Multi-Term Electrical Load Forecasting of Smart Cities Using a New Hybrid Highly Accurate Neural Network-Based Predictive Model

Smart Grids and Sustainable Energy, Год журнала: 2023, Номер 9(1)

Опубликована: Дек. 28, 2023

Язык: Английский

---

Net saving improvement of capacitor banks in power distribution systems by increasing daily size switching number: A comparative result analysis by artificial intelligence

The Journal of Engineering, Год журнала: 2024, Номер 2024(2)

Опубликована: Фев. 1, 2024

Abstract This paper studies the effect of number switching (NOS) per day capacitor banks on loss reduction in radial distribution systems. To this aim, daytime (more precisely, 24 h) is divided into different numbers time segments (equal to same NOS) for capacitors’ size switching. The resulting non‐linear programming with discontinuous derivatives (called DNLP) model solved subject related constraints. results reveal impact hourly further (namely 118.4435, 83.7856, and 101.738 MWh three IEEE systems) higher net savings (i.e. k$5.6067, k$4.2772, k$5.3542 systems compared daily Then, hyper‐tuned Random Forest trained based 69‐bus network, fine‐tuned by 10‐bus fitted 33‐bus network have an intelligent multi‐classification task highest accuracy. Numerical simulation, both classic parts, presented demonstrate performance DeepOptaCap. For final step, DeepOptaCast other models Light Gradient Boosting Method (LGBM), Decision Tree, XGBoost, regarding KPIs mean absolute percentage error, root squared coefficient determination model's superiority.

Язык: Английский

---

A Comprehensive Review of Machine Learning Models for Optimizing Wind Power Processes

Applied Sciences, Год журнала: 2025, Номер 15(7), С. 3758 - 3758

Опубликована: Март 29, 2025

Wind energy represents a solution for reducing environmental impact. For this reason, research studies the elements that propose optimizing wind production through intelligent solutions. Although there are address optimization of turbine performance or other indirectly related factors in production, remains topic insufficiently explored and synthesized literature. This how machine learning (ML) techniques can be applied to optimize production. aims study systematic applications ML identify analyze key stages optimized Through research, case highlighted by which methods proposed directly target issue power process turbines. From total 1049 articles obtained from Web Science database, most studied models context artificial neural networks, with 478 papers identified. Additionally, literature identifies 224 have random forest 114 incorporated gradient boosting about power. Among these, 60 specifically addressed aspect allows identification gaps The notes previous focused on forecasting, fault detection, efficiency. existing addresses indirect component performance. Thus, paper current discusses algorithms processes, future directions increasing efficiency turbines integrated predictive methods.

Язык: Английский

---

Two-stage meta-ensembling machine learning model for enhanced water quality forecasting

Journal of Hydrology, Год журнала: 2024, Номер 641, С. 131767 - 131767

Опубликована: Авг. 3, 2024

Язык: Английский

---

ResFaultyMan: An intelligent fault detection predictive model in power electronics systems using unsupervised learning isolation forest

Heliyon, Год журнала: 2024, Номер 10(15), С. e35243 - e35243

Опубликована: Июль 27, 2024

Язык: Английский

---

Voltage Controller Design for Offshore Wind Turbines: A Machine Learning-Based Fractional-Order Model Predictive Method

Fractal and Fractional, Год журнала: 2024, Номер 8(8), С. 463 - 463

Опубликована: Авг. 6, 2024

Integrating renewable energy sources (RESs), such as offshore wind turbines (OWTs), into the power grid demands advanced control strategies to enhance efficiency and stability. Consequently, a Deep Fractional-order Wind turbine eXpert system (DeepFWX) model is developed, representing hybrid proportional/integral (PI) fractional-order (FO) predictive random forest alternating current (AC) bus voltage controller designed explicitly for OWTs. DeepFWX aims address challenges associated with systems, focusing on achieving smooth tracking state estimation of AC voltage. Extensive comparative analyses were performed against other state-of-the-art intelligent models assess effectiveness DeepFWX. Key performance indicators (KPIs) MAE, MAPE, RMSE, RMSPE, R2 considered. Superior across all evaluated metrics was demonstrated by DeepFWX, it achieved MAE [15.03, 0.58], MAPE [0.09, 0.14], RMSE [70.39, 5.64], RMSPE [0.34, 0.85], well [0.99, 0.99] systems states [X1, X2]. The proposed approach anticipates capabilities FO modeling, control, algorithms achieve precise voltage, thereby enhancing overall stability OWTs in evolving sector integration.

Язык: Английский

---

NeuroQuMan: quantum neural network-based consumer reaction time demand response predictive management

Neural Computing and Applications, Год журнала: 2024, Номер 36(30), С. 19121 - 19138

Опубликована: Авг. 2, 2024

Язык: Английский

---

Design of a Dynamic Feedback LSTM Electricity Price Forecast of Smart Grids

Power systems, Год журнала: 2024, Номер unknown, С. 327 - 344

Опубликована: Янв. 1, 2024

Язык: Английский

---

DeepEMS: Multimodal optimal energy management of microgrid systems based on a hybrid multi‐stage machine learning model

The Journal of Engineering, Год журнала: 2024, Номер 2024(10)

Опубликована: Окт. 1, 2024

Abstract The effective management of microgrids is important towards transition to sustainable energy paradigm. By optimizing the utilization different sources, such as solar photovoltaic panels and storages, it improves reliability grid develops resiliency in dealing with challenges unexpected variations demand. To this end, proposed paper presents DeepEMS, a system developed manage through incorporation diverse intelligent algorithms. DeepEMS provides dynamic microgrid Bidirectional Long Short‐Term Memory (BiLSTM) networks, Sliding Linear Programming (SLP), Random Forest (RF). implementing these methodologies, can optimize consumption throughout by dynamically identifying coordinating needs various sources. achieves precise multimodal optimization facilitates integration storage systems, interactions, renewable sources (RES), demonstrated simulations data analytics. presented performance control, resource allocation, management, utilization. Furthermore, comparative analysis alternative models including XGBoost, Light GBM, RF, Decision Trees, consistently higher measured several key indicators (KPIs).

Язык: Английский

---

Hybrid emerging model predictive data-driven forecasting of three-phase electrical signals of photovoltaic systems using GBR-LSTM

e-Prime - Advances in Electrical Engineering Electronics and Energy, Год журнала: 2024, Номер 8, С. 100549 - 100549

Опубликована: Апрель 23, 2024

In numerous industrial contexts, precise analysis and forecasting of electrical signals within three-phase systems are indispensable. As a result, this work presents DeepPhase, hybrid framework that combines Long Short-Term Memory (LSTM) neural networks with gradient-boosted regression (GBR) to predict the current, voltage, power signals. The performance model is evaluated in comparison benchmark models, namely Bidirectional LSTM (BiLSTM), K-Nearest Neighbors (KNN), LSTM, which utilize essential Key Performance Indicators (KPIs). demonstrated by its highest Coefficient Determination (R2) 0.999, Mean Absolute Error (MAE) 6.94 × 10−5, Percentage (MAPE) 0.07%, Root Square (RMSE) 0.000156, DeepPhase consistently exhibits predictive precision. For Three-Phase Current, MAE 2.13 10−3, MAPE 0.01%, RMSE 0.062432, R2 0.960596; for Voltage, 9.52E-03, 0.03%, 0.014, 0.999. results study highlight effectiveness analyzing dynamics complex This has significant implications improving decision-making control strategies systems.

Язык: Английский

---