Soil water erosion susceptibility assessment using deep learning algorithms

Journal of Hydrology, Journal Year: 2023, Volume and Issue: 618, P. 129229 - 129229

Published: Feb. 6, 2023

Accurate assessment of soil water erosion (SWE) susceptibility is critical for reducing land degradation and loss, mitigating the negative impacts on ecosystem services, quality, flooding infrastructure. Deep learning algorithms have been gaining attention in geoscience due to their high performance flexibility. However, an understanding potential these provide fast, cheap, accurate predictions lacking. This study provides first quantification this potential. Spatial are made using three deep – Convolutional Neural Network (CNN), Recurrent (RNN) Long-Short Term Memory (LSTM) Iranian catchment that has historically experienced severe erosion. Through a comparison predictive analysis driving geo-environmental factors, results reveal: (1) elevation was most effective variable SWE susceptibility; (2) all developed models had good prediction performance, with RNN being marginally superior; (3) maps revealed almost 40 % highly or very susceptible 20 moderately susceptible, indicating need control catchment. algorithms, catchments can potentially be predicted accurately ease readily available data. Thus, reveal great use data poor catchments, such as one studied here, especially developing nations where technical modeling skills processes occurring may

Language: Английский

---

Implementation of real-time optimal load scheduling for IoT-based intelligent smart energy management system using new decisive algorithm

Journal of Electrical Systems and Information Technology, Journal Year: 2025, Volume and Issue: 12(1)

Published: March 14, 2025

Abstract This paper presents the implementation of a real-time optimal load scheduling system for an IoT-based intelligent smart energy management (SEMS) using novel decisive algorithm. The increasing use electrical equipment by consumers often leads to mismatch between demand and supply, posing significant challenges sector. proposed addresses these optimizing distribution enhancing efficiency through advanced demand-side techniques. By leveraging data from IoT sensors incorporating user preferences, new algorithm dynamically adjusts power consumption avoid peak-hour overloads, thus preventing widespread outages. Experimental results demonstrate that effectively reduces overall while maintaining comfort costs. innovative approach controlled partial shedding based on consumer priorities ensures balanced resilient supply. study highlights potential algorithms in transforming practices providing sustainable solutions future.

Language: Английский

---

A literature review on an IoT-based intelligent smart energy management systems for PV power generation

Hybrid Advances, Journal Year: 2023, Volume and Issue: 5, P. 100136 - 100136

Published: Dec. 29, 2023

Renewable energy is the most dependable and universally acknowledged way of meeting world's expanding needs. In order to optimize solar generation, particular focus must be paid both application maintenance. IoT-based monitoring system proposals have been made in collect analyze data, which will allow for performance prediction reliable power output. Demand-side management's primary objective maximize economical utilization renewable resources without sacrificing overall efficiency. areas where use strongly reliant on grid, an intelligent management may effectively regulate usage. With cloud computing, opportunities problems driven out by growing grids successfully handled. This study examines role that systems play research practical industrial practises, acknowledging as stakeholders this undertaking. The investigation closely looks at a number IoT-related topics relation production. addition providing guidance upcoming academics field, it also lists possible future uses IoT, inspiring them further field's present understanding provide new ideas. Providing thorough analysis smart architecture purpose.

Language: Английский

---

Design and deployment of a novel decisive algorithm to enable real-time optimal load scheduling within an intelligent smart energy management system based on IoT

Energy Reports, Journal Year: 2024, Volume and Issue: 12, P. 579 - 592

Published: June 27, 2024

Consumers routinely use electrical devices, leading to a disparity between consumer demand and the supply side significant concern for energy sector. Implementing demand-side management can enhance efficiency mitigate substantial supply-side shortages. Current practices focus on reducing power consumption during peak hours, enabling decrease in overall electricity costs without sacrificing usage. To tackle mentioned challenges maintain system equilibrium, it is essential develop flexible portable system. Introducing an intelligent could pre-empt outages by implementing controlled partial load shedding based preferences. During response event, adapts imposing maximum limit, considering various scenarios adjusting appliance priorities. Experimental work, incorporating user comfort levels, sensor data, usage times, conducted using Smart Energy Management Systems (SEMS) integrated with cost-optimization algorithms.

Language: Английский

---

Short-term photovoltaic power prediction model based on feature construction and improved Transformer

Energy, Journal Year: 2025, Volume and Issue: unknown, P. 135213 - 135213

Published: Feb. 1, 2025

Language: Английский

---

A hybrid Autoformer framework for electricity demand forecasting

Energy Reports, Journal Year: 2023, Volume and Issue: 9, P. 3800 - 3812

Published: March 6, 2023

Electricity demand forecasting is of great significance to the electricity system and residents' life, but it difficult forecast series because influence cyclical factors. also faces problem small data amounts. Therefore, we need design a model that less affected by volume can cope with complex series. Based on Autoformer model, this paper establishes novel framework excellent performance. In part preprocessing, multiple linear regression 10 variables Bootstrap processing are added. Auto-Correlation mechanism modified better extract historical nonlinear characteristics from different time spans. Using framework, further analyze impact working days seasonal changes in Taixing City New South Wales. addition, propose new method, which adjust original sequence according actual situation. The experimental results show method achieve good precision forecasting. Taking China Wales Australia as examples, performance proposed than Autoformer, Reformer, Informer, other mainstream models. indexes our test set MAE: 35.05, RMSE: 47.28, MAPE: 1.63 193.17, 239.96, 2.43 NSW.

Language: Английский

---

Reinforcement Learning-Based Prediction of Alarm Significance in Marginally Operating Electrical Grids

IEEE Transactions on Industrial Informatics, Journal Year: 2024, Volume and Issue: 20(4), P. 6510 - 6521

Published: Jan. 12, 2024

The increasing electrical load strains the grid, leading to frequent overload alarms and reduced reliability. Moreover, as grid expands, its maintenance poses greater challenges, underscoring necessity for smart investment strategies. Rather than solely focusing on expanding infrastructure, an alternative approach involves utilizing software-based solutions, which result in predictive automated systems. Conversely, due resource constraints, it becomes crucial assess significance of network prioritize allocation effectively. In this article, a novel framework is proposed predict marginal operating grids, existing infrastructure. A simple clustering model first introduced enhance scalability framework. Convolutional long short-term memory, convolutional neural network, recurrent some more deep learning models double Q-network Q-learning techniques are employed prediction task. Following that, virtual thresholds defined, wherein exceeding results alarm being raised. Chernoff–Hoeffding bound assign quantifying predicted deviations. Subsequently, expert observation alarms, input into particle swarm optimization algorithm fine-tune parameters bound. effectiveness method evaluated residential industrial loads within part Danish distribution network. showcase robustness contrast with other counterparts.

Language: Английский

---

IoT enabled Intelligent Energy Management System employing advanced forecasting algorithms and load optimization strategies to enhance renewable energy generation

Unconventional Resources, Journal Year: 2024, Volume and Issue: 4, P. 100101 - 100101

Published: Jan. 1, 2024

Effectively utilizing renewable energy sources while avoiding power consumption restrictions is the problem of demand-side management. The goal to develop an intelligent system that can precisely estimate availability and plan ahead for next day in order overcome this obstacle. Intelligent Smart Energy Management System (ISEMS) described work designed control usage a smart grid environment where significant quantity being introduced. proposed evaluates various predictive models achieve accurate forecasting with hourly day-ahead planning. When compared other models, Support Vector Machine (SVM) regression model based on Particle Swarm Optimization (PSO) seems have better performance accuracy. Then, using anticipated requirements, experimental setup ISEMS shown, its evaluated configurations considering features are prioritized associated user comfort. Furthermore, Internet Things (IoT) integration put into practice monitoring at end.

Language: Английский

---

Deep Learning in Cybersecurity: A Hybrid BERT–LSTM Network for SQL Injection Attack Detection

IET Information Security, Journal Year: 2024, Volume and Issue: 2024, P. 1 - 16

Published: April 5, 2024

In the past decade, cybersecurity has become increasingly significant, driven largely by increase in threats. Among these threats, SQL injection attacks stand out as a particularly common method of cyber attack. Traditional methods for detecting mainly rely on manually defined features, making detection outcomes highly dependent precision feature extraction. Unfortunately, approaches struggle to adapt sophisticated nature attack techniques, thereby necessitating development more robust strategies. This paper presents novel deep learning framework that integrates Bidirectional Encoder Representations from Transformers (BERT) and Long Short-Term Memory (LSTM) networks, enhancing attacks. Leveraging advanced contextual encoding capabilities BERT sequential data processing ability LSTM proposed model dynamically extracts word sentence-level subsequently generating embedding vectors effectively identify malicious query patterns. Experimental results indicate our achieves accuracy, precision, recall, F1 scores 0.973, 0.963, 0.962, 0.958, respectively, while ensuring high computational efficiency.

Language: Английский

---

Intelligent power management system for optimizing load strategies in renewable generation

Electrical Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 29, 2024

Language: Английский

---