Power Market Load Forecasting on Neural Network With Beneficial Correlated Regularization

Xu, Fang; Cun, Xin; Yan, Mengxuan; Yuan, Haoliang; Wang, Yifei; Lai, Loi Lei

doi:10.1109/tii.2017.2789297

Cited by 36 publications

(28 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The installed power capacity of renewable energy generation grew more than 200 GW, which is mostly PV generation in 2019 [4,5]. However, because of the intermittency and uncertainty of PV, the high penetration of PV could bring great challenges to the power grid, such as power distribution system planning and operation [6][7][8][9], load demand forecasting [10][11][12], hybrid energy system configuration [13,14], and PV power forecasting [15,16].…”

Section: Background and Motivationmentioning

confidence: 99%

See 1 more Smart Citation

Photovoltaic Output Power Estimation and Baseline Prediction Approach for a Residential Distribution Network with Behind-the-Meter Systems

et al. 2020

Self Cite

View full text Add to dashboard Cite

Considering that most of the photovoltaic (PV) data are behind-the-meter (BTM), there is a great challenge to implement effective demand response projects and make a precise customer baseline (CBL) prediction. To solve the problem, this paper proposes a data-driven PV output power estimation approach using only net load data, temperature data, and solar irradiation data. We first obtain the relationship between delta actual load and delta temperature by calculating the delta net load from matching the net load of irradiation for an approximate day with the least squares method. Then we match and make a difference of the net load with similar electricity consumption behavior to establish the relationship between delta PV output power and delta irradiation. Finally, we get the PV output power and implement PV-load decoupling by modifying the relationship between delta PV and delta irradiation. The case studies verify the effectiveness of the approach and it provides an important reference to perform PV-load decoupling and CBL prediction in a residential distribution network with BTM PV systems.

show abstract

Section: Background and Motivationmentioning

confidence: 99%

“…The delta solar irradiation set ∆R k beh d i , t and approximate delta PV output power set ∆P k * PV,beh d i , t can be calculated by Equations (13) and (14), according to the dates recording in Equations (11) and (12).…”

Section: Pv Output Power Sensitivity Modelmentioning

confidence: 99%

Photovoltaic Output Power Estimation and Baseline Prediction Approach for a Residential Distribution Network with Behind-the-Meter Systems

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence techniques are widely used for shortterm load forecasting, such as artificial neural network (ANN) [6], support vector machine (SVM) [7], extreme learning machine [8], Bayesian neural network [9], deep neural network [10] and recurrent neural network (RNN) [11]. In [12], long short-term memory (LSTM) is used to solve the vanishing gradient problem of RNN and outperforms other neural network methods.…”

Section: Introductionmentioning

confidence: 99%

Missing-Insensitive Short-Term Load Forecasting Leveraging Autoencoder and LSTM

et al. 2020

View full text Add to dashboard Cite

“…On the other hand, the output power generated by RES such as wind and solar possesses difficulties in precise controlling. To address the problem of predicting model accuracy and income inconsistency, [10] proposes a useful regularization method for neural network prediction.…”

Section: Introductionmentioning

confidence: 99%

Solar power integration, neural network, spinning reserve, Improved-Levenberg-Marquardt (ILM) algorithm

Tang¹,

Zhu²,

Chen³

et al. 2019

2019 Scientific Conference on Network, Power Systems and Computing (NPSC 2019)

View full text Add to dashboard Cite

the inherent factors, uncertainty and variability, are always existed in intermittent power resources such as wind and solar. Because of blind construction and lack of planning, the number of renewable generation plants are increasing dramatically, the transmission system could not afford such large capacity over such long distance. This paper proposes a novel spinning reserve decision-making model for power system with solar power integration. A new PV power generation forecasting model is established. The training target of neural network contains both accuracy section and maximum deviation section. In addition, Improved-Levenberg-Marquardt (ILM) algorithm is achieved for neural network training. A numerical study with practical data is presented and the result shows that new PV power generation forecasting model can reduce cost of construction of standby power plant with acceptable accuracy level. The proposed approach for spinning reserve decision-making with solar power integration power system is tested in a modified IEEE 9-bus 3-machine Benchmark Network.

show abstract

Power Market Load Forecasting on Neural Network With Beneficial Correlated Regularization

Cited by 36 publications

References 25 publications

Photovoltaic Output Power Estimation and Baseline Prediction Approach for a Residential Distribution Network with Behind-the-Meter Systems

Photovoltaic Output Power Estimation and Baseline Prediction Approach for a Residential Distribution Network with Behind-the-Meter Systems

Missing-Insensitive Short-Term Load Forecasting Leveraging Autoencoder and LSTM

Solar power integration, neural network, spinning reserve, Improved-Levenberg-Marquardt (ILM) algorithm

Contact Info

Product

Resources

About