An improved encoder-decoder-based CNN model for probabilistic short-term load and PV forecasting

Jurado, Mauro; Samper, Mauricio E.; Rosés, Rodolfo

doi:10.1016/j.epsr.2023.109153

Cited by 17 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Forecasting: Predicting several variables in the B2Gintegrated systems domain in different time-frames serving as an input for most of the other services. We decompose the forecasting service into consumption (i.e., appliances [107]- [110], buildings [111]- [114], and netload [115]- [118]), price [119]- [122], and local production either through forecasting variables (i.e., irradiance [123]- [126] or wind speed [127]- [130]) or directly the power (i.e., wind [135]- [138] and PV [131]- [134]).…”

Section: Business-related Dimensionmentioning

confidence: 99%

Data-Driven Analytics for Reliability in the Buildings-to-Grid Integrated System Framework: A Systematic Text-Mining-Assisted Literature Review and Trend Analysis

Bachoumis,

Mylonas,

Plakas

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Data-driven machine learning-based methods have provided immense capabilities, revolutionizing sectors like the Buildings-to-grid (B2G) integrated system. Since the penetration rate of distributed energy resources increases towards a net-zero emissions power system, so does the need for advanced services that ensure B2G-integrated system reliability. The convergence of advancements in machine learning, computational resources at the entire cloud-edge continuum, and large datasets from sensing devices enable the development of these data-driven energy analytics services. This work conducts a systematic text-mining-based literature review to examine the diverse range and trends of machine learning methods used to enhance reliability in B2G-integrated systems. While traditional manual sampling and analysis approaches have limited the effectiveness of previous literature review papers in this field, this systematic literature review work aims to synthesize and summarize the existing body of research more efficiently and effectively. To achieve this, this study collected almost 10,500 papers from Scholar and Scopus databases. It employed text-mining-assisted BERTopic-based topic modelling and statistical trend analysis techniques to uncover semantic patterns and explore the temporal evolution of research themes. A two-dimensional taxonomy was derived to analyze the technical papers from a business and machine learning-related perspective. By quantifying the temporal trends within these topics, the study unveiled insights about the state-of-the-art analytics that ensure reliability in the B2G-integrated system domain while proposing future research directions.

show abstract

Section: Business-related Dimensionmentioning

confidence: 99%

Data-Driven Analytics for Reliability in the Buildings-to-Grid Integrated System Framework: A Systematic Text-Mining-Assisted Literature Review and Trend Analysis

Bachoumis,

Mylonas,

Plakas

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…However, including PV-DG behind-the-meter makes net load forecasting more complex, particularly at higher levels of spatial granularity (e.g., distribution transformers), as seen in previous studies [45,46]. To overcome the aforementioned complexity, in this work, we use a short-term net load forecasting model developed in [47] to estimate the input data for the DOP, i.e., the hourly nodal injection powers observed behind-the-meter of the MV/LV distribution transformers. It is essential to note that each node in the system can have only load or net load; however, the datadriven model can provide accurate results for either case.…”

Section: Nodal Injection Power Forecastsmentioning

confidence: 99%

“…It is essential to note that each node in the system can have only load or net load; however, the datadriven model can provide accurate results for either case. More detailed information on model aspects, including the utilized data, implementation specifics, and hyperparameter fitting process, is available in [47,48]. We refer readers to [47] for a comprehensive review of this innovative model.…”

Section: Nodal Injection Power Forecastsmentioning

confidence: 99%

See 1 more Smart Citation

Day-Ahead Operational Planning for DisCos Based on Demand Response Flexibility and Volt/Var Control

Jurado,

Salazar,

Samper

et al. 2023

Energies

Self Cite

View full text Add to dashboard Cite

Considering the integration of distributed energy resources (DER) such as distributed generation, demand response, and electric vehicles, day-ahead scheduling plays a significant role in the operation of active distribution systems. Therefore, this article proposes a comprehensive methodology for the short-term operational planning of a distribution company (DisCo), aiming to minimize the total daily operational cost. The proposed methodology integrates on-load tap changers, capacitor banks, and flexible loads participating in demand response (DR) to reduce losses and manage congestion and voltage violations, while considering the costs associated with the operation and use of controllable resources. Furthermore, to forecast PV output and load demand behind the meter at the MV/LV distribution transformer level, a short-term net load forecasting model using deep learning techniques has been incorporated. The proposed scheme is solved through an efficient two-stage strategy based on genetic algorithms and dynamic programming. Numerical results based on the modified IEEE 13-node distribution system and a typical 37-node Latin American system validate the effectiveness of the proposed methodology. The obtained results verify that, through the proposed methodology, the DisCo can effectively schedule its installations and DR to minimize the total operational cost while reducing losses and robustly managing voltage and congestion issues.

show abstract

“…The aim of this paper is to determine which load forecasting (LF) technique is most suitable for specific applications in smart grids (SG). Reference [35] proposes a short‐term load forecasting model that considers load consumption and distributed PV generation behind the meter. This model is based on an efficient deep‐learning network.…”

Section: Introductionmentioning

confidence: 99%

Short‐term load and spinning reserve prediction based on LSTM and ANFIS with PSO algorithm

Ferdosian,

Abdi,

Karimi

et al. 2024

The Journal of Engineering

View full text Add to dashboard Cite

With the increase in population and the growth of technology, the load demand has increased and major changes in spinning reserve are unavoidable. Short‐term forecasting to hourly predict the required load and spinning reserve is of great importance. All of the power system studies in planning and operation fields are depend on short‐term hourly load forecasting. In this work, the problem of load forecasting and spinning reserve based on deep learning (DL) algorithms and traditional methods is investigated with the help of the proposed information combination system. The proposed method tries to reduce the weaknesses of the stated methods and increase the accuracy of the predicted signal. First, short‐term predicting of load and spinning reserve is performed using a combination of adaptive network‐based fuzzy inference system (ANFIS) and meta‐heuristic algorithms including differential evolution (DE), genetic algorithm (GA), and particle swarm optimization (PSO). The ANFIS‐PSO is selected as the best ANFIS combination in load and spinning reserve prediction with a lower error criterion than other methods. Also, the long short‐term memory (LSTM) network can provide good accuracy for load and spinning reserve forecasting. Therefore, the combination of ANFIS‐PSO and LSTM is used to reduce the average error and error variance.

show abstract

An improved encoder-decoder-based CNN model for probabilistic short-term load and PV forecasting

Cited by 17 publications

References 26 publications

Data-Driven Analytics for Reliability in the Buildings-to-Grid Integrated System Framework: A Systematic Text-Mining-Assisted Literature Review and Trend Analysis

Data-Driven Analytics for Reliability in the Buildings-to-Grid Integrated System Framework: A Systematic Text-Mining-Assisted Literature Review and Trend Analysis

Day-Ahead Operational Planning for DisCos Based on Demand Response Flexibility and Volt/Var Control

Short‐term load and spinning reserve prediction based on LSTM and ANFIS with PSO algorithm

Contact Info

Product

Resources

About