SARSA) is proposed, which allows the use of specific metrics to find the best tradeoff between energy reduction and Quality of Service (QoS) constraints. The results of the simulations show that, depending on the target of the 5G use case, in low traffic load scenarios and when a reduction in energy consumption is preferred over QoS, it is possible to achieve energy savings up to 80% with 50 ms latency, 75% with 20 ms and 10 ms latencies and 20% with 1 ms latency. If the QoS is preferred, then the energy savings reach a maximum of 5% with minimal impact in terms of latency.