Cloud-based Internet Of Things Research Articles

A new state of charge estimation technique of lithium-ion battery using adaptive extended Kalman filter and artificial neural network

Due to rapid rise in climate change, world is seeing a major technology shift from conventional vehicles to electric vehicles (EVs). Battery’s state of charge (SOC) is a critical parameter in EVs whose accuracy affects not only the battery management system but can also influence the driving range estimation for an EV. In this paper, a simulation-based hybrid technique is presented, that combines both adaptive extended Kalman filter (AEKF) and artificial neural network (ANN) for SOC estimation of lithium-ion battery. The proposed hybrid technique is validated using five different EV driving cycles, that is, LA92, US06, urban dynamometer driving schedule (UDDS), highway fuel economy test (HWFET) and a mixed driving cycle at four different temperature values, that is, 0°C, 10°C, 25°C and 40°C. To facilitate the potential EV users, a real-time SOC estimator is also implemented. The real-time SOC estimated through open circuit voltage method and Coulomb counting method is further used for reservation of a charging slot in a nearby charging station. Moreover, to monitor the charging status of a potential EV from a remote location, a cloud-based Internet of things (IoT) platform, that is, ThingSpeak, is used. This results into the reduction of waiting time for an EV user at a charging station. In addition to this, a comparative analysis is carried out between proposed hybrid method and existing methods. It is demonstrated that our hybrid technique achieves lower root mean square error and higher accuracy as compared to existing methods at different operating conditions.

Data-driven internet of things and cloud computing enabled hydropower plant monitoring system

Hydropower is one of the renewable energy sources that can play a crucial role to fulfil the global energy demand. However, the performance of the hydro turbine is severely affected by silt erosion and cavitation problems which causes a reduction in the overall efficiency of the plant. Various studies have been carried out and are available in the literature to investigate silt erosion and cavitation issues in hydro turbines. It has been reported that cavitation and silt erosion varies with the variation in discharge under part load and overload operating conditions of the machine. However, very few studies are available to predict the performance of the machine under variable operating conditions. Hence, there is a scope of study for monitoring the performance under these conditions in real-time, as it is difficult to predict the behavior of the machine using the existing models. In view of the above, an architecture of a data-driven IoT-based cloud computing-enabled hydropower plant monitoring system has been proposed under the present study. In order to develop this system, historical plant data has been collected and correlations are developed, which are validated with real-time data on the ThingSpeak cloud. It has been found that the developed model can accurately predict the condition of the hydro turbine with an R2-value of 0.9693 having a mean absolute percentage error (MAPE) of 0.67% at 0.89% of root mean square percentage error (RMSPE), and the power factor with an R2-value of 0.9503, having a MAPE of 0.798% at 0.91% of RMSPE.

Cloud-based Library Management and Book Tracking through the Internet of Things

The cognitive content of this research article is to create a library management system that will eliminate the need for registers and other time-consuming manual methods of tracking inventory and processing payments. Students often fail to make use of the library's seating resources because they are unaware of their availability. Students may use this system to inquire about book availability, locate a seat in the library, and see detailed information about any book in the library's collection. Library management systems that use barcodes or radio frequency identification have been used before with some success, but they have drawbacks. In order to ensure the smooth, efficient, and theft-free functioning of libraries, the suggested technique makes use of cloud-based IoT technology. With this setup, the user may read a full book's worth of content without having to carry around their laptop or desktop computer; they only need their smartphone and a portable reader. Using IoT, library data may be accessed from the comfort of home. This "Smart Library System" is designed to streamline the process of locating and checking out books through the Internet.

A secure cryptosystem using DNA cryptography and DNA steganography for the cloud-based IoT infrastructure

In this digital era, most of the data of an Internet of Things (IoT) infrastructure are communicated over the internet and they are stored in a cloud environment. As there are numerous users and attackers over the internet, IoT data face many security issues. Currently, Deoxyribonucleic Acid (DNA) cryptography is a cutting-edge area, which is used to enhance data security. In this paper, a novel cryptosystem is proposed using DNA cryptography and DNA steganography for the cloud-based IoT infrastructure. Here, the confidential data is encrypted by using a long secret key. Then, it is hidden in an image. Thus, the proposed cryptosystem not only hides the data, but also encrypts the confidential data prior to storing it on the cloud server, and it resists many security attacks in the cloud-based IoT infrastructure. To evaluate the performance of the proposed scheme, many experiments are performed. The results show the effectiveness of the proposed scheme.

A Novel Decentralized Group Key Management Scheme for Cloud-Based Vehicular IoT Networks

The vehicular internet of things (VIoT) network is connecting smart commuters to elevate traffic problems and effectiveness that help to improve driving conditions for vehicles. Every ITS-based vehicle OBU and commuter might be interchangeable and used to give access permission for the various services during transportation such as infotainment, emergency service, environment service, road condition, etc. These services are suffering from the 1-affect-n problem, scalability, memory resources, computation, and communication overhead. In this paper, the authors proposed a novel decentralized group key management protocol for cloud-based vehicular IoT networks (GVIoTNet) to solve the problem of 1-affect-n and scalability by using the decentralized approach of group key access, key generation, key distribution, key update among vehicles and commuters. Further, by using the master key encryption approach, the average rekeying minimization is 84.84% with the GroupIT scheme. The minimization of rekeying reduces storage overhead and improves computation as well as communication overhead.

Improving Quality Indicators of the Cloud-Based IoT Networks Using an Improved Form of Seagull Optimization Algorithm

The Internet of things (IoT) points to billions of devices located worldwide which are connected and share their data based on the Internet. Due to the new technologies that provide cheap computer chips and universal wireless networks, it is feasible that everything from a small tablet to a very large airplane will be connected to the Internet and will be a part of the IoT. In most applications, IoT network nodes face limitations in terms of energy source and cost. Therefore, the need for innovative methods to improve quality indicators that increase the lifespan of networks is evident. Here, a novel technique is presented to increase the quality of service (QoS) in IoT using an improved meta-heuristic algorithm, called the improved seagull optimization algorithm (ISOA), along with traffic management in these networks. Based on this subject, the traffic-aware algorithm can manage the sending of packets and increase the QoS provision in terms of time to a great extent. The performance evaluation of the proposed method and comparison with the previous methods demonstrated the accuracy and efficiency of this method and its superiority over the previous works.

Accuracy determination using deep learning technique in cloud-based IoT sensor environment

The Internet of Things (IoT) offers users a wide variety of facilities because it interconnects billions of smart devices. However, when connected to wireless connections, unlimited access to IoT gadgets poses potential risks. As it eases cost constraints on sensor nodes, the cloud service with IoT networks has received greater attention. In addition, the high complexity of the distribution and networking of IoT makes them vulnerable to attacks. Intrusion detection systems (IDSs) are selected to ensure the security of reliable information and operations. IDS successfully detects anomalies in complex network situations and guarantees network security. Deep Convolution Network (DCN) IDS have a slow learning curve and poor categorization precision. Deep Learning (DL) methods are often used in a wide range of safety data processing, imaging, and signal processing like Poor transfer learning ability, reusability of modules, and integration. To overcome the constraints of Machine Learning (ML) IDS is intended to provide a comprehensive mechanism to learn the detection mechanism for multicloud IoT environments. The proposed IDS approach increases training efficiencies while increasing detection accuracy. Experimental investigations of the proposed system using the considered database confirms that the performance of the proposed system is capable and in the range of acceptance with relative to existing methods. Further, achieving detection capability, reliability, and accuracy of 97.51, 96.28, and 94.41% respectively are achieved.

Embedded fog models for remote aquatic environmental monitoring

Fog computing is used in Internet of Things (IoT) applications to allow end node processing and storage to facilitate device autonomy and other benefits in light of unstable/unreliable cloud network connections. This paper investigates how a cloud-based IoT remote aquatic environmental monitoring platform can be adapted using a fog architectural approach to provide embedded condition assessment and forecasting functionality. An equivalent IoT hydroponic garden water quality monitoring test platform is developed which is capable of accommodating embedded fog models using a node-level microcontroller (i.e., ESP8266). The test platform is deployed in a hydroponics setting to gather environmental data and evaluate the feasibility of fog intelligence functionality on an embedded system. The first model involves a node-level Fuzzy Logic water quality condition assessment using the current sensor readings. The second model is a Support Vector Machine that makes short-term predictions of water quality parameters based on a history of locally stored sensor readings. The third model contrasts Long Short-Term Memory for water quality parameter prediction. The fog test platform and embedded models are evaluated according to performance, functionality and ease-of-implementation on a microcontroller. Finally, we propose a framework detailing the future modifications for the remote aquatic environmental monitoring platform to achieve embedded fog capabilities based on the experience with the hydroponics test platform.

Hybrid lightweight cryptography with attribute-based encryption standard for secure and scalable IoT system

ABSTRACT Internet of Things (IoT) devices require lower power consumption with higher security, which can be achieved by using lightweight cryptography (LWC) approaches. Attribute-based encryption (ABE) provides a fine-grained access control policy over encrypted data, making it useful in IoT-based cloud storage for allowed data protection. However, the conventional ABE approaches resulted in poor security performance against various attacks in the IoT environment. So, in this paper, the LWC-ABE method is proposed to enhance the security performance against various attacks in the IoT environment. The proposed LWC-ABE contains only multiple trusted authority environments, which is a bottleneck in IoT servers and IoT devices. The proposed LWC-ABE method supports high expressiveness, access policy updates, large attribute domains, and white box traceability properties. The simulation results shows that the proposed LWC-ABE resulted in reduced encryption and decryption times for multi users, different message sizes scenarios as compared to conventional approaches. The numerical outcomes of the proposed method are much better based on performance of encryption and decryption times as 0.000835 and 0.000310 respectively.

Automated fault detection and diagnosis deployment Internet of Things solution for building energy system

The building sector is the highest energy consumer and ranks first in terms of carbon emissions among all sectors. To address these issues, decarbonization and electrification in the building energy sector are two critical missions of the new US administration. For decarbonization, the new administration has set a target to reduce greenhouse gas emissions by 50–52% by 2030 and targeting a carbon-neutral economy by 2050. For electrification, the goal is to achieve 100% clean electricity by 2035. Such decarbonization and electrification in the building sector require that energy consumption in buildings be reduced significantly. Therefore, the building sector must continuously adopt new technologies to achieve its energy and carbon emission goals. One of the most fundamental technologies is the Internet of Things (IoT). IoT has proven to be an effective solution for the building domain, including building information/energy modeling, smart buildings, etc. Although much progress has been made in the development of IoT-based building energy systems, there is still a lack of reliable, scalable, and affordable IoT-based automated fault and degradation diagnostic (AFDD) solutions. Such solutions would enable deployment of advanced algorithms into real systems to archive the projected energy benefits. This study reviews existing IoT solutions developed for building energy–related application and developed a simple but effective AFDD IoT deployment solution, including developing a suitable IoT architecture and conducting easy and scalable deployment by leveraging a common cloud-based IoT service.

A Fuzzy-Based Method for Objects Selection in Blockchain-Enabled Edge-IoT Platforms Using a Hybrid Multi-Criteria Decision-Making Model

The broad availability of connected and intelligent devices has increased the demand for Internet of Things (IoT) applications that require more intense data storage and processing. However, cloud-based IoT systems are typically located far from end-users and face several issues, including high cloud server load, slow response times, and a lack of global mobility. Some of these flaws can be addressed with edge computing. In addition, node selection helps avoid common difficulties related to IoT, including network lifespan, allocation of resources, and trust in the acquired data by selecting the correct nodes at a suitable period. On the other hand, the IoT’s interconnection of edge and blockchain technologies gives a fresh perspective on access control framework design. This article provides a novel node selection approach for blockchain-enabled edge IoT that provides a quick and dependable node selection. Moreover, fuzzy logic to approximation logic was used to manage numerical and linguistic data simultaneously. In addition, the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), a powerful tool for examining Multi-Criteria Decision-Making (MCDM) problems, is used. The suggested fuzzy-based technique employs three input criteria to select the correct IoT node for a given mission in IoT-edge situations. The outcomes of the experiments indicate that the proposed framework enhances the parameters under consideration.

Resource placement strategy optimization for IoT oriented monitoring application

Cloud computing and the low power wide area network (LPWAN) network represent the key infrastructures for developing intelligent solutions based on the internet of things (IoT). However, the diversity of use cases and deployment scenarios of IoT in the different domains makes optimizing IoT-based cloud solutions a major challenge. The cloud solution’s cost increases with the increase in central processing unit (CPU) resources and energy consumption. The optimal use of edge material resources in industrial solutions will reduce the consumption of resources and thus optimize cloud infrastructure costs in terms of resources and energy consumption. The article presents the network and application architecture of an IoT monitoring solution based on cloud services. Then, we study the integration of IoT services based on application placement strategies on the fog cloud compared to the traditional centralized cloud strategy. Simulations evaluate the scenarios with the iFogSim simulator and the analyzed results compare the traditional strategy with the cloud-fog. The results show that cost and energy consumption in the cloud can be significantly reduced by processing the application at the end devices level with respect to the possible limit of CPU processing power for each IoT end device. Latency and network usage respect quality of service constraints in cloud-fog placement for this type of monitoring-oriented IoT application.

Anomaly Detection for IOT/Cloud-Based Model in Fog Computing Using Machine Learning

We know that the key technologies that are involved in the Internet of Things are wireless sensor networks and cloud computing, big data, embedded systems, and the internet. It is a giant network with connected devices. These devices gather and share data. But many IoT devices have poor security and cybercriminals are taking benefit of this. The two techniques cloud and fog computing both combined can be used to transfer secure data in IoT devices as cloud computing provides storage of data on cloud servers and fog computing offers us various services to access data and provides support for cloud servers. This research work presents various techniques to detect an intruder and anomaly detection in IoT-based cloud systems. Also, a comparison of all the techniques used to detect intruders and anomalies are compared on various parameters like accuracy, performance, efficiency, precision, recall, the detection rate.

Multicopy and Multiserver Provable Data Possession for Cloud-Based IoT

Provable data possession (PDP) is widely considered to be an efficient method in verifying the integrity of remote data. While earlier PDP schemes are generally designed to check the integrity of data copies on a single cloud server (CS), there have been attempts to design multicopy and multiserver PDP (MCMS-PDP) schemes in recent years. However, it is known that MCMS-PDP schemes may be vulnerable to copy-summation attacks or do not support dynamic operations. The former enables a (dishonest) CS to only store a summation of copies for successful verification, while the latter does not allow the data owner to update the stored data. In this article, we propose a new MCMS-PDP scheme based on homomorphic verifiable tags. Specifically, our proposed scheme is designed to check the integrity of all copies in one challenge–response and resist copy-summation attacks. The scheme also supports public verification and block-level dynamic operations, such as modification, insertion, and deletion using the divide-and-conquer table. We then prove the security of our scheme, assuming the intractability of the computational Diffie–Hellman problem, in the random oracle model. We also evaluate the performance of the scheme to demonstrate its efficiency.

Dynamic System Diversification for Securing Cloud-based IoT Subnetworks

Remote exploitation attacks use software vulnerabilities to penetrate through a network of Internet of Things (IoT) devices. This work addresses defending against remote exploitation attacks on vulnerable IoT devices. As an attack mitigation strategy, we assume it is not possible to fix all the vulnerabilities and propose to diversify the open-source software used to manage IoT devices. Our approach is to deploy dynamic cloud-based virtual machine proxies for physical IoT devices. Our architecture leverages virtual machine proxies with diverse software configurations to mitigate vulnerable and static software configurations on physical devices. We develop an algorithm for selecting new configurations based on network anomaly detection signals to learn vulnerable software configurations on IoT devices, automatically shifting towards more secure configurations. Cloud-based proxy machines mediate requests between application clients and vulnerable IoT devices, facilitating a dynamic diversification system. We report on simulation experiments to evaluate the dynamic system. Two models of powerful adversaries are introduced and simulated against the diversified defense strategy. Our experiments show that a dynamically diversified IoT architecture can be invulnerable to large classes of attacks that would succeed against a static architecture.

A Fog-Cluster Based Load-Balancing Technique

The Internet of Things has recently been a popular topic of study for developing smart homes and smart cities. Most IoT applications are very sensitive to delays, and IoT sensors provide a constant stream of data. The cloud-based IoT services that were first employed suffer from increased latency and inefficient resource use. Fog computing is used to address these issues by moving cloud services closer to the edge in a small-scale, dispersed fashion. Fog computing is quickly gaining popularity as an effective paradigm for providing customers with real-time processing, platforms, and software services. Real-time applications may be supported at a reduced operating cost using an integrated fog-cloud environment that minimizes resources and reduces delays. Load balancing is a critical problem in fog computing because it ensures that the dynamic load is distributed evenly across all fog nodes, avoiding the situation where some nodes are overloaded while others are underloaded. Numerous algorithms have been proposed to accomplish this goal. In this paper, a framework was proposed that contains three subsystems named user subsystem, cloud subsystem, and fog subsystem. The goal of the proposed framework is to decrease bandwidth costs while providing load balancing at the same time. To optimize the use of all the resources in the fog sub-system, a Fog-Cluster-Based Load-Balancing approach along with a refresh period was proposed. The simulation results show that “Fog-Cluster-Based Load Balancing” decreases energy consumption, the number of Virtual Machines (VMs) migrations, and the number of shutdown hosts compared with existing algorithms for the proposed framework.

A novel fuzzy clustering-based method for human activity recognition in cloud-based industrial IoT environment

A novel fuzzy clustering-based method for human activity recognition in cloud-based industrial IoT environment

Fog Computing

Managing the knowledge generated by the Internet of Things (IoT) sensors and actuators is one of the most important. Challenges in introducing IoT systems. Traditional cloud-based IoT systems We challenged the large scale, non- uniformity, and high latency observed in some cloud ecosystems. One solution is to decentralize applications, management, and data analytics within the network itself. Use of distributed and integrated computing models. This approach is called the nebula Calculate. This document introduces a conceptual model of fog and mist computing. They refer to the cloud-based computing model of the IoT. This document shows further features Key characteristics and aspects of fog computing, including service models and deployments It provides a baseline of what strategy and fog computing are, and how to use them.

A Privacy-Aware Approach for Managing the Energy of Cloud-Based IoT Resources Using an Improved Optimization Algorithm

Cloud-based Internet of Things (IoT) is a network of physical things controlled and monitored via the Internet to develop numerous smart systems. In this network, numerous physical things with different types of sensors are created that can be linked to the Internet. IoT devices need to work with limited energy sources for a long time, and wireless communications are the primary source of energy usage. As a result, the lifespan of IoT devices can be extended by minimizing radio communications. Because of the great capability of the IoT, the issue of resource energy consumption is raised. On the other hand, privacy concerns must be considered when designing cloud-based IoT applications. The current article introduces programming formulations of the mentioned issues using an improved ant colony optimization (IACO) algorithm. The method is combined with a new kind of local search algorithm to obtain higher-quality responses. Also, for responding to privacy concerns, a privacy-preserving method has been suggested. The suggested approach has been tested widely, and the outcomes have been compared to the genetic and particle swarm optimization (PSO) algorithms. The results indicated the good ability of the proposed method in terms of network lifespan and energy consumption.

Towards Fast and Accurate Federated Learning with Non-IID Data for Cloud-Based IoT Applications

As a promising method of central model training on decentralized device data while securing user privacy, Federated Learning (FL) is becoming popular in the Internet of Things (IoT) design. However, when the data collected by IoT devices are highly skewed in a non-independent and identically distributed (non-IID) manner, the accuracy of the vanilla FL method cannot be guaranteed. Although there exist various solutions that try to address the bottleneck of FL with non-IID data, most of them suffer from extra intolerable communication overhead and low model accuracy. To enable fast and accurate FL, this paper proposes a novel data-based device grouping approach that can effectively reduce the disadvantages of weight divergence during the training of non-IID data. However, since our grouping method is based on the similarity of extracted feature maps from IoT devices, it may incur additional risks of privacy exposure. To solve this problem, we propose an improved version by exploiting similarity information using the Locality-Sensitive Hashing (LSH) algorithm without exposing extracted feature maps. Comprehensive experimental results on well-known benchmarks show that our approach can not only accelerate the convergence rate, but also improve the prediction accuracy for FL with non-IID data.