Infrared-visible object detection aims to leverage the complementary information between infrared and visible modalities to improve detection performance in challenging environments. However, existing infrared-visible object detection methods face several limitations: (1) difficulty in effectively extracting and decomposing modality-common and modality-specific features; (2) interference from modality-irrelevant or redundant information; and (3) insufficient fusion of cross-modal complementary cues. To address these issues, we propose a novel Modality Decomposition and Compensation Fusion Network (MDCF-Net). Specifically, MDCF-Net first decomposes the common and unique features across different modalities. It then performs selective enhancement and interaction between these features via cross-modality compensation. Finally, a dynamic fusion strategy based on spatial and channel attention is applied to adaptively integrate the enhanced features. Extensive experiments on two public datasets, LLVIP and FLIR, demonstrate that our proposed method achieves superior detection performance and exhibits robust generalisation across various challenging conditions. The Code is available at https://github.com/fanjiangtao666/MDCF-Net/tree/main

To mitigate various challenges in the edge-cloud ecosystem, such as global monitoring, flow control, and policy modification of legacy networking paradigms, software-defined networks (SDN) have evolved as a major technology. However, the dependency on a single centralized controller is challenging due to the scalability and resilience issues. Thus, deploying multiple controllers becomes inevitable to process the data with maximum throughput and minimum delay. Controller placement problem (CPP) is a major issue that needs to be addressed by designing efficient solutions. To address the CPP, two parameters, i) number of controllers and ii) location of controllers, need to be handled optimally. Thus, an Optimal COntroller Placement Scheme (COPS) using the multi-objective evolutionary approach for SDN is proposed in this paper. The results prove its effectiveness in terms of various evaluation parameters.

6G applications rely on data-intensive AI models for network optimization. These demand a scalable and energyefficient framework to handle massive device networks with stringent latency requirements which current solutions struggle to support. Although reinforcement learning (RL) and split learning have matured to provide commercial solutions elsewhere. Current solutions in 6G have not used them systematically to achieve the sustainability goals. In this paper, we propose a three-layer framework that minimizes energy consumption of the communication system capable of handling large number of devices. The proposed solution uses RL agents at the edge layer to mathematically model the system and communicate to fog layer for aggregation. The aggregated feature maps are further communicated to cloud layer for global model training. We use split learning for communication and training, the learning at each device are communicated for global model creation effectively. Each edge device improves the overall RL model where system matures quickly consuming minimal energy. The proposed framework's efficacy has been tested extensively for accuracy and scalability, in terms of energy consumption, latency and memory utilizations. The simulation results validate the claims of maturity in models across edge, fog and cloud levels.

With the widespread adoption of Healthcare Internet of Things devices, the need for effective intrusion and anomaly detection has become pivotal in ensuring network security. However, the optimization of machine learning (ML) and deep learning models for these detection tasks frequently necessitates extensive computational resources, adversely affecting both temporal and energy efficiency. This paper introduces an AutoML framework specifically tailored to enhance anomaly detection models, with a strategic focus on energy efficiency throughout the optimization process. The process commences with data preprocessing, followed by feature selection employing a combination of Recursive Feature Elimination and SHapley Additive exPlanations to identify important features for anomaly detection. Subsequently, a baseline Multilayer Perceptron neural network model is trained, and hyperparameter optimization is executed within a constrained search space to mitigate energy consumption. The framework produces optimized models, which are assessed based on accuracy and energy consumption at various checkpoints, with the models demonstrating inferior performance systematically excluded based on predefined accuracy or energy consumption objectives. Experimental outcomes reveal that the pipeline effectively balances detection performance with energy consumption, with certain cases showing minimal accuracy losses (less than 1%) accompanied by substantial energy savings (over 60%), presenting a sustainable and resource-efficient approach to anomaly detection within IoT systems.

Edge computing improves the Internet of Vehicles (IoV) by offloading heavy computations from in-vehicle devices to high-capacity edge servers, typically roadside units (RSUs), to ensure rapid response times for intensive and latency-sensitive tasks. However, maintaining Quality of Service (QoS) remains challenging in dense urban settings and remote areas with limited infrastructure. To address this, we propose an software-defined networking (SDN)-driven model for uncrewed aerial vehicle (UAV)-assisted vehicular edge computing (VEC), integrating RSUs and UAVs to provide computing services and gather global network data via an SDN controller. UAVs serve as adaptable platforms for mobile-edge computing (MEC), filling gaps left by traditional MEC frameworks in areas with high vehicle density or sparse network resources. An optimal offloading mechanism, designed to minimize the Age of Information (AoI) while balancing energy consumption and rental costs, is implemented through a soft actor-critic (SAC)-based algorithm that jointly optimizes UAV trajectory, user association, and offloading decisions. Experimental results demonstrate the model’s superior performance, achieving up to 87.2% energy savings in energy-limited settings and a 50% reduction in time-sensitive scenarios, consistently outperforming traditional strategies across various task sizes.

Network slicing enables 5G/6G networks to support ultrareliable low-latency communication (URLLC), enhanced mobile broadband (eMBB), and massive machine-type communication (mMTC). However, while this virtual networking technology enhances network efficiency, it also adds substantial signaling overhead. Maintaining submillisecond latency and managing dense deployments require continuous signaling at high resolution, which keeps hardware components active, leading to increased energy consumption. In this article, we introduce a novel network controller that manages slice congestion and admission, designed to meet flexible Quality-of-Experience requirements for both priority and nonpriority traffic. Utilizing metadata from Internet of Things (IoT) device applications and network characteristics, we introduce adaptability and elasticity features, enabled by transfer and reinforcement learning, significantly lowering signaling overhead and network resources. Further, analytical results show the proposed framework effectively reduces rejection rates and congestions across varying mMTC and eMBB traffic loads.

In healthcare IoT networks, network anomalies can disrupt the flow of reliable data, potentially compromising healthcare data’s security and integrity. To address this challenge, several anomaly detection methods have been developed using artificial intelligence (AI) algorithms. However, finding an optimal AI model with the best tuning parameters for effective anomaly detection is a time-consuming and resource-intensive task. To address this issue, we propose an Automated AI (AutoAI) approach to optimize the tuning of hyperparameters in healthcare data anomaly detection. By leveraging the power of AutoAI, our goal is to streamline the anomaly detection process, making it more accurate and efficient. Our method is designed to adapt dynamically to the ever-changing nature of healthcare data, ensuring robustness against emerging anomalies. The proposed AutoAI method was validated in a realistic scenario and the outcomes depict the superiority of the proposed approach as compared to existing schemes on various performance evaluation metrics.

Integration of the Internet of Things (IoT), intelligent sensor networks, and patient-centric modules has successfully revitalized the way we pursue healthcare services. Seamless online doctor-patient communication facilities have vanished the partial line between traditional physical on-site treatment and current remote monitoring. In the Healthcare 4.0 environment, patients can connect with doctors via video conference, send audio transcripts as responses, and share pictorial or text-based vital information. One of the major concerns related to remote healthcare treatment applications is the efficient utilization of networks for data transmission. To mitigate this paramount challenge, we propose SDN care. It is a Deep Learning(DL)-based SDN-enabled network classification approach to facilitate seamless and secured communication between doctors and patients in the Healthcare 4.0 ecosystem. SDN care relies on one-dimensional Convolutional Neural Network (CNN) architecture to efficiently classify the type of data under communication and make adjustments in SDN parameters. The latency, bandwidth, jitter, etc., are adjusted based on prediction from the CNN model for effective utilization. Proposed SDN-care is further compared with Artificial Neural Network (ANN), and it also has been examined using different types of optimizers. The performance evaluation of SDN-care has been done through various metrics such as accuracy, loss convergence, precision, recall, f1 score, Receiver Operating Characteristic (ROC) curve, precision-recall trade-off curve and compared with different optimizers such as Adam, SGD, RMSprop, and Adadelta. Thus, SDN care introduces significant advancements in SDN-enabled remote patient-doctor communication environments using various modes of data exchange.

Monitoring in-bed pose estimation based on the Internet of Medical Things (IoMT) and ambient technology has a significant impact on many applications such as sleep-related disorders including obstructive sleep apnea syndrome, assessment of sleep quality, and health risk of pressure ulcers. In this research, a new multimodal in-bed pose estimation has been proposed using a deep learning framework. The Simultaneously-collected multimodal Lying Pose (SLP) dataset has been used for performance evaluation of the proposed framework where two modalities including long wave infrared (LWIR) and depth images are used to train the proposed model. The main contribution of this research is the feature fusion network and the use of a generative model to generate RGB images having similar poses to other modalities (LWIR/depth). The inclusion of a generative model helps to improve the overall accuracy of the pose estimation algorithm. Moreover, the method can be generalized for situations to recover human pose both in home and hospital settings under various cover thickness levels. The proposed model is compared with other fusion-based models and shows an improved performance of 97.8% at PCKh @0.5. In addition, performance has been evaluated for different cover conditions, and under home and hospital environments which present improvements using our proposed model.

Localization is an important issue for Internet of Underwater Things (IoUT) since the performance of a large number of underwater applications highly relies on the position information of underwater sensors. In this paper, we propose a hybrid localization approach based on angle-of-arrival (AoA) and received signal strength (RSS) for IoUT. We consider a smart fishing scenario in which using the proposed approach fishers can find fishes’ locations effectively. The proposed method collects the RSS observation and estimates the AoA based on error variance. To have a more realistic deployment, we assume that the perfect noise information is not available. Thus, a minimax approach is provided in order to optimize the worst-case performance and enhance the estimation accuracy under the unknown parameters. Furthermore, we analyze the mismatch of the proposed estimator using mean-square error (MSE). We then develop semidefinite programming (SDP) based method which relaxes the non-convex constraints into the convex constraints to solve the localization problem in an efficient way. Finally, the Cramer–Rao lower bounds (CRLBs) are derived to bound the performance of the RSS-based estimator. In comparison with other localization schemes, the proposed method increases localization accuracy by more than 13%. Our method can localize 96% of sensor nodes with less than 5% positioning error when there exist 25% anchors.

Financial Technology have revolutionized the delivery and usage of the autonomous operations and processes to improve the financial services. However, the massive amount of data (often called as big data) generated seamlessly across different geographic locations can end up as a bottleneck for the underlying network infrastructure. To mitigate this challenge, software-defined network (SDN) has been leveraged in the proposed approach to provide scalability and resilience in multicontroller environment. However, in case if one of these controllers fail or cannot work as per desired requirements, then either the network load of that controller has to be migrated to another suitable controller or it has to be divided or balanced among other available controllers. For this purpose, the proposed approach provides an adaptive recovery mechanism in a multicontroller SDN setup using support vector machine-based classification approach. The proposed work defines a recovery pool based on the three vital parameters, reliability, energy, and latency. A utility matrix is then computed based on these parameters, on the basis of which the recovery controllers are selected. The results obtained prove that it is able to perform well in terms of considered evaluation parameters.

With the increasing number of Internet of Things (IoT) devices being deployed and used in daily life, the load on computational devices has grown exponentially. This situation is more prevalent in smart cities where such devices are used for autonomous control and monitoring. Smart cities have different kinds of applications that are aided through IoT devices that collect data, send it to computational processing and storage devices, and get back decisions or actuate the actions based on the input data. There has been a stringent requirement to reduce the end-to-end delay in this process owing to the remote deployment of cloud data centres. This eventually led to the revolution of edge computing, wherein nano–micro-processing devices can be deployed closer to the premises of the smart application and process the data generated with a lower turnaround time. However, due to the limited computational power and storage, controlling the workload diverted to the edge devices has been challenging. The workload scheduling policies and task allocation schemes often fail to consider the run time health of the edge devices due to a lack of proper monitoring infrastructure. Thus, in this article, we proposed a health monitoring and diagnosis framework for geo-distributed edge clusters processing big data generated by smart city applications. This framework is built over the Map-Reduce approach for distributed processing of big data on edge clusters deployed across the smart city. Within this framework, SmartMonit (a monitoring agent) is deployed that collects the health statistics of edge devices and predicts the potential failures using an artificial neural network-based self-organising maps approach. The proposed framework is deployed over different clusters to test the efficacy concerning failure detection.

Due to the extremely important role of data in the industrial Internet of Things (IIoT) network, trust and security of data are among the major concerns. In this article, we develop a cloud-integrated 5G-IIoT network architecture enabled by a three-party authenticated key exchange (AKE) protocol with privacy-preserving to secure data exchanged via wireless communication, cope with unauthorized entities, and ensure data integrity. Moreover, we develop a trust model based on the Dempster–Shafer theory to check the trustworthiness of data collected by smart devices/sensor nodes. Security analysis performed on our scheme demonstrates that it can withstand different well known attacks in the IIoT environment. We also analyzed the validity of our scheme by using the automated validation of internet security protocols and applications tool. Additionally, the performance evaluation and experimental results prove the effectiveness of the proposed scheme compared to the existing works in terms of accuracy, delay, trust, and throughput.

In real-time medical monitoring systems, given the significance of medical data and disease symptoms, a secure and always-on connection with the medical centre over the public channels is essential. To this end, an edge-enabled Internet of Medical Things (IoMT) scheme is designed to improve flexibility and scalability of the network and provide seamless connectivity with minimum latency. The entities involved in such network are vulnerable to various attacks and can potentially be compromised. To address this issue, an authentication scheme comprised of digital signature and Authenticated Key Exchange (AKE) protocol is proposed which guarantees only authorized entities get access to the services available in the medical system. Moreover, to fulfill the privacy-preserving, each entity is mapped to a different pseudo-identity. The non-mathematical and performance analysis show that the proposed scheme is robust against various attacks such as impersonation and replay attacks.

Although modern Maritime Transportation Systems (MTS) have been extensively benefited from Internet of Things (IoT) technology, but still the risks and challenges in safety and reliability have increased substantially. The involvement of different maritime parties in the marine transportation flow scheduling and management further escalates these challenges. Thus, we need an IoT-based collaborative processing system that unifies the modular structure and integrates multiple modules involved in MTS. Moreover, the need for a shared and controlled access mechanism that cannot be manipulated or tampered by unauthorized parties is also essential requirement in MTS. Blockchain, as an emerging technology, has become a key tool in data security protection because of its non-tampering and non-forgery characteristics. Keeping in view of this aspect, in this paper, an IoT-based collaborative processing system based on blockchain is proposed for marine transportation flow scheduling and management. In addition, we propose a novel consensus mechanism based on Verifiable Random Function (VRF) and reputation voting to reduce the communication cost in blockchain consensus communication process. The proposed scheme has been validated in a simulated environment and the results illustrate that the scheme has obvious effect in resisting replay attack and camouflage attack. Furthermore, the optimized consensus mechanism improves the security by 8% and the transaction processing speed by 6% on the premise that the communication cost is basically unchanged.

The global escalation in the road traffic density alleviates the harmful emissions and fuel bills due to congestion and misaligned traffic control. The conventional traffic monitoring schemes (camera or sensor-based) are not able to cover every nook and corner and thus miss various vital traffic parameters that can otherwise be very useful for traffic density and pattern analysis. Internet of Drones (IoD) has been widely adopted to resolve various related challenges and has strong potential in traffic monitoring even in the areas where scarcity of fixed infrastructure is witnessed. Thus, in this paper, we have proposed an IoD-based traffic monitoring system to avoid the congestion on the roads within the available infrastructure. Moreover, to deal with the dynamic network typologies, an software-defined networking (SDN)-based centralized controller is configured to generate the flow rules for end to end data transmission. However, the drones communicate with each other through an open channel (now controlled through a programmable SDN architecture). Thus, the integrity of data collected by drones must be protected through a robust security mechanism. So, we have adopted a blockchain technology to secure the proposed system against unauthorised access and maintain data integrity. However, maintaining the entire blockchain on the drones can lead to several resource bottlenecks. Thus, we have used a referenced blockchain architecture that decouples the data from the blockchain part and stores it in the off-chain. The proposed scheme has been validated using simulated environments that validates its the superiority in contrast to the existing variants.

Security and privacy of data-in-transit are critical issues in Industry 4.0, which are further amplified by the use of faster communication technologies such as 6G. Along with security issues, computation and communication costs, as well as data confidentiality, must be also accommodated. In this article, we design a cybertwin-based cloud-centric network architecture to improve the flexibility and scalability of 6G industrial networks. Cybertwin not only enables the deployment of advanced security solutions but also provides an always-on connection. However, the security of data-in-transit over wireless communication between users/things and cybertwin remains a concern. Hence, a privacy-preserving authentication scheme based on digital signature and authenticated key exchange protocol is designed to address the security concerns of data exchanged. In addition, we conduct a security analysis that proves that the scheme resists several attacks in the Industry 4.0 environment. Moreover, the evaluation performed confirmed the superiority of the proposed work comparing to the existing works.

Growing population and migration to cities have given birth to multiple urban issues. Traffic congestion is one of the most prominent ones with severe side effects like fuel wastage, loss of lives, and slow productivity. The traditional traffic control system deploys programming logic control (PLC) which uses round-robin scheduling algorithm. However, few recent works have proposed IoT-based framework which requires the deployment of a series of sensors. In this paper, we propose an IoT-based framework that uses the existing network of CCTV cameras at the junction. An edge device is used to estimate the traffic density and detect emergency vehicles using YOLO v3 -Efficient Net. These two parameters are used as an input to a novel traffic control algorithm. The performance of the proposed framework has been evaluated by analyzing its properties using the UA-DETRAC dataset. The proposed framework achieves 68.10% vehicle detection accuracy.

The in-house health monitoring sensors form a large network of Internet of things (IoT) that continuously monitors and sends the data to the nearby devices or server. However, the connectivity of these IoT-based sensors with different entities leads to security loopholes wherein the adversary can exploit the vulnerabilities due to the openness of the data. This is a major concern especially in the healthcare sector where the change in data values from sensors can change the course of diagnosis which can cause severe health issues. Therefore, in order to prevent the data tempering and preserve the privacy of patients, we present a decoupled blockchain-based approach in the edge-envisioned ecosystem. This approach leverages the nearby edge devices to create the decoupled blocks in blockchain so as to securely transmit the healthcare data from sensors to the edge nodes. The edge nodes then transmit and store the data at the cloud using the incremental tensor-based scheme. This helps to reduce the data duplication of the huge amount of data transmitted in the large IoT healthcare network. The results show the effectiveness of the proposed approach in terms of the block preparation time, header generation time, tensor reduction ratio, and approximation error.

With the growth in the Internet of things (IoT) paradigm, there has been a tremendous makeshift in how the distributed devices work to achieve a common goal. However, it remains essential that all these devices work in a coherent manner to perform a collective action. This makes the task of resource provisioning extremely important in such a paradigm. The end-user level in IoT mostly comprises of low computation and communication powered devices. Improper utilization of the available resources in such a scenario burdens the complete system and degrades the quality of service. In such a scenario, the use of cloud computing techniques can help to manage the resources effectively. More so, with the emergence of relatively newer cloud-based technologies such as edge and fog computing, resource management in the IoT has become far more effective. These technologies bring the computation and communication capabilities closer to the IoT devices where some of the services can be offloaded to the edge devices. These devices are called IoT edge devices and they provide a unique opportunity to tackle some of the existing and pertinent issues for resource management in IoT paradigms; yet at the same time, they face their own set of challenges. However, the use of IoT edge devices in a traditional IoT paradigm results in better utilization of the available resources as well as improving the overall quality of service. Keeping this in mind, this special issue addressed some of the aspects related to resource management in IoT edge devices with the focus on various challenges faced, and potential techniques and solutions to address such challenges by leveraging IoT edge devices. We received numerous submissions in the issue, and we accepted 13 high-quality submissions for publication as a result after following a rigorous review process. Each of the accepted papers is summarized as follows. In the first paper, Khan et al.1 presented "A cache-based approach toward improved scheduling in fog computing" for efficient resource allocation in the fog computing environment, while maintaining the quality of service. The authors use first-in first-out scheme to place the jobs in queue and cache the job type, fog server, arrival time, time to leave, and internal processing time. The jobs are then moved from the queue by the fog broker which selects fog server having sufficient required power and resources to execute the job. The authors' proposed cache-based scheme showed promising results in terms of reducing the execution time, latency, processing delays and power consumption as compared to the conventional first-come-first-serve and shortest job first policies. The second paper on "Extensive review of cloud resource management techniques in industry 4.0: Issue and challenges" by Dewangan et al.2 sheds light on various types of resource provisioning schemes and classified those into different categories (to help understand them better) on the basis of the underlying technique and their overall objective. This survey helps to understand the optimal schemes for catering to different performance metrics such as time, cost, energy, service level of agreement rate, power consumption, resource utilization, etc. Moreover, the authors also highlighted some of the current research challenges in the domain of resource management. The next paper, "An energy efficient and low overhead fault mitigation technique for internet of thing edge devices reliable on-chip communication" by Ibrahim et al.3 presents a coding scheme to make the network-on-chip fault-tolerant. The network-on-chip provides communication backbone in the underlying network for which the proposed scheme handled both single and multibit adjacent bit errors. The next paper in this issue is on "Design and data analytics of electronic human resource management activities through Internet of Things in an organization" by Nasar et al.4 The authors focus on designing a data analytical human resource management system for IoT devices in an organization for ensuring the policies, strategies, and practices within the organization. The activities covered under this improved system include e-recruitment, e-Selection, e-performance management, e-learning, and e-compensation and the performance of the system was validated on four Kaggle databases. In the fifth paper on "A Mobile Data Offloading Framework based on a Combination of Blockchain and Virtual Voting", Hassija et al.5 enable mobile users to offload computation tasks to resource-rich mobile-devices in order to reduce energy consumption and enhance performance. The authors used directed acyclic graphs (DAGs) for mobile offloading algorithm where the users can securely submit a transaction (powered by blockchain) request for task offloading a DAG, while a game-theoretic scheme was employed in order to model the interactions between various mobile devices for bargaining cost and time. The sixth paper by Lu is on "Security of Internet of Things edge devices".6 The paper focuses on securing the edge nodes and edge gateways in IoT to meet its future security needs to eliminate the data leakage risk. The edge nodes were optimized by using a cache replacement algorithm, namely Max-PSN and the results illustrate that the proposed mechanism performed superiorly to the lead frequently used and least recently used algorithms with respect to the hit rate and average response speed of centralized and distributed systems. In the seventh paper, Balasubramanian and Jolfaei present "A scalable framework for healthcare monitoring application using the Internet of Medical Things".7 The authors made use of IoT for providing real-time alarm and assistance in order to ease the activities of pregnant women by merging the advantages of event-driven and assistive care loop framework architecture. In the next paper, Bodkhe and Tanwar shed some light on "Secure data dissemination techniques for IoT applications: Research challenges and opportunities".8 As the name suggests, the authors presented a comprehensive summary of secure data dissemination schemes present in the existing literature for IoT applications along with their potential research issues and possible countermeasures. The majority of the researched literature in this survey covers the Internet of Vehicles, Internet of Drones, and Internet of Battlefield things with respective open issues and challenges of each of these. As countermeasures, the authors researched opportunities in the directions of the requirement of secure dissemination protocols, efficient data aggregation methods, and cluster-based data dissemination. The ninth paper on "Comparative study of support vector machines and random forests machine learning algorithms on credit operation" by Teles et al.9 compares the support vector machine (SVM) and random forest (RF) scheme for their application to predict financial risks on credit operation. The outcomes of this paper suggest that while both can be effectively used for the specified task, RF has an advantage of the speed and operational simplicity over SVM; while SVM has the benefit of higher classification accuracy. The tenth paper presented by Zhao et al. titled "Message-Sensing Classified Transmission Scheme Based on Mobile Edge Computing in the Internet of Vehicles".10 The authors make use of mobile edge computing for secure message transmission by prioritizing secure messages using the analytic hierarchy process to guarantee a higher transmission level for urgent messages. Moreover, using the Lagrangian relaxation method, an optimal task offloading model was devised for delay and energy loss by assigning different weight factors to these parameters. The next paper is "FPFTS: A Joint Fuzzy PSO Mobility-aware Approach to Fog Task Scheduling Algorithm for IoT Devices" by Javanmardi et al.11 The authors build a fog task scheduler leveraging the particle swarm optimization along with fuzzy theory to assign tasks of the users to fog devices. The proposed task schedular was tested on iFogSim simulator and results show that it outperformed first-come-first-serve and delay-priority algorithms with respect to delay and network utilization. Zhang et al.,12 in their paper "Service offloading oriented edge server placement in smart farming" made use of the edge resources to support the real-time intelligent controls in smart farming. The authors presented a service offloading oriented architecture for reducing delay in data transmission from sensors to the edge servers while balancing the load on the servers and optimizing the energy consumption. The final accepted paper in this special issue is on "A metaheuristic optimization approach for energy efficiency in the IoT networks" by Iwendi et al.13 The authors proposed a hybrid metaheuristic algorithm, namely, WOA-SA, for optimizing the energy consumption of the sensors in IoT-based wireless sensor networks. The two metaheuristic approaches, namely, whale optimization algorithm and simulated annealing for choosing the cluster heads in order to optimize the energy consumption in the network. The proposed approach was found to be more effective than its counterparts in terms of load, temperature, residual energy, and cost function. We sincerely hope that after reading the accepted contributions in this special issue would help the readers of the journal and a wider research community to gain knowledge on the presented research challenges, techniques and solutions, and encourage them to further work on different aspects of resource management in IoT devices. We thank the editor-in-chief and editorial board members for providing us with the opportunity to conduct a special issue in Software: Practice and Experience. We also like to thank the administrative staff, reviewers and most importantly, the authors, for their help and contributions in successful organization of this issue.

The penetration of electric vehicles (EVs) embedded with information and communication technology (ICT) devices and tools form a huge connected network that can be viewed as Internet-of-EVs(IoEV). The huge data gathered in IoEV network needs to be processed at cloud-based infrastructure which has abundant resources. However, due to the high mobility of the EVs, resource management from the remote cloud service providers has become one of the most difficult tasks to be performed in this environment. In this regard, data analytics fused with fog or edge computing can be leveraged to increase the resource availability in V2G environment where resources are provided to the EVs on the edge of the network. Keeping these points in mind, this paper presents a new framework for integration of cloud computing and IoEV on the edge of the network which provides flexibility to the end users for smooth execution of various applications. In addition, a resource allocation and job scheduling strategy for EVs at the edge of the network is presented in the paper. The results obtained with respect to various performance metrics confirm the applicability of the proposed scheme for future applications in V2G scenario.

Distributed Renewable Energy Sources (DRES) are considered as instrumental within modern smart grids and more broadly to the various ancillary services contained within the energy trading market. Thus, the adequate power production profiling and forecasting of DRES deployments is of vital importance such as to support various grid optimisation and accounting processes. The variety of DRES in stallation companies in conjunction with the diversity of ownership on DRES machinery, controller firmware and Supervisory Control and Data Acquisition (SCADA) software leads to cases where centralised SCADA measurements are not entirely available or are provided under a subscription-based model. In this work, we consider this pragmatic scenario and introduce a SCADA-agnostic approach that utilises freely available weather measurements for explicitly profiling and forecasting power generation as produced in real wind turbine deployments. For this purpose, we leverage various machine learning (ML) libraries to demonstrate the applicability of our system and further compare it with forecasting outputs obtained when using SCADA measurements. Through this study, we demonstrate a viable and exogenous profiling solution achieving similar accuracy with SCADA-based schemes under much lower computational costs.

With advances in fog and edge computing, various problems such as data processing for large Internet of Things (IoT) systems can be solved in an efficient manner. One such problem for the next generation smart grid (SG) IoT system comprising of millions of smart devices is the data aggregation problem. Traditional data aggregation schemes for SGs incur high computation and communication costs, and in recent years, there have been efforts to leverage fog computing with SGs to overcome these limitations. In this article, a new fog-enabled privacy-preserving data aggregation scheme (FESDA) is proposed. Unlike existing schemes, the proposed scheme is resilient to false data injection attacks by filtering out the inserted values from external attackers. To achieve privacy, a modified version of the Paillier cryptosystem is used to encrypt the consumption data of the smart meter (SM) users. In addition, FESDA is fault-tolerant, which means, the collection of data from other devices will not be affected even if some of the SMs malfunction. We evaluate its performance along with three other competing schemes in terms of aggregation, decryption, and communication costs. The findings demonstrate that FESDA reduces the communication cost by 50%, when compared with the privacy-preserving fog-enabled data aggregation scheme.

The ever-growing demand for electricity in the residential sector results in creating a severe burden on electric grids. However, with the emergence of smart homes (SHs) and smart grids (SGs), this burden can be reduced to some extent. To address this issue, we propose an energy management system in this paper which manages the power requirements of SHs automatically according to the utility constraints and user priorities. The proposed system is based on a heuristic technique, which considers the user's priority and power available from the grid as well as distributed energy resources for scheduling of appliances. It works by dividing the appliance scheduling problem in an SH into subproblems for different time slots. Then, a heuristic solution is designed for each subproblem. The instantaneous load demands are handled in real time to comply with the available power from the grid/utility. The data from different SHs is gathered to test the performance of the proposed scheme in real time. Results show that the proposed scheme efficiently manages the load demand of the SH with respect to power available from the utility, battery energy storage system, and user preferences.

Smart grid (SG) is an emerging technology which provides many services to the end users and utilities, such as load management, frequency regulation, and grid stability. Although many solutions exist to provide these services in a secure manner, but these solutions are not adequate keeping in view of the heavy cryptographic primitives execution on these devices. Hence, in this article, GUARDIAN, a blockchain-based secure demand response management scheme is presented so as to take energy trading decisions securely for managing the overall load of residential, commercial, and industrial sectors. In GUARDIAN, the miner nodes, which are block verifiers, are selected using their power consumption and processing power. These nodes are responsible for authenticating the energy transactions in SG. The energy transaction is initialized by an end user which creates the block of transaction to trade the energy. The miner nodes then validate these blocks and adds these in the blockchain. The successful energy trade occurs only for the blocks which are in the blockchain. The proposed scheme is lightweight in terms of communication and computation costs. Moreover, the results obtained demonstrate the effectiveness of proposed scheme for secure demand response management in the SG.

Distributed Renewable Energy Sources (DRESs) such as wind and solar are becoming a promising alternative for the energy supply in modern (smart) electricity grids as part of future sustainable smart cities. Successful integration of DRESs requires efficient, resilient, and secure communication in order to satisfy the highly challenging and real-time constraints of smart city applications. Regardless of the various research solutions proposed in this context within the last decade, the relevant standardization is a non-trivial issue and is still in its infancy. In this position paper, we briefly review the currently employed DRES communications standards and identify the gaps in their present status. Finally, we discuss and suggest potential pathways for further improvement.

Nowadays, the conventional healthcare domain has witnessed a paradigm shift towards patient-driven healthcare 4.0 ecosystem. In this direction, healthcare recommender systems provide ubiquitous healthcare services to the end users even on the move. However, there are various challenges for the design of patient driven healthcare recommender systems. Some of the major challenges are: a) handling huge amount of data generated by smart devices and sensors, b) dynamic network management for real-time data transmission, and c) lack of knowledge gathering and aggregation methods. For these reasons, in this paper; DLRS: A Deep Learning based Recommender System using software defined networking (SDN) is designed for smart healthcare ecosystem. DLSR works in the following phases: a) a tensor-based dimensionality reduction algorithm is proposed for removing unwanted dimensions in the acquired data, b) a decision tree-based classification scheme is presented for categorization of the patient queries on the basis of different diseases, and c) a convolutional neural network based system is designed for providing recommendations about the patient health. On evaluation, the results obtained prove the superiority of the proposed scheme in contrast to existing competing schemes.

Security has become one of major concern especially in critical applications like e-healthcare. To cater to the security needs in e-healthcare, this paper proposes a novel scheme which prevents data from unauthorized fabrication and preserves the integrity of data. The proposed scheme also removes overhead of integrity validation from user's end as this work is assigned to a trusted third party, i.e., a proxy server. For this purpose, the patient's data given by user is sent to proxy server along with user's signature where it is broken down in the form of blocks. A `tag' is then generated for each block using lightweight elliptic curve cryptography (ECC). This block-tag pair is then uploaded on the data server which is used for integrity checking. Whenever a patient's data access request is raised, the block of data is retrieved using tag value and integrity is then verified. In addition to it, a lightweight lattice-based authentication scheme is proposed in the paper to authenticate the users. The request is served only when the user is deemed authentic and there is no modification in the original data sent by the user. The effectiveness of the proposed authentication scheme has been proven by performing its analysis in terms of computation time and communication cost. Moreover, the superiority of the proposed data integrity scheme has been validated by comparing it with the traditional discrete logarithmic scheme.

Vehicular ad-hoc networks (VANET) have been used in many application and services ranging from intelligent transportation to e-healthcare. However, in VANET, one of the major challenges is the cluster head (CH) selection as it influences vehicle mobility, transmission range, and inter-vehicle distance. However, for stable cluster formation in VANET, it is essential that these constraints must be considered while selecting the CH. However, with an increase in the number of nodes in a cluster, the existing CH selection schemes become inefficient which leads to a substantial increase in the execution time for aforementioned applications. Hence, to address this issue, a rough set-based scheme is presented in this paper for CH selection with an aim to reduce the CH selection time. To achieve this aim, the concept of cluster member fields (which represents similar nodes) has been used which reduces the number of nodes participating in the CH selection. The proposed scheme has been evaluated with respect to various performance metrics such as CH selection time and CH reliability (on the basis of vehicle density and average velocity of vehicles in the clusters). The results obtained confirm that the CH selection time in the proposed scheme is less and CH reliability in more as compared with an existing scheme.

Demand response management in smart cities is one of the most challenging tasks to be performed due to the continuous changes in the load profile of the home users. The existing proposals in the literature fail to observe the hidden patterns in the load profile of these users. So, to fill these gaps, the concept of deep learning has been used in this paper for smart energy management in a smart city. The consumption data from smart homes (SHs) is gathered and taken as an input to the deep learning model, convolution neural network (CNN). The CNN model learns the hidden patterns in the data and outputs different load curves. These load curves are then used to train a support vector regression (SVR) model, which predicts the overall load consumption of all SHs in the smart city. This prediction is then compared with the power generation from the grid and consequently the demand response (DR) of the connected SHs is managed so as to minimize the gap between predicted demand and supply. The proposed scheme has been evaluated on the dataset collected from PJM and open energy information with respect to load demand prediction and DR management. The results obtained prove the efficacy of the proposed scheme. The prediction errors, i.e., root mean squared error and mean absolute percentage error are observed less in comparison to the cases when CNN and SVR are used individually.

In a multi-cloud environment, consumers can access multiple cloud services using a single heterogeneous computing architecture. In such an environment, multiple instances of the same cloud service and its component may be geographically dispersed. So, cloud service broker (CSB) exploits the heterogeneity of multi-cloud environment to provide high performance at a low price to its consumers. The consumer tasks are allocated to the geo-dispersed cloud service components for execution of various services. For this purpose, an optimal service components identification and task allocation are major concerns keeping in view of the heterogeneity in multi-cloud environment. For this purpose, a scheduling algorithm, which takes care of location, price, and performance is required. Therefore, in this paper, SLOPE: A Self Learning Optimization and Prediction Ensembler for Task Scheduling in Multi-cloud Environment is proposed. SLOPE works in two phases, 1) In first phase, Bayes theorem is used to design a self-learning algorithm, to compute the conditional probability (strength) of each service component in order to select the probable rule string, and 2) a roulette wheel method is used to select an optimal scheduling policy for a given service request. SLOPE helps to identify the best possible service component from the pool of resources on the basis of dynamic factors and then schedule a service request to the selected component. Unlike most of the other existing approaches, SLOPE builds an efficient schedule for service selection. Experimental results demonstrate that SLOPE performs better in comparison to other competing schemes of its category.

Energy management in commercial buildings is a challenging task due to their specific set of requirements. One such building that has not been fully investigated in the literature to provide energy efficiency is a university building. There are many challenges associated while managing the energy of a university building, such as-scheduling of classes, availability of faculty, and capacity of classrooms. To address these challenges for providing better energy efficiency, an efficient heating, ventilation, and air-conditioning (HVAC) management scheme for a university building is presented in this paper. The HVAC loads are chosen as these are more flexible in the classrooms than other loads, such as-lighting and projectors. In this paper, the HVAC energy management problem is formulated as a mixed-integer linear programming (MILP) problem. To solve this problem, a heuristic-based algorithm is proposed, which optimally minimizes the use of HVAC without affecting user comfort. Moreover, it also minimizes the cost of rescheduling the classes on a given day. The results obtained on the dataset traces taken from a university building clearly indicate that the proposed scheme reduces the energy demand of HVAC systems by 19.75% for an entire week without affecting the user comfort. Moreover, this scheme shows superior performance when compared with existing commercial demand response management schemes with respect to load reduction and cost savings.

With advancements in information and communication technology, there is a steep increase in the remote healthcare applications in which patients can get treatment from the remote places also. The data collected about the patients by remote healthcare applications constitute big data because it varies with volume, velocity, variety, veracity, and value. To process such a large collection of heterogeneous data is one of the biggest challenges which requires a specialized approach. To address this challenge, a new fuzzy rule based classifier is presented in this paper with an aim to provide Healthcare-as-a-Service. The proposed scheme is based upon the initial cluster formation, retrieval, and processing of the big data in cloud environment. Then, a fuzzy rule based classifier is designed for efficient decision making for data classification in the proposed scheme. To perform inferencing from the collected data, membership functions are designed for fuzzification and defuzzification processes. The proposed scheme is evaluated on various evaluation metrics, such as average response time, accuracy, computation cost, classification time, and false positive ratio. The results obtained confirm the effectiveness of the proposed scheme with respect to various performance evaluation metrics in cloud computing environment.

With advancements in information and communication technology (ICT), there is an increase in the number of users availing remote healthcare applications. The data collected about the patients in these applications varies with respect to volume, velocity, variety, veracity, and value. To process such a large collection of heterogeneous data is one of the biggest challenges that needs a specialized approach. To address this issue, a new fuzzy rule-based classifier for big data handling using cloud-based infrastructure is presented in this paper, with an aim to provide Healthcare-as-a-Service (HaaS) to the users located at remote locations. The proposed scheme is based upon the cluster formation using the modified Expectation-Maximization (EM) algorithm and processing of the big data on the cloud environment. Then, a fuzzy rule-based classifier is designed for an efficient decision making about the data classification in the proposed scheme. The proposed scheme is evaluated with respect to different evaluation metrics such as classification time, response time, accuracy and false positive rate. The results obtained are compared with the standard techniques to confirm the effectiveness of the proposed scheme.

Cloud computing (CC) has emerged as a leading technology for providing on-demand services such as, network access, data storage, computation to end users for smooth execution of various applications. Such services are provided over physical servers hosted by large data centers (DCs) which may be geographically located. In recent times, with an increase in service requests for various resources, DCs have expanded drastically in terms of number of servers. With such an increase in high-end servers, the energy consumption of DCs has escalated many folds which may lead to additional burden on the grid. Moreover, the escalation in energy consumption of DCs has an impact on carbon footprints in the environment. Hence, the integration of renewable energy sources (RES) with DCs may ease the load of grid to a great extent. However, due to intermittent nature of RES, it is a difficult task to sustain DCs using RES. Hence, to sustain the energy consumption of DCs using RES, the penetration of electric vehicles (EVs) can be a major leap. To resolve these issues, a software-defined network (SDN)-based DC energy management system using RES and EVs is designed in this paper. In the proposed scheme, a charging- discharging mechanism for penetration of EVs is formulated to cope with the intermittent nature of RES. The results obtained clearly depict that the penetration of EVs played a major role to manage the energy consumption of DC using RES.

Nontechnical losses, particularly due to electrical theft, have been a major concern in power system industries for a long time. Large-scale consumption of electricity in a fraudulent manner may imbalance the demand-supply gap to a great extent. Thus, there arises the need to develop a scheme that can detect these thefts precisely in the complex power networks. So, keeping focus on these points, this paper proposes a comprehensive top-down scheme based on decision tree (DT) and support vector machine (SVM). Unlike existing schemes, the proposed scheme is capable enough to precisely detect and locate real-time electricity theft at every level in power transmission and distribution (T&D). The proposed scheme is based on the combination of DT and SVM classifiers for rigorous analysis of gathered electricity consumption data. In other words, the proposed scheme can be viewed as a two-level data processing and analysis approach, since the data processed by DT are fed as an input to the SVM classifier. Furthermore, the obtained results indicate that the proposed scheme reduces false positives to a great extent and is practical enough to be implemented in real-time scenarios.