Computation offloading at lower time and lower energy consumption is crucial for resource-constrained mobile devices. This paper proposes an offloading decision-making model using federated learning. Based on the device configuration, task type, and input, the proposed decision-making model predicts whether the task is computationally intensive or not. If the predicted result is computationally intensive , then based on the network parameters the proposed decision-making model predicts whether to offload or locally execute the task. The experimental results show that the proposed method achieves above 90 % prediction accuracy in offloading decision-making, and reduces the response time and energy consumption of the user device by ∼ 11-31 %. A secure partial computation offloading method for federated learning is also proposed to deal with the Straggler effect of federated learning. The results present that the proposed partial computation offloading method for federated learning has achieved a prediction accuracy of above 98 % for the global model.

ABSTRACT Introduction Federated learning has become an emerging technology in data analysis for IoT applications. Methods This paper implements centralized and decentralized federated learning frameworks for crop yield prediction based on Long Short‐Term Memory Network and Gated Recurrent Unit. For centralized federated learning, multiple clients and one server are considered, where the clients exchange their model updates with the server that works as the aggregator to build the global model. For the decentralized framework, a collaborative network is formed among the devices either using ring topology or using mesh topology. In this network, each device receives model updates from the neighboring devices and performs aggregation to build the upgraded model. Results The performance of the centralized and decentralized federated learning frameworks is evaluated in terms of prediction accuracy, precision, recall, F1‐Score, and training time. The experimental results show that 93% prediction accuracy is achieved using the centralized and decentralized federated learning‐based frameworks. The results also show that using centralized federated learning, the response time can be reduced by 75% than the cloud‐only framework. Conclusion Centralized and decentralized federated learning architectures show good performance in terms of prediction accuracy and loss. The training time, including communication for both case studies, is also not very high, as observed from the results. Further, as no raw data is shared, the data privacy is protected. Finally, the future research directions of the use of federated learning in crop yield prediction are proposed.

Abstract Crop yield prediction is a crucial area in agriculture that has a large impact on the economy of a country. This article proposes a crop yield prediction framework based on Internet of Things and edge computing. We have used a fifth generation network device referred to as femtolet as the edge device. The femtolet is a small cell base station that has high storage and high processing ability. The sensor nodes collect the soil and environmental data, and then the collected data is sent to the femtolet through the microcontrollers. The femtolet retrieves the weather‐related data from the cloud, and then processes the sensor data and weather‐related data using Bi‐LSTM. The femtolet after processing the data sends the generated results to the cloud. The user can access the results from the cloud to predict the suitable crop for his/her land. This is observed that the suggested framework provides better accuracy, precision, recall, and F1‐score compared to the state‐of‐the‐art crop yield prediction frameworks. This is also demonstrated that the use of femtolet reduces the latency by ˜25% than the conventional edge‐cloud framework.

Abstract Internet of Things (IoT) has a pivotal role in developing intelligent and computational solutions to facilitate varied real‐life applications. To execute high‐end computations and data analytics, IoT and cloud‐based solutions play the most significant role. However, frequent communication with long distant cloud servers is not a delay‐aware and energy‐efficient solution while providing time‐critical applications such as healthcare. This article explores the possibilities and opportunities of integrating cloud technology with fog and edge‐based computing to provide healthcare services to users in exigency. Here, we propose an end‐to‐end framework namedRESCUE(enabling green healthcare services using integrated iot‐edge‐fog‐cloud computing environments), consisting efficient spatio‐temporal data analytics module for efficient information sharing, spatio‐temporal data analysis to predict the path for users to reach the destination (healthcare center or relief camps) with minimum delay in the time of exigency (say, natural disaster). This module analyzes the collected information through crowd‐sourcing and assists the user by extracting optimal path postdisaster when many regions are nonreachable. Our work is different from the existing literature in varied aspects: it analyses the context and semantics by augmenting real‐time volunteered geographical information (VGI) and refines it. Furthermore, the novel path prediction module incorporates such VGI instances and predicts routes in emergencies avoiding all possible risks. Also, the design of development of a latency‐aware, power‐aware data‐driven analytics system helps to resolve any spatio‐temporal query more efficiently compared to the existing works for any time‐critical application. The experimental and simulation results outperform the baselines in terms of accuracy, delay, and power consumption.

Abstract Several global health incidents and evidences show the increasing likelihood of pandemics (large‐scale outbreaks of infectious disease), which has adversely affected all aspects of human lives. It is essential to develop an analytics framework by extracting and incorporating the knowledge of heterogeneous data‐sources to deliver insights for enhancing preparedness to combat the pandemic. Specifically, human mobility, travel history, and other transport statistics have significantly impact on the spread of any infectious disease. This article proposes a spatio‐temporal knowledge mining framework, named STOPPAGE, to model the impact of human mobility and other contextual information over the large geographic areas in different temporal scales. The framework has two key modules: (i) spatio‐temporal data and computing infrastructure using fog/edge based architecture; and (ii) spatio‐temporal data analytics module to efficiently extract knowledge from heterogeneous data sources. We created a pandemic‐knowledge graph to discover correlations among mobility information and disease spread, a deep learning architecture to predict the next hotspot zones. Further, we provide necessary support in home‐health monitoring utilizing Femtolet and fog/edge based solutions. The experimental evaluations on real‐life datasets related to COVID‐19 in India illustrate the efficacy of the proposed methods. STOPPAGE outperforms the existing works and baseline methods in terms of accuracy by (18–21)% in predicting hotspots and reduces the power consumption of the smartphone significantly. The scalability study yields that the STOPPAGE framework is flexible enough to analyze a huge amount of spatio‐temporal datasets and reduces the delay in predicting health status compared to the existing studies.

Summary Energy‐efficient smart retail system design is a challenging research area. In this paper, we propose an automated retail system using a femtolet‐based fog network. A femtolet is an indoor base station providing computation and storage. Femtolets in our system work as indoor base stations and maintain databases of the products located in their respective coverage areas. The femtolets switch to active or idle mode according to the user's presence in its coverage. A smart trolley is proposed for our retailing system, which guides the user to the particular product type selected by the user. The user, after entering the shopping mall, carries the smart trolley. The customer selects and purchases products using this trolley. On the basis of product purchasing, the respective databases maintained inside the femtolets are updated. An Android application for the proposed retailing is developed. We compare the power consumption and delay of the proposed retail system with the existing retail system. Simulation analyses illustrate that the proposed approach reduces power by approximately 89% and 94%, respectively, in comparison to the local cloud server–based and remote cloud server–based retail systems. Thus, we refer to the proposed system as a green retail system. The performance of the proposed system through experimental analysis is also evaluated.

Fast interactive response in mobile cloud computing is an emerging area of interest. Execution of applications inside the remote cloud increases the delay and affects the service quality. To avoid this difficulty cloudlet is introduced. Cloudlet provides the same service to the device as cloud at low latency but at high bandwidth. But selection of a cloudlet for offloading computation at low power is a major challenge if more than one cloudlet is available nearby. In this paper we have proposed a power and latency aware optimum cloudlet selection strategy for multi-cloudlet environment with the introduction of a proxy server. Theoretical analysis show that using the proposed approach the power and the latency consumption are reduced by approximately 29-32 and 33-36 percent respectively than offloading to the remote cloud. An experimental analysis of the proposed cloudlet selection scheme is performed using cloudlets and cloud servers located at our university laboratory. Theoretical and experimental results demonstrate that using the proposed strategy power and latency aware cloudlet selection can be performed. The proposed approach is compared with the existing methods on multi-cloudlet scenario to demonstrate that the proposed approach reduces the power consumption and the system response time.

This study presents a frequency allocation strategy for macro‐femtocell and micro‐femtocell cluster‐based long‐term evaluation‐advanced network. In the proposed approach the network is divided into a number of clusters. Each cluster contains a macrocell or a number of microcells. Femtocells are deployed within a macrocell or a microcell. In the proposed strategy fractional frequency reuse is used. Each macrocell and microcell is divided into three regions. Different frequency sets are allocated for macrocell and femtocells in a macro‐femtocell cluster. Similarly in a micro‐femtocell cluster, different frequency sets are provided to a microcell and the femtocells contained in that microcell. For each region inside a macrocell or a microcell, the allotted frequency band is different from the adjacent region. The path loss model for the macro‐femtocell and micro‐femtocell cluster‐based network is developed in this study. The signal‐to‐interference‐plus‐noise ratio and spectral efficiency are determined. The simulation results show that using the proposed strategy signal‐to‐interference‐plus‐noise ratio can be increased to ∼62–92%. Simulation results present that macro‐femtocell and micro‐femtocell cluster‐based network reduces the power transmission to ∼48% than that of a macro‐femtocell network. Hence it is referred as a green mobile network.