Search

Proportional Integral Derivative (PID) controllers are widely employed in industrial applications due to their effectiveness, simplicity, and versatility. Within the automotive sector, one notable application of the Proportional Integral (PI) controller is in the realm of electric motors, particularly the Brushless Direct Current (BLDC) motors powering Electric Vehicles (EVs). The precision of speed control over BLDC motors, renowned for their efficiency and reliability, is paramount for optimizing vehicle performance and ensuring energy efficiency. PIDs must be tuned each time they are used in an application to optimize performance. A well-known empirical hit and trial tuning strategy is the Ziegler–Nichols method, which results in sub-optimal performance in the presence of locally optimal solutions of large-dimensional search spaces. Existing Artificial Intelligence methods tailored for PID controller tuning often focus on singular optimization aspects, neglecting potential performance gains achievable through multi-objective considerations. Furthermore, prevalent swarm-based PID optimization methods typically initialize the population randomly without imposing any bounds on input parameters, thus rendering them susceptible to inconsistent, unreliable, sub-optimal solutions in unconstrained search environments. In our research endeavors, we mathematically model the multi-objective optimization of BLDC motor speed control, energy usage, and efficiency using constrained Differential Evolution and Particle Swarm Optimized PID controllers. The Ziegler–Nichols tuning method is used to ascertain the initial PI parameters and define bounds within the input space. Our methodology addresses a critical gap by integrating real-time road gradient data into the EV control system, enhancing precision and minimizing energy consumption, especially during challenging road conditions. The proposed approach significantly improves motor speed control and energy efficiency in EVs. With our proposed swam-based optimization over 30 iterations, MSE decreased by approximately 95.4% (from 3.8834 to 0.1809), while energy consumption reduced by about 3.1% (from 1.015 kWh to 0.984 kWh). These results highlight the effectiveness of our method in enhancing both speed control precision and energy efficiency. In addition, code related data is available at Github.

Recently, a noticeable increase in the shortage of energy resources has been observed, coupled with a rapidly escalating demand for energy. In response to this challenge, this paper proposed a dynamic predictive optimization method that considers real-time energy price policies to optimize energy usage while simultaneously ensuring occupant comfort. To this aim, real-time environment data is collected using embedded devices via sensors. Meanwhile, real-time energy usage data is collected using smart meters. The collected environment and energy data train a Deep Learning (DL) model for predicting energy and thermal comfort. The proposed framework employs a Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Gated Recurrent Unit (GRU) to predict humidity, temperature, Predicted Mean Vote (PMV), and energy consumption. The trained models are then deployed on the embedded devices for edge inference. The Whale Optimization Algorithm (WOA) optimizes occupant comfort and energy use. The WOA optimizes the energy cost while considering occupant comfort and real-time energy pricing. The output of whale optimization is passed to a Fuzzy Logic Controller (FLC) to trigger control commands for proactive response. The Open Connectivity Foundation (OCF) standard is used to perform the communication. The real-time OCF-based optimal actuator control testbed experiments are evaluated using several energy policies. Extensive experiments demonstrate the effectiveness of the proposed system. The developed framework achieves cost savings ranging from 35.98% to 38.22%.

Decentralized Federated Learning (DFL) enables collaborative model training across multiple devices without relying on a central server, preserving data privacy and achieving full decentralization. However, optimizing hyperparameters (HPs) in DFL presents significant challenges due to system and statistical heterogeneity and the lack of centralized coordination. Existing Hyperparameter Optimization (HPO) methods for Federated Learning (FL) typically rely on a central server, making them unsuitable for fully decentralized environments. These methods face scalability issues, high communication and computation overhead, and limited adaptability to node-specific requirements. The need for serverless, fully decentralized HPO is particularly critical in scenarios demanding minimal communication and efficient resource usage. To address these challenges, we propose the single-pass Decentralized Federated Hyperparameter Optimization framework (DFed-HPO), which integrates three advanced HPO strategies for computation and communication-efficient HP optimization. DFed-HPO includes three hyperparameter aggregation mechanisms: MetaRegress Aggregator (MA), Consensus Aggregator (CA), and Fusion Aggregator (FA). MA uses meta-learning principles to predict the performance of new configurations with minimal communication, while CA and FA enhance optimization and aggregation based on model similarity and consensus-building among nodes. By conducting HPO in a single pass, DFed-HPO reduces communication overhead while achieving robust hyperparameter consensus. We validated DFed-HPO on MNIST and the Electricity dataset, demonstrating its potential in energy management applications, including green hydrogen production using renewable energy systems. Results show that DFed-HPO improves model performance, accelerates convergence, and adapts to non-IID data, offering a scalable and efficient solution for decentralized AI networks in resource-constrained settings.

The integrated Electrical Control Unit (ECU) assumes a pivotal role in overseeing and coordinating various components within mobility systems, encompassing the Vehicle Control Unit (VCU), Electrical Power Steering (EPS), Electronic Stability Control (ESC), and Body Control Unit (BCU). The integrated ECU enables efficient power allocation, effective regenerative energy capture, and optimal utilization of available energy resources through integrating and synchronizing these subsystems. This review study provides an in-depth analysis of the various aspects of integrated ECU in electric vehicles (EVs) and its sub-branches, including VCU, EPS, ESC, and BCU. The proposed research study offers a comprehensive overview of the development strategies of the integrated ECU, with a specific focus on mobility energy efficiency. Moreover, our research study presents the utilized elements by each control unit, highlighting their roles and significance in enabling efficient vehicle control and safety in future intelligent transportation systems. Additionally, our study examines the summary of integrated control unit developments, thoroughly evaluating the improvement in techniques and efficiency with the analysis results of performance measures of EVs. By summarizing these strategies and the analysis results, readers gain insights into the evolution and advancements made in the field. This facilitates a comprehensive understanding of the approaches used to enhance vehicle performance, stability, and control. Ultimately, this study aims to serve as a valuable resource for researchers interested in comprehending the intricate workings of ECUs and their sub-branches in EVs.

Federated learning (FL) enables decentralized model training, but the distribution of data across devices presents significant challenges to global model convergence. Existing approaches risk losing the representativeness of local models after model aggregation, calling for a more efficient and robust solution. In this study, we address the model aggregation challenge within FL by focusing on elevating the performance of the global model amidst class imbalance and non-independent, non-identically distributed data. We aim to train a global model collaboratively that represents all participating nodes, promoting fairness and ensuring adequate representation of all classes in the model. We propose redistributing local model weights based on their precision-based contributions to each class to enhance the performance and communication efficiency of federated thermal comfort prediction. Our proposed method can assist in allocating more resources and attention to nodes with high precision for underrepresented classes, thereby improving the global model overall performance and fairness. Furthermore, our framework leverages the virtualization capability of digital-twin to enable the dynamic registration and participation of nodes in the federated learning process in real-time. The developed digital-twin framework allows for real-time monitoring and control of the decentralized training. Through our evaluation on a real dataset, we showcase noteworthy enhancements in accuracy and communication efficiency when compared to existing methods. Our evaluation shows that the proposed Class Precision-Weighted Aggregation technique (Fed-CPWA) outperforms Federated Averaging, with higher accuracy of 82.85% and lower communication costs by 25%. Our contribution represents a significant stride towards sustainable thermal comfort modeling, further advancing the development of equitable and resilient federated learning techniques.

Emerging technologies and applications including the Internet of Things (IoT), social networking, and crowd-sourcing generate large amounts of data at the network edge. Machine learning models are often built from the collected data, to enable the detection, classification, and prediction of future events. Due to bandwidth, storage, and privacy concerns, it is often impractical to send all the data to a centralized location. Recently, the emerging Federated Learning (FL) systems mitigates some of those concerns, by keeping data private to cater the confidentiality issues. Although FL has drawn the attention of researchers and developers, the involvement of an aggregator server for global model updates, makes the system prone to privacy and security breaches. To resolve this issue Swarm Learning (SL) securely onboards edge clients and dynamically elects the swarm leader, to perform collaborative model training in an extremely decentralized, private and secured manner. However, the conventional blockchain-enabled dynamic selection of leader at every communication round is resource intensive and degrades SL’s effectiveness. In this paper, we propose a lightweight communication and computation efficient cooperative swarm learning framework for cyclic edge intelligent computing. The proposed cooperative swarm learning provides cyclic learning based on Deep Neural Networks procedure for training a global model in a sequential ring topology in one iteration which reduces the computational and communication overhead. The global model update method trains a shared global thermal comfort prediction model. Since there is model updating being performed in each participant of the cyclic edge intelligent computing network, bandwidth and computing power demand are reduced. An empirical investigation on Non-IID thermal comfort dataset demonstrates the superiority of the proposed framework.

The growing energy demand with diminishing energy resources calls for development of optimal indoor control system through accurate energy and occupant comfort modeling in a smart-home. While some major obstacles faced by smart-home IoT network are heterogeneity and disparate IP frameworks resulting in a connectivity and interoperability issues. In this paper we developed a new Open Connectivity Foundation (OCF) based prediction assisted optimal control framework for optimizing energy consumption and maximizing occupant comfort in smart-home. To the best of our knowledge, we are the first to design a scalable, secure, and inter-operable optimal control solution for smart-home IoT networks. The developed framework offloads machine learning models on IoT device for accurate energy and thermal comfort modeling to enable prediction assisted optimization. The system enables edge analytics using deep learning based inference models for proactive response. For optimization standard Firefly algorithm is modified based on inertia weight approach to achieve improved performance. OCF based optimal actuator control test-bed deployment and real-time experimentation is conducted to evaluate the performance of the system. Empirical investigation verified the effectiveness of proposed framework with energy saving scope of 36.82%, 5 s average response time and 3.36 MS Round Trip Time.

Federated Learning (FL) promises to solve the data privacy problem by training the local model on each node and sharing the model parameters instead of the data itself. Next, the FL server applies model aggregation techniques to aggregate the received models and broadcast the resulting model to the connected clients. This study proposes a Digital Twin-based Federated Learning (DT-FL) framework to virtually monitor and controls the remotely deployed physical clients and their training process. The connection-oriented protocol, Open Connectivity Foundation (OCF) Iotivity, connects the FL clients with the FL server to ensure packet delivery. OCF Iotivity sends/receives the models’ weights to/from the server, and Hyper Text Transfer Protocol (HTTP) is used to monitor clients’ local training. After receiving partially trained models from clients, the server performs the best model selection using the normal distribution method by considering the performance of the model. Finally, the best-selected models are aggregated, and the final model is broadcasted to the clients. The framework utilizes Raspberrypi 4 devices as clients with limited computational capabilities, due to which the experiments are conducted with structured energy consumption data. The dataset comprised of 8 multistory residential buildings located in different geographical locations of the Republic of Korea. Each residential building is treated as an FL client and registered on DT using the IP address and port number. The DT-FL framework can be used with classification and regression datasets, and the model architecture for that data can be designed on the DT platform. The experiments are conducted with the partial and full participation of clients. The results show the minimum delay time in physical and virtual object synchronization and better performance and generalization of the global model for each client. The source code of the proposed DT-FL framework is available on GitHub.

Context prediction plays a vital role in an assistive ubiquitous environment. The environmental configuration in a ubiquitous environment is heavily dependent on the context of the events occurring in the environment. Current state of the art approaches utilize the user’s history information for predicting the context of the events. When the user’s history does not provide apposite contextual information for the observed activity/event at time t, the history based state of the art context prediction techniques fails to predict the appropriate future context. To overcome the gap of missing context information in the user’s context history, we propose a Profile based Collaborative Context Prediction (PCCP) approach. PCCP is a predictive association rules based system which utilizes the history of similar users and collaborate among users of the ubiquitous environment. PCCP generates rules at high level of abstraction, human readable and understandable that helps in avoiding the underline details. To evaluate the PCCP, a smart office is considered as an experimental environment. Experiments are carried out on indigenous multi user smart office data set. Our experiments showed significant level of accuracy in both environments. Due to the understandability of output and higher accuracy of PCCP, it can be extended to assist the user in a smart environment.

Recently, various smart application services have been developed using GPS (Global Positioning System), RFID (Radio Frequency IDentification) and sensor networks. The GPS has been successfully applied for outdoor location tracking by many applications, but it might still be insufficient in an indoor environment where GPS signals are often severely obstructed. The RFID technology has been utilized to play an important role in location tracking for indoor smart applications. Therefore, in this paper, we present the scenario and architecture of an indoor location tracking service for things or space in an exhibition environment based on mobile RFID. The RFID tags of things or spaces are identified as the locations of point being passed and we obtain the spatial data from the tags using mobile RFID readers, Web server and Database server. We have designed and implemented the prototype of location tracking system for exhibition scenario using Microsoft .NET framework. Additionally, we have verified the functionality of this system so various other indoor smart services may be provided using the proposed system.

Presently, blockchain technology has been widely applied in various application domains such as the Internet of Things (IoT), supply chain management, healthcare, etc. So far, there has been much confusion about whether blockchain performs with scale, and admittedly, a lack of information about best practices that can improve the performance and scale. This paper proposes a novel blockchain network construction methodology to improve the performance of Hyperledger Fabric. As a highly scalable permissioned blockchain platform, Hyperledger Fabric supports a wide range of enterprise use cases from finance to governance. A comprehensive evaluation is performed by observing various configurable network components that can affect the blockchain performance. To demonstrate the significance of the proposed methodology, we set up the experiment environment for the baseline and the test network using optimized parameters, respectively. The experimental results indicate that the test network's performance is enhanced effectively compared to the baseline in transaction throughput and transaction latency.