In a Mobile Edge Computing (MEC) environment, latency and energy consumption can be reduced by offloading tasks from mobile devices to Edge Servers (ESs) instead of remote cloud servers. The placement of ESs closest to end users can improve QoE and QoS. Additionally, the deployment of additional servers to cover each user will ensure that user requirements are met even if the designated edge server is unable to provide service. Therefore, the use of additional ESs can improve network robustness. However, edge service providers tend to cover all areas of a city with a minimum number of servers to save costs. Since the coverage zones of ESs can overlap, fewer additional ESs need to be deployed to support overlapping areas, resulting in cost savings. This paper examines the problem of ES placement and proposes a new model to simultaneously optimize network latency, coverage with overlap control, and OPerational EXpenditures (OPEX) of the MEC. In addition, a binary version of the hybrid NSGA II-MOPSO algorithm called BHNM is proposed to obtain the approximated Pareto front. Results based on the real-world dataset from Shanghai Telecom show that the BHNM algorithm outperforms the Binary MOPSO with Turbulence (BMOPSO-T) and NSGA-II algorithms in terms of Pareto front diversity.

With the advent of modern technologies and applications, NDN networks have been known as a reliable approach to meeting the needs ahead. A prominent feature of these networks is the ability to cache comprehensive content within network nodes. Separating the content from the original location reduces the content retrieval latency, network traffic, and overhead within the applications containing considerable required data volume. This approach also improves the user experience . In this article, first, the idea of intra-network caching with an approach based on the cooperation of adjacent nodes along the path is proposed to form a local virtual cluster with distributed cache space. Second, popular cached data will be shared by exchanging minimal notification messages between them to develop content storage decisions. Two new modules are defined in each node, called RIT and NCT which have offered the possibility of utilizing the resources of nodes adjacent to the delivered route. In the next stage, a novel approach is proposed to determine the content caching threshold in each node by considering the parameters affecting the content, as well as the network topology and real-time status of the nodes. Finally, the decision mechanism regarding the storage of content in each node along the path is presented by using an adaptive approach based on set thresholds. In such a manner, undesirable redundancy of content that wastes network resources will be removed, and more caching space in each area of the network will be provided. The results of simulations using ndnSim revealed that the performance of the proposed algorithm (cache hit ratio, average data delivery latency and path stretch) is better than other existing benchmark strategies. Considering other different parameters confirmed the effectiveness of the presented approach.

The Internet of Things (IoT) has significantly increased the number of terminals and network traffic. It is necessary to exploit the full capacity of the network and optimize content transfer. Despite the powerful processing and storage capabilities of base stations in 5G technology, edge caching effectively reduces content access time and duplicate traffic, thus optimizing content transfer for more storage resources. The limited memory resources and the dynamic nature of the requested content have necessitated the use of smart caching methods. Sending the required data to central servers can cause additional network overload and learning disabilities due to private data. For this reason, a hierarchical federated deep reinforcement learning (HFDRL) is proposed in this article that uses the FDRL method to predict the user’s future requests and to determine the appropriate content replacement strategy. In addition, to perform learning and collaborate caching, the method by which partner devices are determined plays a key role in edge caching performance. HFDRL categorizes edge devices hierarchically, thus avoids the disadvantages of very small or large clusters, takes advantage of both. By minimizing the redundancy of content storage and latency, HFDRL improves the performance for each local base station network individually and the global network. Simulation results of the proposed method show that the hit rate and delay have improved, respectively, by an average of 55% and 67% compared to traditional methods, 40% and 56% compared to the collaborative method, and 14% and 15% compared to one-level FDRL without using hierarchical edge devices clustering.

Social tagging provides an effective way for users to organize, manage, share and search for various kinds of resources. These tagging systems have resulted in more and more users providing an increasing amount of information about themselves that could be exploited for recommendation purposes. How ever, since social tags are generated by users in an uncontrolled way, they can be noisy and unreliable and thus exploiting them for recommendation is a non-trivial task. In this article, a new recommender system is proposed based on the similarities between user and item profiles. The approach here is to generate user and item profiles by discovering frequent user-generated tag patterns. We present a method for finding the underlying meanings (concepts) of the tags, mapping them to semantic entities belonging to external knowledge bases, namely WordNet and Wikipedia, through the exploitation of ontologies created within the W3C Linking Open Data initiative. In this way, the tag-base profiles are upgraded to semantic profiles by replacing tags with the corresponding ontology concepts. In addition, we further improve the semantic profiles through enriching them with a semantic spreading mechanism. To evaluate the performance of this proposed approach, a real dataset from The Del.icio.us website is used for empirical experiment. Experimental results demonstrate that the proposed approach provides a better representation of user interests and achieves better recommendation results in terms of precision and ranking accuracy as compared to existing methods. We further investigate the recommendation performance of the proposed approach in face of the cold start problem and the result confirms that the proposed approach can indeed be a remedy for the problem of cold start users and hence improving the quality of recommendations.

With the rapid increasing rate of the high volume of social web contents due to the growing popularity of social media services, significant attention has been drawn towards recommender systems i.e. systems, that offer recommendations to users on items appropriate to their requirements. To offer su itable recommendations, the systems need comprehensive user and item models that would be able to provide thorough understanding of their characteristics and preferences. In this article, a new recommender system is proposed based on the similarities between user and item profiles. The approach here is to generate user and item profiles by discovering frequent user-generated tag patterns, and to enrich each individual profile by a two-phase profile enrichment procedure. The profiles are extended by association rules discovered through the association rule mining process. The user/item profiles are further enriched through collaboration with other similar user/item profiles. To evaluate the performance of this proposed approach, a real dataset from The Del.icio.us website is used for empirical experiment. Experimental result s demonstrate that the proposed approach provides a better representation of user interests and achieves better recommendation results in terms of precision and ranking accuracy as compared to existing methods.