An ensemble-based approach for short-term load forecasting for buildings with high proportion of renewable energy sources

Pramanik, Abrar Shahriar; Sepasi, Saeed; Nguyen, Tung-Lam; Roose, Leon

doi:10.1016/j.enbuild.2024.113996

Cited by 3 publications

(3 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interpolate A({t max }) 2 φ ′ (t max ) and A({t min }) 2 φ ′ (t min ) to obtain δ 1 (t) and δ 2 (t), respectively. The instantaneous frequencies φ ′ 1 (t) and φ ′ 2 (t) can be computed by Equations ( 5) and (6).…”

Section: Time-varying Filter-based Emdmentioning

confidence: 99%

See 1 more Smart Citation

A Deep Learning Approach Based on Novel Multi-Feature Fusion for Power Load Prediction

Xiao,

An,

Zhang

2024

Processes

View full text Add to dashboard Cite

Adequate power load data are the basis for establishing an efficient and accurate forecasting model, which plays a crucial role in ensuring the reliable operation and effective management of a power system. However, the large-scale integration of renewable energy into the power grid has led to instabilities in power systems, and the load characteristics tend to be complex and diversified. Aiming at this problem, this paper proposes a short-term power load transfer forecasting method. To fully exploit the complex features present in the data, an online feature-extraction-based deep learning model is developed. This approach aims to extract the frequency-division features of the original power load on different time scales while reducing the feature redundancy. To solve the prediction challenges caused by insufficient historical power load data, the source domain model parameters are transferred to the target domain model utilizing Kendall’s correlation coefficient and the Bayesian optimization algorithm. To verify the prediction performance of the model, experiments are conducted on multiple datasets with different features. The simulation results show that the proposed model is robust and effective in load forecasting with limited data. Furthermore, if real-time data of new energy power systems can be acquired and utilized to update and correct the model in future research, this will help to adapt and integrate new energy sources and optimize energy management.

show abstract

Section: Time-varying Filter-based Emdmentioning

confidence: 99%

“…Ref. [6] proposed an ensemble-based short-term load forecasting method tailored for buildings, which was applied to predict future energy demands and manage the intermittency and variability of renewable energy sources.…”

Section: Introduction 1background and Challengesmentioning

confidence: 99%

A Deep Learning Approach Based on Novel Multi-Feature Fusion for Power Load Prediction

Xiao,

An,

Zhang

2024

Processes

View full text Add to dashboard Cite

show abstract

“…Global climate change and increasing demand for energy have led to a dramatic transformation from conventional energy to renewable energy systems [1][2][3]. Over the last 20 years, solar photovoltaics (PVs) has witnessed rapid growth as the most widely applied form of renewable energy source (RES) [4,5].…”

Section: Introductionmentioning

confidence: 99%

Operational Strategy of a DC Inverter Heat Pump System Considering PV Power Fluctuation and Demand-Side Load Characteristics

Li,

Lu,

Sun

et al. 2024

Buildings

View full text Add to dashboard Cite

With the increase in application of solar PV systems, it is of great significance to develop and investigate direct current (DC)-powered equipment in buildings with flexible operational strategies. A promising piece of building equipment integrated in PV-powered buildings, DC inverter heat pump systems often operate with strategies either focused on the power supply side or on the building demand side. In this regard, the aim of this study was to investigate the operational strategy of a DC inverter heat pump system for application in an office building with a PV power system. Firstly, the PV power fluctuation and demand-side load characteristics were analyzed. Then, a series of heat transfer and heat pump system models were developed. A reference building model was developed for simulating the performance of the system. A control logic of the DC inverter heat pump was proposed with a certain level of flexibility and capability considering both the characteristics of the PV power generation and the demand-side heating load. MATLAB/Simulink 2021 software was used for simulation. The simulation results show that the DC inverter heat pump is able to regulate its own power according to the change signal of the bus voltage such that the DC distribution network can achieve power balance and thus provide enough energy for a room. This study can provide a reference for developing flexible operational strategies for DC inverter heat pump systems. The proposed strategy can also help to improve the systems’ performance when they are applied in buildings with distributed PV systems.

show abstract

A comparative analysis of machine learning techniques for building cooling load prediction

Havaeji,

Ghanizadeh Anganeh,

Torbat Esfahani

et al. 2024

J Build Rehabil

View full text Add to dashboard Cite

An ensemble-based approach for short-term load forecasting for buildings with high proportion of renewable energy sources

Cited by 3 publications

References 49 publications

A Deep Learning Approach Based on Novel Multi-Feature Fusion for Power Load Prediction

A Deep Learning Approach Based on Novel Multi-Feature Fusion for Power Load Prediction

Operational Strategy of a DC Inverter Heat Pump System Considering PV Power Fluctuation and Demand-Side Load Characteristics

A comparative analysis of machine learning techniques for building cooling load prediction

Contact Info

Product

Resources

About