Quantum support vector machine for forecasting house energy consumption: a comparative study with deep learning models

Journal of Cloud Computing Advances Systems and Applications, Journal Year: 2024, Volume and Issue: 13(1)

Published: May 20, 2024

Abstract The Smart Grid operates autonomously, facilitating the smooth integration of diverse power generation sources into grid, thereby ensuring a continuous, reliable, and high-quality supply electricity to end users. One key focus within realm smart grid applications is Home Energy Management System (HEMS), which holds significant importance given fluctuating availability dynamic nature loading conditions. This paper presents an overview HEMS methodologies utilized for load forecasting. It introduces novel approach employing Quantum Support Vector Machine (QSVM) predicting periodic consumption, leveraging AMPD2 dataset. In establishment microgrid, various factors such as energy consumption patterns household appliances, solar irradiance, overall are taken account in dataset creation. forecasting Systems stands out from other methods due its unique capabilities. Unlike traditional methods, QSVM leverages quantum computing principles handle complex nonlinear patterns. demonstrates superior accuracy by effectively capturing intricate relationships data, leading more precise predictions. Its ability adapt datasets produce significantly low error values, RMSE MAE, showcases efficiency grids. Moreover, model’s exceptional flexibility performance, evidenced achieving 97.3% on challenging like AMpds2, highlight distinctive edge over conventional techniques, making it promising solution enhancing HEMS.The article provides brief summary demonstrating comparing them with deep learning models showcase efficacy proposed algorithms.

Language: Английский

---

Multi-step ahead forecasting for electric power load using an ensemble model

Expert Systems with Applications, Journal Year: 2022, Volume and Issue: 211, P. 118649 - 118649

Published: Aug. 24, 2022

Language: Английский

---

A Deep Learning Approach for Peak Load Forecasting: A Case Study on Panama

Energies, Journal Year: 2021, Volume and Issue: 14(11), P. 3039 - 3039

Published: May 24, 2021

Predicting the future peak demand growth becomes increasingly important as more consumer loads and electric vehicles (EVs) start connecting to grid. Accurate forecasts will enable energy suppliers meet reliably. However, this is a challenging problem since very nonlinear. This study addresses research question of how deep learning methods, such convolutional neural networks (CNNs) long-short term memory (LSTM) can provide better support these areas. The goal build suitable forecasting model that accurately predict demand. Several data from 2004 2019 was collected Panama’s power system validate study. Input features residential consumption monthly economic index were considered for predicting First, we introduced three different CNN architectures which multivariate CNN, CNN-LSTM multihead CNN. These then benchmarked against LSTM. We found CNNs outperformed LSTM, with being best performing model. To our initial findings, evaluated robustness models Gaussian noise. demonstrated far superior than LSTM spatial-temporal time series data.

Language: Английский

---

Digital twin modeling for district heating network based on hydraulic resistance identification and heat load prediction

Energy, Journal Year: 2023, Volume and Issue: 288, P. 129726 - 129726

Published: Dec. 1, 2023

Language: Английский

---

Optimizing home energy management: Robust and efficient solutions powered by attention networks

Heliyon, Journal Year: 2024, Volume and Issue: 10(4), P. e26397 - e26397

Published: Feb. 1, 2024

This paper explores the integration of attention networks in realm home energy management systems (HEMS) to enhance robustness and efficiency consumption optimization. With growing demand for smart grid technologies, need achieve side response becomes paramount. The proposed solution leverages dynamically allocate significance various aspects patterns, considering diverse load types dynamic loading scenarios present households. In this investigation, we focus on AMpds2 dataset, characterized by intricate assess its performance across time series forecasting methodologies, including (RNN), (LSTM), (TCN), transformers. Multiple methodologies undergo evaluation using hyperparameter combinations. Evaluation metrics, specifically (RMSE) (MAE), are employed. Advanced optimizers such as (Adam) (Adamax) applied, activation functions, sigmoid, linear, tanh, ReLU, implemented. A comprehensive analysis involves 16 combinations four distinct models. Through meticulous scrutiny, it is determined that utilization transformers patterns results a 4% increase accuracy, elucidated section. implementation study carried out Python 3.2 platform, matplotlib library employed visualize comparison between actual predicted data.

Language: Английский

---

Analysis of aggregated load consumption forecasting in short, medium and long term horizons using Dynamic Mode Decomposition

Energy Reports, Journal Year: 2024, Volume and Issue: 12, P. 1000 - 1013

Published: July 10, 2024

Language: Английский

---

Unhulled rice prices forecast at farmer level for development of Indonesian sustainable local production

IOP Conference Series Earth and Environmental Science, Journal Year: 2025, Volume and Issue: 1488(1), P. 012114 - 012114

Published: April 1, 2025

Abstract Rice with husks on is known as unhulled rice. Determining rice price involves a few important parties, including the government, BULOG, farmers, distributors, millers, and consumers. BULOG (Badan Urusan Logistik) or Indonesian Agency for Logistics Affairs in Indonesia) plays significant role firm that regulates stability of rice/ Indonesia. They purchase from farmers distribute it based set by government. The goal this research to develop model can predict prices while taking farmer prosperity into account. Farmers contend government purchased excessively low, whilst production expenses are rising concurrently. time series approach Holt-Winters, (S)ARIMA(X), ETS (Error, Trend, Season) utilised select best forecast three variables Gabah Kering Panen (GKP) Dry Unhulled Rice, Giling (GKG), Harga Pembelian Pemerintah (HPP) Government Purchased Price . To improve outcome prediction, forecasting will be analysed conjunction market price.

Language: Английский

---

Forecasting highly fluctuating electricity load using machine learning models based on multimillion observations

Advanced Engineering Informatics, Journal Year: 2022, Volume and Issue: 53, P. 101707 - 101707

Published: Aug. 1, 2022

Language: Английский

---

Forecasting Long-Term Electricity Consumption in Saudi Arabia Based on Statistical and Machine Learning Algorithms to Enhance Electric Power Supply Management

Energies, Journal Year: 2023, Volume and Issue: 16(4), P. 2035 - 2035

Published: Feb. 18, 2023

This study aims to develop statistical and machine learning methodologies for forecasting yearly electricity consumption in Saudi Arabia. The novelty of this include (i) determining significant features that have a considerable influence on consumption, (ii) utilizing Bayesian optimization algorithm (BOA) enhance the model’s hyperparameters, (iii) hybridizing BOA with algorithms, viz., support vector regression (SVR) nonlinear autoregressive networks exogenous inputs (NARX), modeling individually long-term (iv) comparing their performances widely used classical time-series integrated moving average (ARIMAX) regard accuracy, computational efficiency, generalizability, (v) future validation. population, gross domestic product (GDP), imports, refined oil products were observed be total coefficient determination R2 values all developed models are >0.98, indicating an excellent fit historical data. However, among three proposed models, BOA–NARX has best performance, improving accuracy (root mean square error (RMSE)) by 71% 80% compared ARIMAX BOA–SVR respectively. overall results confirm higher reliability methods can power system operators more accurately forecast ensure sustainability electric energy. also provide guidance helpful insights researchers understanding crucial research, emerging trends, new developments energy studies.

Language: Английский

---

An advanced kernel search optimization for dynamic economic emission dispatch with new energy sources

International Journal of Electrical Power & Energy Systems, Journal Year: 2024, Volume and Issue: 160, P. 110085 - 110085

Published: June 27, 2024

Language: Английский

---