A Secure IIoT Environment That Integrates AI-Driven Real-Time Short-Term Active and Reactive Load Forecasting with Anomaly Detection: A Real-World Application DOI Creative Commons
Md. Ibne Joha,

Md Minhazur Rahman,

Md Shahriar Nazim

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(23), P. 7440 - 7440

Published: Nov. 21, 2024

The Industrial Internet of Things (IIoT) revolutionizes both industrial and residential operations by integrating AI (artificial intelligence)-driven analytics with real-time monitoring, optimizing energy usage, significantly enhancing efficiency. This study proposes a secure IIoT framework that simultaneously predicts active reactive loads while also incorporating anomaly detection. system is optimized for deployment on an edge server, such as single-board computer (SBC), well cloud or centralized server. It ensures reliable smart data acquisition systems control, protective measures. We propose Temporal Convolutional Networks-Gated Recurrent Unit-Attention (TCN-GRU-Attention) model to predict loads, which demonstrates superior performance compared other conventional models. metrics load forecasting are 0.0183 Mean Squared Error (MSE), 0.1022 Absolute (MAE), 0.1354 Root (RMSE), forecasting, the 0.0202 0.1077 0.1422 (RMSE). Furthermore, we introduce Isolation Forest detection considers transient conditions appliances when identifying irregular behavior. very promising performance, average all using this being 95% Precision, 98% Recall, 96% F1 Score, nearly 100% Accuracy. To entire system, Transport Layer Security (TLS) Secure Sockets (SSL) security protocols employed, along hash-encoded encrypted credentials enhanced protection.

Language: Английский

Hierarchical Resources Management System for Internet of Things-Enabled Smart Cities DOI Creative Commons

Christoforos Papaioannou,

Asimina Dimara, Alexios Papaioannou

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(3), P. 616 - 616

Published: Jan. 21, 2025

The efficient management of IoT systems is fundamental to advancing smart cities while enabling the seamless integration technologies that enhance urban sustainability and resilience. This paper introduces a Hierarchical Resource Management System (HRMS) tailored for IoT-enabled cities, emphasizing decentralized architecture at building level scaling up city-wide applications. At its core, system integrates Adaptive Resilient Node (ARN), designed autonomously manage energy resources ensure continuous operation through self-healing capabilities. study outlines HRMS architecture, operational workflows, core functionalities, demonstrating how hierarchical framework supports real-time decision-making, fault tolerance, scalable resource allocation. proposed system’s lightweight inter-node communication enhances workload balancing responsiveness, addressing critical challenges in management. Experimental evaluations show achieves 50% improvement efficiency 30% reduction downtime across various environments, highlighting transformative potential sustainable resilient growth.

Language: Английский

Citations

0
MAS-DR: An ML-Based Aggregation and Segmentation Framework for Residential Consumption Users to Assist DR Programs DOI Open Access
Petros Tzallas, Alexios Papaioannou, Asimina Dimara

et al.

Sustainability, Journal Year: 2025, Volume and Issue: 17(4), P. 1551 - 1551

Published: Feb. 13, 2025

The increasing complexity of energy grids, driven by rising demand and unpredictable residential consumption, highlights the need for efficient response (DR) strategies data-driven services. This paper proposes a machine learning-based framework DR that clusters users based on their consumption patterns categorizes individual usage into distinct profiles using K-means, Hierarchical Agglomerative Clustering, Spectral DBSCAN. Key features such as statistical, temporal, behavioral characteristics are extracted, novel Household Daily Load (HDL) approach is used to identify groups. also includes context analysis detect daily variations peak periods users. High-impact users, identified anomalies frequent spikes or grid instability risks IsolationForest kNN, flagged. Additionally, classification service integrates new segmented portfolio. Experiments real-world datasets demonstrate framework’s effectiveness in helping managers design tailored programs.

Language: Английский

Citations

0
Machine Learning for Leadership in Energy and Environmental Design Credit Targeting: Project Attributes and Climate Analysis Toward Sustainability DOI Open Access
Ali Mansouri,

Mohsen Naghdi,

Abdolmajid Erfani

et al.

Sustainability, Journal Year: 2025, Volume and Issue: 17(6), P. 2521 - 2521

Published: March 13, 2025

Achieving Leadership in Energy and Environmental Design (LEED) certification is a key objective for sustainable building projects, yet targeting LEED credit attainment remains challenge influenced by multiple factors. This study applies machine learning (ML) models to analyze the relationship between project attributes, climate conditions, outcomes. A structured framework was implemented, beginning with data collection from USGBC (LEED-certified projects) US NCEI (climate data), followed preprocessing steps. Three ML models—Decision Tree (DT), Support Vector Regression (SVR), XGBoost—were evaluated, XGBoost emerging as most effective due its ability handle large datasets, manage missing values, provide interpretable feature importance scores. The results highlight strong influence of version type, demonstrating how criteria project-specific characteristics shape sustainability Additionally, factors, particularly cooling degree days (CDD) precipitation (PRCP), play crucial role determining attainment, underscoring regional environmental conditions. By leveraging techniques, this research offers data-driven approach optimizing strategies enhancing process. These insights pave way more informed decision-making green design policy, future opportunities refine predictive even greater accuracy impact.

Language: Английский

Citations

0
Simulation of Malfunctions in Home Appliances’ Power Consumption DOI Creative Commons
Alexios Papaioannou, Asimina Dimara,

Christoforos Papaioannou

et al.

Energies, Journal Year: 2024, Volume and Issue: 17(17), P. 4529 - 4529

Published: Sept. 9, 2024

Predicting errors in home appliances is crucial for maintaining the reliability and efficiency of smart homes. However, there a significant lack such data on appliance malfunctions that can be used developing effective anomaly detection models. This research paper presents novel approach simulating heterogeneous power consumption patterns. The proposed model takes normal patterns as input employs advanced algorithms to produce labeled anomalies, categorizing them based severity malfunctions. One main objectives this involves models accurately reproduce patterns, highlighting anomalies related major, minor, specific resulting dataset may serve valuable resource training specifically tailored detect diagnose these real-world scenarios. outcomes contribute significantly field environments. simulated datasets facilitate development predictive maintenance strategies, allowing early mitigation proactive not only improves lifespan but also enhances energy efficiency, thereby reducing operational costs environmental impact.

Language: Английский

Citations

0
A Secure IIoT Environment That Integrates AI-Driven Real-Time Short-Term Active and Reactive Load Forecasting with Anomaly Detection: A Real-World Application DOI Creative Commons
Md. Ibne Joha,

Md Minhazur Rahman,

Md Shahriar Nazim

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(23), P. 7440 - 7440

Published: Nov. 21, 2024

The Industrial Internet of Things (IIoT) revolutionizes both industrial and residential operations by integrating AI (artificial intelligence)-driven analytics with real-time monitoring, optimizing energy usage, significantly enhancing efficiency. This study proposes a secure IIoT framework that simultaneously predicts active reactive loads while also incorporating anomaly detection. system is optimized for deployment on an edge server, such as single-board computer (SBC), well cloud or centralized server. It ensures reliable smart data acquisition systems control, protective measures. We propose Temporal Convolutional Networks-Gated Recurrent Unit-Attention (TCN-GRU-Attention) model to predict loads, which demonstrates superior performance compared other conventional models. metrics load forecasting are 0.0183 Mean Squared Error (MSE), 0.1022 Absolute (MAE), 0.1354 Root (RMSE), forecasting, the 0.0202 0.1077 0.1422 (RMSE). Furthermore, we introduce Isolation Forest detection considers transient conditions appliances when identifying irregular behavior. very promising performance, average all using this being 95% Precision, 98% Recall, 96% F1 Score, nearly 100% Accuracy. To entire system, Transport Layer Security (TLS) Secure Sockets (SSL) security protocols employed, along hash-encoded encrypted credentials enhanced protection.

Language: Английский

Citations

0