A Novel Interval Energy-Forecasting Method for Sustainable Building Management Based on Deep Learning

Duan, Yun

doi:10.3390/su14148584

Cited by 8 publications

(5 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For day-ahead forecasting, the 21 International Journal of Energy Research yearly model had substantially higher accuracy than the seasonal models, with an accuracy difference of 0.6% MAPE, despite requiring four times as much time. Thus, seasonal EfficientNetV2B0 and annual ResNet50V2 models were the most effective for hour-ahead and day-ahead forecasts, respectively (5) The hyperparameters of the best models for hourahead and day-ahead regional energy consumption forecasting, namely, EfficientNetV2B0 and ResNet50V2, respectively, were successfully optimized using the JS algorithm to produce the optimal models JS-EfficientNetV2B0 and JS-ResNet50V2. The optimal hybrid models had the highest accuracy values among all the tested models, with a MAPE range of 0.98-1.12% for the seasonal hour-ahead JS-EfficientNetV2B0 models and MAPE of 4.13% for the annual day-ahead ResNet50V2 model.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Forecasting Regional Energy Consumption via Jellyfish Search-Optimized Convolutional-Based Deep Learning

Chou

Nguyen

2023

International Journal of Energy Research

View full text Add to dashboard Cite

The energy sector must achieve a delicate balance between energy supply and demand. Highly accurate energy consumption forecasts can help plant operators achieve this goal. In this study, various techniques from three artificial intelligence categories, namely, convolutional neural networks (CNNs), machine learning (ML), and time-series deep learning (DL), were applied to predict short-term regional energy consumption from a power company. An image conversion process was proposed to utilize the powerful image-processing capabilities of CNNs, in which numerical matrices of input values created by the sliding-window technique are encoded into two-dimensional grayscale images as input for CNN models. The proposed method outperformed conventional numerical input methods. Then, the best ML and time-series DL models were combined into ensemble models with ImageNet-winning CNN architectures based on the rationale of utilizing the strengths of each approach and compensating for their limitations. However, according to the numerical experiments for the regional energy consumption prediction, the ensemble models had lower performance than CNNs alone. Various leading models performing single-step or multistep forecasting and models that use seasonal or annual data were constructed. The performance of all the constructed models was evaluated, and the most efficient models were determined as proposed models. Finally, a nature-inspired optimization algorithm, Jellyfish Search (JS), was used to fine-tune the proposed models’ hyperparameters to minimize prediction error. The results revealed that the fine-tuning of hyperparameters via the JS algorithm significantly enhanced the precision of the CNN models, resulting in a mean absolute percentage error (MAPE) improvement range of 4.4% to 17.5% compared to the default models. The proposed models can help utilities plan daily power allocation and match supply and demand to maintain a stable power system.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Energy consumption forecasts can be divided into three categories based on the time horizon [5]: long-term estimates of one year to one decade, medium-term forecasts of several weeks to months, and short-term forecasts of one hour to one week. Each category has a specific function.…”

Section: Introductionmentioning

confidence: 99%

Forecasting Regional Energy Consumption via Jellyfish Search-Optimized Convolutional-Based Deep Learning

Chou

Nguyen

2023

International Journal of Energy Research

View full text Add to dashboard Cite

show abstract

“…On the other hand, regional wind power forecasts using QR neural networks have been investigated in [113], where the authors used ramp functions to avoid the crossing of multiple quantiles. Similarly, LSTM integrated with penalised QR has been implemented in [114] to obtain probabilistic load forecasts in terms of PI. Deep Gaussian processes : Deep Gaussian processes involve stacking of Gaussian processes as in the layers of neural networks. Each Gaussian process layer works as a single layer neural network.…”

Section: Probabilistic Techniquesmentioning

confidence: 99%

Energy forecasting in smart grid systems: recent advancements in probabilistic deep learning

Kaur

Islam

Mahmud

et al. 2022

IET Generation Trans & Dist

View full text Add to dashboard Cite

Energy forecasting plays a vital role in mitigating challenges in data rich smart grid (SG) systems involving various applications such as demand-side management, load shedding, and optimum dispatch. Managing efficient forecasting while ensuring the least possible prediction error is one of the main challenges posed in the grid today, considering the uncertainty in SG data. This paper presents a comprehensive and application-oriented review of state-of-the-art forecasting methods for SG systems along with recent developments in probabilistic deep learning (PDL). Traditional point forecasting methods including statistical, machine learning (ML), and deep learning (DL) are extensively investigated in terms of their applicability to energy forecasting. In addition, the significance of hybrid and data preprocessing techniques to support forecasting performance is also studied. A comparative case study using the Victorian electricity consumption in Australia and American electric power (AEP) datasets is conducted to analyze the performance of deterministic and probabilistic forecasting methods. The analysis demonstrates higher efficacy of DL methods with appropriate hyper-parameter tuning when sample sizes are larger and involve nonlinear patterns. Furthermore, PDL methods are found to achieve at least 60% lower prediction errors in comparison to other benchmark DL methods. However, the execution time increases significantly for PDL methods due to large sample space and a tradeoff between computational performance and forecasting accuracy needs to be maintained.

show abstract

“…The model can effectively capture the portion of daily load profiles caused by seasonal variations [38]. The methodology proposed in [39] is based on the long short-term memory (LSTM) model and penalized quantile regression (PQR). A comprehensive analysis for a time period of a year is conducted using the proposed method, and back propagation neural networks (BPNN), support vector machine (SVM), and random forest are applied as reference models [39].…”

Section: Literature Reviewmentioning

confidence: 99%

“…The methodology proposed in [39] is based on the long short-term memory (LSTM) model and penalized quantile regression (PQR). A comprehensive analysis for a time period of a year is conducted using the proposed method, and back propagation neural networks (BPNN), support vector machine (SVM), and random forest are applied as reference models [39]. In [40] an unsupervised multidimensional feature learning forecasting model proposed, named Multi DBN-T, based on a deep belief network and transformer encoder to accurately forecast short-term power load demand and implement power generation planning and scheduling [40].…”

Section: Literature Reviewmentioning

confidence: 99%

Long-Term Electricity Demand Forecasting in the Steel Complex Micro-Grid Electricity Supply Chain—A Coupled Approach

et al. 2022

View full text Add to dashboard Cite

Demand forecasting produces valuable information for optimal supply chain management. The basic metals industry is the most energy-intensive industries in the electricity supply chain. There are some differences between this chain and other supply chains including the impossibility of large-scale energy storage, reservation constraints, high costs, limitations on electricity transmission lines capacity, real-time response to high-priority strategic demand, and a variety of energy rates at different hours and seasons. A coupled demand forecasting approach is presented in this paper to forecast the demand time series of the metal industries microgrid with minimum available input data (only demand time series). The proposed method consists of wavelet decomposition in the first step. The training subsets and the validation subsets are used in the training and fine-tuning of the LSTM model using the ELATLBO method. The ESC dataset used in this study for electrical demand forecasting includes 24-h daily over 40 months from 21 March 2017, to 21 June 2020. The obtained results have been compared with the results of Support Vector Machine (SVM), Decision Tree, Boosted Tree, and Random Forest forecasting models optimized using the Bayesian Optimization (BO) method. The results show that performance of the proposed method is well in demand forecasting of the metal industries.

show abstract

A Novel Interval Energy-Forecasting Method for Sustainable Building Management Based on Deep Learning

Cited by 8 publications

References 45 publications

Forecasting Regional Energy Consumption via Jellyfish Search-Optimized Convolutional-Based Deep Learning

Forecasting Regional Energy Consumption via Jellyfish Search-Optimized Convolutional-Based Deep Learning

Energy forecasting in smart grid systems: recent advancements in probabilistic deep learning

Long-Term Electricity Demand Forecasting in the Steel Complex Micro-Grid Electricity Supply Chain—A Coupled Approach

Contact Info

Product

Resources

About