The economics, reliability and carbon efficiencyof the hybrid system microgrid (HMS) often conflict; hence,reasonable design of the initial microgrid size is important. Wepropose an improved two-archive many-objective evolutionaryalgorithm (TAMaEA) based on fuzzy decisions to solve theoptimal sizing problem for an HMS. For the HMS, the costof power generation, loss of power supply probability, pollutantemissions, and power balance are considered objective functions.For the proposed algorithm, we employ two archives withdifferent diversity selection strategies to balance convergence anddiversity in the high-dimensional objective space. In addition, afuzzy decision method is proposed to further help decision makersobtain a solution from the Pareto front that optimally balanceseach objective. The effectiveness of the proposed algorithm insolving the HMS size optimization problem is investigated forthe case of Yanbu, Saudi Arabia. The simulation results provethat compared with the two-archive evolutionary algorithm forconstrained many-objective optimization (CTAEA), the improveddecomposition-based evolutionary algorithm (IDBEA) and theclustering-based adaptive many objective evolutionary algorithm(CAMOEA), the proposed algorithm can optimize the size ofthe system; the system cost is reduced by 7%, 13%, and 21%, respectively.

We propose a big data based analysis framework to analyze and extract network behaviors in cellular networks for Industry 4.0 applications from a big data perspective, using Hadoop, Hive, HBase, and so on. The data pre-handling and traffic flow extraction approaches are presented to construct effective traffic matrices. Accordingly, we can capture network behaviors in cellular networks from a network-wide perspective. Although there have been a number of prior studies on cellular network usage, to the best of our knowledge, this paper is a first study that characterizes network behaviors using the big data analytics to analyze a network big data of Call Detail Records (CDRs) over a longer duration (5 months), with more users (5 million), more records (several hundred million lines) and nationwide coverage. The call pattern analysis and network behavior extraction approaches are designed to perform big data analysis and feature extractions. Then the corresponding algorithms are proposed to characterize network behaviors, i.e., cellular call patterns and network resource usage. The detailed evaluation is proposed to validate our method. For example, we find that some unpopular calls can last longer time and thus consume more network resources.

In a deregulated energy market, voltage security (VS) is one of the major concerns, as it improves the loadability limits, loading profiles while concurrently reducing power loss. Further, voltage dependent loads can operate at high efficiency at rated voltage. Therefore, power utilities have to explore options of reconfiguration to secure the voltage level under frequently changing operating conditions. In this study, an efficient heuristic and meta‐heuristic (harmony search) approach for reconfiguration is proposed by imposing VS. Two indices namely node voltage security index (NVSI) and node voltage quality index are developed for aggregated improvement in node voltages. Moreover, efficient methodologies for identification of new tie‐lines, network radiality and the load flow solution are also presented. The effectiveness of the proposed index and the methodology is tested for reconfiguration of various distribution systems and the results are obtained with reduced computational efforts.

Understanding the performance of Compound TCP (C-TCP) in wireless settings is complicated because of C-TCP's hybrid congestion control, and the complex inter-dependencies between losses due to wireless channel errors, MAC-layer collisions, and AP buffer overflows. In this paper, we develop a comprehensive model to study the performance of long-lived CTCP flows over industry 4.0 WiFi infrastructure, taking all losses into account. Our mathematical model includes WiFi system parameters, such as the retransmissions limit and the AP buffer size, in order to see how they affect transport-layer throughput and fairness. More importantly, we extend the analytical model to multiple APs, and compare the performance of a dual AP scenario with a conventional single AP scenario. Our results show that using Cognitive Radio (CR) and Federated Learning (FL) techniques in the industrial multiple APs scenario can substantially improve the performance.

Driverless parking, an influential application of Mobility as a Service (MaaS) model, is one of the clear early benefits for autonomous vehicles, given often narrow spaces and multiple potential hazards (such as pedestrians stepping out from in between other vehicles). In recent years, real momentum has been building up for designing automated parking models for vehicles. However, in such an autonomous parking design, location privacy and identity privacy issues are always overlapping due to the improper sharing of data. Most existing studies barely investigate and poorly address such privacy issues. Motivated by this, we develop (and evaluate) an experience-driven, secure and privacy-aware framework of parking reservations for automated cars. Our idea of using differential privacy with zero-knowledge proof provides both security and privacy guarantees to users. Furthermore, the performance of the developed model is enhanced by exploiting reinforcement learning approach such that the utility of the system and the parking reservation rate can be maximized. Extensive evaluation demonstrates the superiority of the proposed model.