Towards next generation Internet of Energy system: Framework and trends

Energy and AI, Год журнала: 2023, Номер 14, С. 100306 - 100306

Опубликована: Окт. 1, 2023

The quickening propensity of growth within the areas information and communications technology energy networks has triggered emergence a central idea termed as Internet Energy (IoE). Such concept relates internet things, which is term used in describing usage sophisticated digital control devices with capability transmitting data via IT systems. an interconnected network being formed upcoming days through upgrades field intelligent systems to real-time optimization management. industry had sustained expansion, reaching IoE milestone continuing this cutting-edge power system, next generation IoE. A directional pathway from traditional system been conducted research work by addressing importance integrating smart transmission communication infrastructure, metering, pricing management scheme. detailed investigation respect technical angles, such architecture, on supply & demand side, protocol based fundamental elements essential technologies carried out indicate blueprint jurisdiction complexity. integration, security challenges may deviate performance that focused proper issues solutions. Finally, framework establish next-generation constructed future scopes insure higher resiliency, cyber-security stability.

Язык: Английский

---

Digital twin-enhanced predictive maintenance for indoor climate: A parallel LSTM-autoencoder failure prediction approach

Energy and Buildings, Год журнала: 2023, Номер 301, С. 113738 - 113738

Опубликована: Ноя. 10, 2023

Язык: Английский

---

Hybrid resampling and weighted majority voting for multi-class anomaly detection on imbalanced malware and network traffic data

Engineering Applications of Artificial Intelligence, Год журнала: 2023, Номер 128, С. 107568 - 107568

Опубликована: Ноя. 26, 2023

Язык: Английский

---

Early energy performance analysis of smart buildings by consolidated artificial neural network paradigms

Heliyon, Год журнала: 2024, Номер 10(4), С. e25848 - e25848

Опубликована: Фев. 1, 2024

The assessment of energy performance in smart buildings has emerged as a prominent area research driven by the increasing consumption trends worldwide. Analyzing attributes using optimized machine learning models been highly effective approach for estimating cooling load (CL) and heating (HL) buildings. In this study, an artificial neural network (ANN) is used basic predictor that undergoes optimization five metaheuristic algorithms, namely coati algorithm (COA), gazelle (GOA), incomprehensible but intelligible-in-time logics (IbIL), osprey (OOA), sooty tern (STOA) to predict CL HL residential building. are trained tested via Energy Efficiency dataset (downloaded from UCI Repository). A score-based ranking system built upon three accuracy evaluators including mean absolute percentage error (MAPE), root square (RMSE), percentage-Pearson correlation coefficient (PPCC) compare prediction models. Referring results, all demonstrated high (e.g., PPCCs >89%) predicting both HL. However, calculated final scores (43, 20, 39, 38, 10 36, 42, STOA, OOA, IbIL, GOA, COA, respectively) indicated STOA perform better than COA OOA. Moreover, comparison with various algorithms earlier literature showed provide more accurate solution. Therefore, use ANN these recommended practical early forecast optimizing design systems.

Язык: Английский

---

Multi-task deep learning for large-scale buildings energy management

Energy and Buildings, Год журнала: 2024, Номер 307, С. 113964 - 113964

Опубликована: Фев. 2, 2024

Язык: Английский

---