Solar forecasting by K-Nearest Neighbors method with weather classification and physical model

Liu, Zhao; Zhang, Ziang

doi:10.1109/naps.2016.7747859

Cited by 24 publications

(16 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed hybrid approach gives a mean absolute bias error (MABE) value of 42 W/m 2 and the RMSE value of 242 W/m 2 in the experimental results. In another study [26], researchers proposed a novel kNN‐based forecasting model considering NWP, solar irradiation input parameters, and physical model of PV units. This proposed model also implements weather condition classification to achieve more accurate forecasting results.…”

Section: Analysis and Resultsmentioning

confidence: 99%

Systematic literature review of photovoltaic output power forecasting

Başaran

Bozyiğit²,

Siano

et al. 2020

IET Renewable Power Generation

View full text Add to dashboard Cite

Since the harmful effects of climate warming on our planet were first observed, the use of renewable energy resources has been significantly increasing. Among the potential renewable energy sources, photovoltaic (PV) system installations keep continuously increasing world‐wide due to its economic and environmental contributions. Despite its significant benefits, the inherent variability of PV power generation due to meteorological parameters can cause power management/planning problems. Thus, forecasting of PV output data (directly or indirectly) in an accurate manner is a critical task to provide stability, reliability, and optimisation of the grid systems. In considering the literature reviewed, there are various research items utilizing PV output power forecasting. In this study, a systematic literature review based on the search of primary studies (published between 2010 and 2020), which forecast PV power generation using machine learning and deep learning methods, is reported. The studies are evaluated based on the PV material used, their approaches, generated outputs, data set used, and the performance evaluation methods. As a result, gaps and improvable points in the existing literature are revealed, and suggestions which include novelties are offered for future works.

show abstract

Section: Analysis and Resultsmentioning

confidence: 99%

Systematic literature review of photovoltaic output power forecasting

Başaran

Bozyiğit²,

Siano

et al. 2020

IET Renewable Power Generation

View full text Add to dashboard Cite

show abstract

“…The performances of hourly day-ahead PVPG forecasting by different models are further compared in Subsection 5.5. In this work, the proposed AD-LSTM model is mainly compared with a commonly-used persistence model (i.e., a forecasting model in which observations of the last day are persisted forward as the forecasting results) [5], a statistical model (i.e., the autoregressive integrated moving average model -ARIMA [13]), a conventional machine learning model (i.e., the k-nearest neighbors -KNN [17]), and the OL-LSTM model [30][31][32]. It is noted that the same hyper-parameters and network structures are adopted for both OL-LSTM and AD-LSTM.…”

Section: Day-ahead Forecasting Of Pv Power Generationmentioning

confidence: 99%

“…Accurate PVPG forecasting is a crucial research arena, and a substantial body of research has been devoted to it. In general, PVPG forecasting methodologies illustrated in previous works can be divided into four major categories: the physical model [11,12]; the statistical model [13][14][15][16]; the machine learning (ML) model [17][18][19][20][21]; and the hybrid model [22][23][24].…”

Section: Introductionmentioning

confidence: 99%

An Adaptive Deep Learning Framework for Day-ahead Forecasting of Photovoltaic Power Generation

Luo,

Zhang

2021

Preprint

View full text Add to dashboard Cite

Accurate forecasts of photovoltaic power generation (PVPG) are essential to optimize operations between energy supply and demand. Recently, the propagation of sensors and smart meters has produced an enormous volume of data, which supports the development of databased PVPG forecasting. Although emerging deep learning (DL) models, such as the long short-term memory (LSTM) model, based on historical data, have provided effective solutions for PVPG forecasting with great successes, these models utilize offline learning. As a result, DL models cannot take advantage of the opportunity to learn from newly-arrived data, and are unable to handle concept drift caused by installing extra PV units and unforeseen PV unit failures. Consequently, to improve day-ahead PVPG forecasting accuracy, as well as eliminate the impacts of concept drift, this paper proposes an adaptive LSTM (AD-LSTM) model, which is a DL framework that can not only acquire general knowledge from historical data, but also dynamically learn specific knowledge from newly-arrived data. A two-phase adaptive learning strategy (TP-ALS) is integrated into AD-LSTM, and a sliding window (SDWIN) algorithm is proposed, to detect concept drift in PV systems. Multiple datasets from PV systems are utilized to assess the feasibility and effectiveness of the proposed approaches. The developed AD-LSTM model demonstrates greater forecasting capability than the offline LSTM model, particularly in the presence of concept drift. Additionally, the proposed AD-LSTM model also achieves superior performance in terms of day-ahead PVPG forecasting compared to other traditional machine learning models and statistical models in the literature.

show abstract

“…Some methods were used artificial intelligent techniques such as artificial neural network as in [16][17][18][19][20]. Other methods used data mining techniques like support vector machine [21][22][23][24], K-nearest neighbor as in [25][26][27]. In addition, there are some optimization techniques such as genetic algorithm and particle swarm in were used to predict and improve the solar system depending on environmental factors such as the temperature, wind, and cloud [28][29][30][31].…”

Section: Fig 3 Pv and Wind Energy Project Distributionmentioning

confidence: 99%

An Efficient Intelligent Power Detection Method for Photovoltaic System

Mansour

Abdallah

Obeidat

2020

International Journal of Circuits, Systems and Signal Processing

View full text Add to dashboard Cite

Jordan has experienced a significant increase in both peak load and annual electricity demand within the last decade due to the growth of the economy and population. Photovoltaic (PV) system is one of the most popular renewable energy source in Jordan. PV system is highly nonlinear with unpredictable behavior since it is always subject to many external factors such as severe weather conditions, irradiance level, sheds, temperature, etc. This makes it difficult to maintain maximum power production around its operation ranges. In this paper, an intelligent technique is used to predict and identify the working ability of the PV system under different weather factors in Tafila Technical University (TTU) in Jordan. It helps in optimizing power productions for different operation points. The PV system in Tafila with size 1 MWp PV generated 5.4 GWh since 2017. It saves about € 1.5 million in three years. A real power data from the PV system and a weather data from world weather online site of TTU location are used in this study. Decision tree technique is employed to identify the relation between the output power and weather factors. The results show that the system accuracy is 82.01% during the training phase and 93.425 % on the validation set.

show abstract

Solar forecasting by K-Nearest Neighbors method with weather classification and physical model

Cited by 24 publications

References 18 publications

Systematic literature review of photovoltaic output power forecasting

Systematic literature review of photovoltaic output power forecasting

An Adaptive Deep Learning Framework for Day-ahead Forecasting of Photovoltaic Power Generation

An Efficient Intelligent Power Detection Method for Photovoltaic System

Contact Info

Product

Resources

About