Neural network-based solar irradiance forecast for peak load management of grid-connected microgrid with photovoltaic distributed generation

Hasan, Hasnawiya; Munawar, Muhammad Ridha; Siregar, Ramdhan Halid

doi:10.1109/iceltics.2017.8253235

Cited by 4 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, big data technology is needed. Big data technology can extract valuable information from a large number of data, which has good applications in many aspects of power grid equipment, such as the diagnosis of distribution network conditions [13], power grid load prediction [14], transmission line evaluation [15], user electricity behavior analysis [16], reactive power optimization problems [17], etc. This study mainly analyzed the fault diagnosis of power grid equipment operation.…”

Section: Discussionmentioning

confidence: 99%

Archives of Electrical Engineering

Qian,

Zhu,

et al. 2020

View full text Add to dashboard Cite

Power big data contains a lot of information related to equipment fault. The analysis and processing of power big data can realize fault diagnosis. This study mainly analyzed the application of association rules in power big data processing. Firstly, the association rules and the Apriori algorithm were introduced. Then, aiming at the shortage of the Apriori algorithm, an IM-Apriori algorithm was designed, and a simulation experiment was carried out. The results showed that the IM-Apriori algorithm had a significant advantage over the Apriori algorithm in the running time. When the number of transactions was 100 000, the running of the IM-Apriori algorithm was 38.42% faster than that of the Apriori algorithm. The IM-Apriori algorithm was little affected by the value of support min . Compared with the Extreme Learning Machine (ELM), the IM-Apriori algorithm had better accuracy. The experimental results show the effectiveness of the IM-Apriori algorithm in fault diagnosis, and it can be further promoted and applied in power grid equipment.

show abstract

Section: Discussionmentioning

confidence: 99%

Archives of Electrical Engineering

Qian,

Zhu,

et al. 2020

View full text Add to dashboard Cite

show abstract

“…This means that the effective distribution capacity of a PV system can be attained by predicting the likely amount of solar irradiance it will experience and then calculating output power. The meteorological data required for this method can be easily obtained by local weather stations without the need for on-site collection, so it is widely used in distributed PV systems [17]. PV power prediction methods can also be used to predict solar irradiance by simply changing the input data to historical solar irradiance.…”

Section: The Incorporation Of Unstablementioning

confidence: 99%

An LSTM Short-Term Solar Irradiance Forecasting Under Complicated Weather Conditions

2019

View full text Add to dashboard Cite

Complicated weather conditions lead to intermittent, random and volatility in photovoltaic (PV) systems, which makes PV predictions difficult. A recurrent neural network (RNN) is considered to be an effective tool for time-series data prediction. However, when the weather changes intensely, the long-term sequence of multivariate may cause gradient vanishing (exploding) during the training of RNN, leading the prediction results to local optimum. Long short-term memory (LSTM) network is the deep structure of RNN. Due to its special hidden layer unit structure, it can preserve the trend information contained in the longterm sequence, which is allowed to solve the problems of RNN and improve performance. An LSTM-based approach is applied for short-term predictions in this study based on a timescale that encompasses global horizontal irradiance (GHI) one hour in advance and one day in advance. Inaccurate forecasts usually occur on cloudy days, and the results of ANN and SVR in the literature prove this. To improve prediction accuracy on cloudy days, the clearness-index was introduced as an input data for the LSTM model and to classify the type of weather by k-means during the data processing, where cloudy days are classified as the cloudy and the mixed(partially cloudy). NN models are established to compare the accuracy of different approaches and the cross-regional study is to prove whether the method can be generalizable. From the results of hourly forecast, the R 2 coefficient of LSTM on cloudy days and mixed days is exceeding 0.9, while the R 2 of RNN is only 0.70 and 0.79 in Atlanta and Hawaii. From the results of daily forecast, All R 2 on cloudy days is about 0.85. However, the LSTM is still very effective in improving of RNN and more accurate than other models.

show abstract