Short-Term Load Forecasting for CCHP Systems Considering the Correlation between Heating, Gas and Electrical Loads Based on Deep Learning

Zhu, Ruijin; Guo, Weilin; Gong, Xuejiao

doi:10.3390/en12173308

Cited by 36 publications

(15 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To reduce overfitting, ensemble learning was employed to create independent predictions of multiple models and to use weighted averaged results [59,[95][96][97]99,113,115,[129][130][131][132][133][134]. Other measures against overfitting include the usage of incremental learning and dynamic neural networks, where the models are updated step by step during training phase [88,106,131,135] or restrictions on coefficients are implemented [136] as well as the introduction of dropout layers [137]. The adjustments of coefficients of the predicting variables in order to capture the essential properties of the training data and provide better generalization to yet unknown data points, is an important and widespread concept to avoid overfitting known as regularization.…”

Section: Measures For Improvement Of Accuracymentioning

confidence: 99%

Modeling Energy Demand—A Systematic Literature Review

et al. 2021

View full text Add to dashboard Cite

In this article, a systematic literature review of 419 articles on energy demand modeling, published between 2015 and 2020, is presented. This provides researchers with an exhaustive overview of the examined literature and classification of techniques for energy demand modeling. Unlike in existing literature reviews, in this comprehensive study all of the following aspects of energy demand models are analyzed: techniques, prediction accuracy, inputs, energy carrier, sector, temporal horizon, and spatial granularity. Readers benefit from easy access to a broad literature base and find decision support when choosing suitable data-model combinations for their projects. Results have been compiled in comprehensive figures and tables, providing a structured summary of the literature, and containing direct references to the analyzed articles. Drawbacks of techniques are discussed as well as countermeasures. The results show that among the articles, machine learning (ML) techniques are used the most, are mainly applied to short-term electricity forecasting on a regional level and rely on historic load as their main data source. Engineering-based models are less dependent on historic load data and cover appliance consumption on long temporal horizons. Metaheuristic and uncertainty techniques are often used in hybrid models. Statistical techniques are frequently used for energy demand modeling as well and often serve as benchmarks for other techniques. Among the articles, the accuracy measured by mean average percentage error (MAPE) proved to be on similar levels for all techniques. This review eases the reader into the subject matter by presenting the emphases that have been made in the current literature, suggesting future research directions, and providing the basis for quantitative testing of hypotheses regarding applicability and dominance of specific methods for sub-categories of demand modeling.

show abstract

Section: Measures For Improvement Of Accuracymentioning

confidence: 99%

Modeling Energy Demand—A Systematic Literature Review

et al. 2021

View full text Add to dashboard Cite

show abstract

“…LSTM and GRU are techniques built upon RNN. LSTM was the most used ANN approach in load forecasting, demonstrating better performance in different complex situations such as lowhigh-frequency components [53], probabilistic load forecasting [55], PV generation [66], CCHP (Combined Cooling, Heating, and Power) system [81], Hybrid energy systems, [87], etc. A combination of three ANNs, namely LSTM, BPNN, and DQN (Deep Q-Network), have been used for establishing a similar day selection based STLF model [40].…”

Section: B Different Ann Techniques In Deep Learning Based Load Forementioning

confidence: 99%

HSIC Bottleneck Based Distributed Deep Learning Model for Load Forecasting in Smart Grid With a Comprehensive Survey

et al. 2020

View full text Add to dashboard Cite

Load forecasting is a vital part of smart grids for predicting the required electrical power using artificial intelligence (AI). Deep learning is broadly used for load forecasting in the smart grid using the artificial neural network (ANN). Generally, computing the deep learning in the smart grid requires massive data aggregation or centralization and significant computational time. This paper presents a survey of deep learning-based load forecasting techniques from 2015 to 2020. This survey discusses the studies based on their deep learning techniques, Distributed Deep Learning (DDL) techniques, Back Propagation (BP) based works, and non-BP based works in the load forecasting process. Consequent to the survey, it was determined that data aggregation dependency would be beneficial for reducing computational time in load forecasting. Therefore, a conceptual model of DDL for smart grids has been presented, where the HSIC (Hilbert-Schmidt Independence Criterion) Bottleneck technique has been incorporated to provide higher accuracy.

show abstract

“…CNN combined with attention block is used to extract the effective characteristics of load influence factors to forecast the next hour's load. [25] uses the Pearson correlation coefficient to measure the time correlation between the current load and the historical load, analyze the coupling relationship between the heat, gas, and electric load, and forecast the electric cooling and heating loads of the CCHP system. Another method that also plays a positive role is based on MTL (Multi-Task Learning) forecasting, which processes information of different types of energy loads through MTL's sharing mechanism [26] and achieves more effective forecasting results than single-task learning.…”

Section: Introductionmentioning

confidence: 99%

Short-Term Electric Load Forecasting of Integrated Energy System Considering Nonlinear Synergy Between Different Loads

Wang

2021

IEEE Access

View full text Add to dashboard Cite

As an efficient form of energy utilization, an integrated energy system integrates oil, natural gas, coal, and other energy sources and converts them into electric, cooling, and heating for users through energy conversion devices. In this process, integrated energy service providers need to make energy conversion decisions based on users' demand information feedback. Therefore, there is uncertainty and coupling between the electric cooling and heating loads, making it difficult to forecast the loads accurately. Firstly, this paper analyzes the integrated energy system's energy consumption characteristics and the interaction mechanism between the supply and demand sides, which fundamentally explains the coupling relationship between different loads of the integrated energy system. Secondly, REC, DEC, REH, and DEH are constructed from electric cooling and heating loads. The relationship between electric load and cooling and heating load is analyzed by a scatter distribution diagram and maximum information coefficient method. The nonlinear correlation between electric load and cooling and heating loads is proved. Based on this, the integrated energy system's synergetic electric load forecasting formula reflecting the nonlinear synergistic effect between loads is proposed. Finally, based on stacking ensemble learning, an integrated energy system electric load forecasting model considering the nonlinear synergy between loads is established by integrating BP neural network, support vector regression, random forest, and gradient boosting decision tree. Through the experimental analysis of the Arizona State University Tempe campus's integrated energy system project, it is found that the effect of the synergistic quadratic forecasting is better than that of the primary forecasting. Besides, the MAPE of the quadratic synergistic forecasting formula is lower than that of the other two forms, indicating that the proposed synergistic electric load forecasting formula considering the nonlinear synergy between loads can improve the accuracy of electric load forecasting of the integrated energy system.INDEX TERMS energy consumption characteristics, integrated energy system, synergetic forecasting, Stacking ensemble learning.

show abstract

Short-Term Load Forecasting for CCHP Systems Considering the Correlation between Heating, Gas and Electrical Loads Based on Deep Learning

Cited by 36 publications

References 45 publications

Modeling Energy Demand—A Systematic Literature Review

Modeling Energy Demand—A Systematic Literature Review

HSIC Bottleneck Based Distributed Deep Learning Model for Load Forecasting in Smart Grid With a Comprehensive Survey

Short-Term Electric Load Forecasting of Integrated Energy System Considering Nonlinear Synergy Between Different Loads

Contact Info

Product

Resources

About