Search

Firefly Algorithm (FA) mimics firefly behavior by flashing and attracts them. Firefly's global search mobility is improved for dependable global optimization using chaotic maps in this work. Investigations of benchmark problems with chaotic maps are carried out in depth. The system uses eight separate chaotic maps to fine-tune the firefly's enticing movements. By using planned chaotic transmissions instead of fixed values, the new method beats classic firefly methods. According to statistical data and the success rates of FA, the new algorithms improve the solution's performance and the reliability of global optimality.

Optimal placement of sensors in protected cultivation systems to maximize monitoring and control capabilities can guide effective decision-making toward achieving the highest levels of productivity and other desirable outcomes. Reinforcement learning, unlike conventional machine learning methods such as supervised learning does not require large, labeled datasets thereby providing opportunities for more efficient and unbiased design optimization. With the objective of determining the optimal locations of sensors in a greenhouse, a multi-arm bandit problem was formulated using the Beta distribution and solved by the Thompson sampling algorithm. A total of 56 two-in-one sensors designed to measure both internal air temperature and relative humidity were installed at a vertical distance of 1 m and a horizontal distance of 3m apart in a greenhouse used to cultivate strawberries. Data was collected over a period of seven months covering four major seasons, February (winter), March, April, and May (spring), June and July (summer), and October (autumn) and analyzed separately. Results showed unique patterns for sensor selection for temperature and relative humidity during the different months. Furthermore, temperature and relative humidity each had different optimal location selections suggesting that two-in-one sensors might not be ideal in these cases. The use of reinforcement learning to design optimal sensor placement in this study aided in identifying 10 optimal sensor locations for monitoring and controlling temperature and relative humidity.

Evolutionary Algorithms (EAs) are powerful heuristic search approaches which relies on Darwinian evolution that capture global solutions to complex optimization problems which has powerful features of reliability and versatility. (EAs) such as Particle swarm optimization (PSO) is a global optimization method that is extremely effective. PSO's flaws include slow convergence, premature convergence, and getting stuck at local optima. In this paper, chaotic map and dynamic-weight Particle Swarm Optimization (CHDPSOA) are combined with PSO to enhance the search strategy through adjusting the inertia weight of PSO and changing the position update formula in the (CHDPSOA), resulting in efficient balancing for local and global PSO feature selection processes. The performance of CHDPSOA was compared to that of three metaheuristic techniques: Differential Evolution (DE) and the original PSO, using eight numerical functions. The validation of this technique is carried out on four different datasets. The results show that the CHDPSOA is a good feature selection technique that balances the exploration and exploitation search processes to produce good results. The proposed CHDPSOA method performed well in correctly categorizing features using the KNN Classifier for all four datasets.

Software-Defined Networking (SDN) is a network paradigm introduced to overcome the inherent challenges of traditional networks. Its architecture is either deployed with a single controller or multiple controllers. While the first is not suitable for large-scale networks, the latter is confronted with a controller placement problem (CPP) in a large-scale network environment. CPP involves the challenge of deploying the optimal number of controllers within a network while meeting certain performance requirements considered conflicting in nature such as reliability, load balancing, latency, energy efficiency, and computation time. A single optimal or random placement may not be feasible in CPP and careful planning is of the essence to find an appropriate trade-off among the metrics. To achieve this, several CPP approaches have been proposed, developed, and deployed over the years, each having its unique objectives, strengths, and weaknesses. Therefore, this paper performed a comprehensive review of some of the existing approaches to identify the unique solutions offered, comprehend the different strategies and the challenges that exist as well as provide researchers with future directions aimed at improving the optimum location and allocation of controllers, in particular, for SDN application in wireless sensor network (WSN). The findings revealed several existing solutions and algorithms as well as several challenges such as the need for an efficient algorithm, attack-aware, cost-aware, and energy-aware CPP schemes while achieving a good quality of service.

Long Range Wide Area Networking (LoRaWAN) has established itself as one of the leading Media Access Control (MAC) layer protocols in the realm of Low Power Wide Area Networks (LPWAN). Although the technology itself is quite mature, the resource allocation mechanism, the Adaptive Data Rate (ADR) algorithm it uses is still quite new, unspecified and its functionalities still limited. Various studies have shown that the performance of the ADR algorithm gradually suffers in dense networks. As such, studies and proposals have been made as attempts to improve the algorithm. In this paper, the authors chose four proposed algorithms that focused on improving the ADR in terms of data extraction rate (DER) and evaluated them to study and critically analyze their performances. LoRaSim was used and the algorithms were employed in a simple sensing application that involved end devices transmitting data to the gateway every hour. The performances were measured based on how they affected DER as the network size increases. The results obtained show that the implemented algorithms outperformed the ADR algorithm. However, as network size increases, these superior performances are not adequate for a reliable and energy-efficient LoRaWAN network. Though attempts have been made to improve the ADR algorithm, arriving at its ideal implementation is still an open research area and therefore, we recommend more improvement should be proposed.

This paper introduces a hybrid mini-grid system based on the smart integration of isolated solar home systems. A novel algorithm has been proposed which prioritises photovoltaic supply over grid and diesel generator sources. The algorithm uses a Hidden Markov Model, global horizontal insolation data and Peukert's law to model and simulate two usage scenarios over a period of one year. It was found that even with erratic grid power supply, substantial cost savings can be achieved. These savings are dependent on the initial battery bank state of charge (SOC) amongst other variables, and can be improved if grid power supply becomes less erratic.

The Adaptive Data Rate (ADR) is used in LoRa WAnto ensure optimized data rates and transmission powers for static end devices. However, its implementation is still new, and therefore, its functionalities are limited. Multiple proposals have been made to help improve the ADR but an optimum solution is yet to be found. Therefore, this paper surveyed nine most relevant papers with the goal of identifying the ADR challenges and critically analyzing the solutions put forward to solve them. The critique of the solutions was based on the problems they solve, how they solve them, and the improvements they achieved. Findings show that the poorly designed ADR algorithm results in increased collisions and unfairness in collision probabilities amongst network traffic in LoRaWAN. Furthermore, the findings show that the studies surveyed had limitations in terms of the data rates investigated, the transmission parameters considered, and the region in which they were conducted. To help mitigate some of these challenges, few suggestions are presented in this paper.

Internet of things (IoT) is an innovative technology that has gained significant research attention in recent years and is still gaining momentum. This technology permits communication between humans and objects or objects with objects to collect and exchange data as well as provide essential services. However, despite the benefits and services it offers, it is faced with several challenges that are dominated by inefficient energy utilization due to nodes' continuous communication and other issues. This challenge affects all existing low power wide area network (LPWAN) technologies such as SigFox, LoRa, Narrow-band IoT (NB-IoT), and so on. Accordingly, several solutions have been offered to address the challenge but yet to achieve an optimum solution. Therefore, this paper conducted a review of existing approaches to minimize energy utilization and high latency during transmission in the NB-IoT and IoT in general. The essence is to comprehend the different techniques, challenges, and technologies used. The analysis revealed the existence of schemes/algorithms which are routing based, sleep/wake, and others. It also shows that NB-IoT is still faced with the challenge of an increase in latency and high energy consumption. Thus, there a need to address the challenge to boost the smooth operation of the technology.

Software-Defined Wireless Sensor Networks (SDWSN) has received significant attention in recent years due to its inherent challenges such as network security, trust management, inefficient energy consumption, and so on. In particular, inefficient energy utilization has remained a core critical challenge as sensor nodes are naturally resource constraint and mostly deployed in unattended environments. This challenge has a direct impact on SDWSN performance and reliability. Albeit, several techniques have been proposed and developed to address the challenge in the traditional WSN and few for SDWSN, optimal efficient energy utilization is yet to be achieved. Therefore, this paper survey some of the energy efficiency techniques reported in the literature. The goal is to gain insights into these techniques, strategies employed, their pros and cons which could be utilized to design an efficient-energy mechanism for SDWSN. The findings obtained show that the existing approach ensures efficient energy utilization and improve network performance. While some have routing protocol and security mechanisms, fault tolerance, and battery fault detector mechanisms are not incorporated.

Software Defined Networks (SDN) is a novel computing paradigm that decouples the control plane from the data plane. Its introduction has brought about great and innovative changes in the way the computer network is designed, managed, and operated. Currently, SDN architecture can be deployed with a single centralized controller or multiple controllers. However, deploying a single controller to manage a large area network such as wide area networks is ineffective and not ideal since network performance requirements and good quality of service can't be achieved. This challenge is solved by deploying multiple controllers to eliminate single-point-of-failure, controller overload, transmission delay, and so on. Despite these, multi-controllers deployments come with controller placement problem (CPP) and several approaches have been proposed and developed to address it. Therefore, this paper conducted a review of some of the CPP for SDN with a focus on capacitated and uncapacitated schemes. We analyzed the schemes, classified them, and provide few future research directions aimed at improving the CPP scheme.

In future wireless systems, intelligent capabilities are of utmost importance. To efficiently utilize resources, communication systems require knowledge of the prevalent situation in a frequency band through learning. To learn appropriately, it is critical for practitioners to select the right parameters in building learning models, use the appropriate algorithms and performance evaluation methods. In this paper, we evaluate the performance of some deep learning models compared to other machine learning methods, explore the different scenarios in which deep learning can be used for radio frequency (RF) monitoring, and evaluate performance in the various scenarios. Our work looks at the best practices and procedures for developing intelligent RF Learning. Specifically, we analysed over-the-air RF dataset collected from a USRP-based testbed to identify the number of interfering devices as a case study. From the obtained results, we discuss how Signal-to-Noise Ratio (SNR) selection for training affects the model performance as it relates to practical implementation of Deep Learning in communications systems.

In recent years, LoRaWAN has been considered as one of the commonest low power area network technologies and has gained much attention due to the rapid growth of Internet of Things (IoT) market and applications. Its communication is characterized by very low power consumption, low cost, extensive network coverage and so on. However, LoRaWAN is faced with scalability challenge, which has affected its adoption. This challenge has attracted several research attentions and is far from over. Therefore, this paper performed a review on existing works, about 13 papers on LoRa/LoRaWAN were reviewed focusing on several challenges and solution methods for IoT applications. The analysis shows that LoRaWAN is effective for IoT deployment and confirmed the existence of scalability challenge which is still an open issue. Moreover, scalability issue often give rise to other challenges such as network coverage, capacity, and interference.

Internet of Things (IoT) is one of the most promising technologies and has wide spread application areas in the information technology for future products and services. Developments in IoT have given rise to device proliferation which in turn increase IoT challenges such as security. One of the security challenges is the authentication of heterogeneous devices in the network. Due to the unique nature of these devices, traditional security schemes proposed and developed over the years have been rendered inept and infeasible for IoT application. However, several lightweight solutions have also been proposed for IoT application, but are far from being efficient. Therefore, this paper performed a review on some of these studies in order to comprehend the challenge, identify some of the approaches offered, and provide recommendations for future research. We reviewed about 9 articles and our analysis shows authentication is still an open issue in IoT and there is no generic approach to authenticate devices.

This paper presents a PSCAD simulation platform for studying reconfiguration methods applied to distribution systems and microgrids. The simulation model allows to manually operate the switches for reconfiguration and service restoration studies. It can also support Python-interfaced automatic switch control. Some performance metrics like unbalance factor and error calculations are introduced. The IEEE 123 node test system was implemented in the simulation platform in order to provide benchmarking results and to demonstrate the process of reconfiguration with dynamic stability considerations. Two case studies are presented. One is on reconfiguration for the purpose of restoration of an isolated section due to a fault and another on dynamic reconfiguration for the restoration of an autonomous microgrid. The PSCAD simulation platform can be extended to verify the control performance and optimization solutions of various distribution and microgrid applications.