This paper describes a new approach to online forecasting of power production from PV systems. The method is suited to online forecasting in many applications and in this paper it is used to predict hourly values of solar power for horizons of up to 36 h. The data used is 15-min observations of solar power from 21 PV systems located on rooftops in a small village in Denmark. The suggested method is a two-stage method where first a statistical normalization of the solar power is obtained using a clear sky model. The clear sky model is found using statistical smoothing techniques. Then forecasts of the normalized solar power are calculated using adaptive linear time series models. Both autoregressive (AR) and AR with exogenous input (ARX) models are evaluated, where the latter takes numerical weather predictions (NWPs) as input. The results indicate that for forecasts up to 2 h ahead the most important input is the available observations of solar power, while for longer horizons NWPs are the most important input. A root mean square error improvement of around 35% is achieved by the ARX model compared to a proposed reference model.

/pdf/online-short-term-solar-power-forecasting-1ljgpbshkb.pdf

Online Short-term Solar Power Forecasting

A review of deep learning for renewable energy forecasting

Integration of photovoltaics into power grids is difficult as solar energy is highly dependent on climate and geography; often fluctuating erratically. This causes penetrations and voltage surges, system instability, inefficient utilities planning and financial loss. Forecast models can help; however, time stamp, forecast horizon, input correlation analysis, data pre and post-processing, weather classification, network optimization, uncertainty quantification and performance evaluations need consideration. Thus, contemporary forecasting techniques are reviewed and evaluated. Input correlational analyses reveal that solar irradiance is most correlated with Photovoltaic output, and so, weather classification and cloud motion study are crucial. Moreover, the best data cleansing processes: normalization and wavelet transforms, and augmentation using generative adversarial network are recommended for network training and forecasting. Furthermore, optimization of inputs and network parameters, using genetic algorithm and particle swarm optimization, is emphasized. Next, established performance evaluation metrics MAE, RMSE and MAPE are discussed, with suggestions for including economic utility metrics. Subsequently, modelling approaches are critiqued, objectively compared and categorized into physical, statistical, artificial intelligence, ensemble and hybrid approaches. It is determined that ensembles of artificial neural networks are best for forecasting short term photovoltaic power forecast and online sequential extreme learning machine superb for adaptive networks; while Bootstrap technique optimum for estimating uncertainty. Additionally, convolutional neural network is found to excel in eliciting a model's deep underlying non-linear input-output relationships. The conclusions drawn impart fresh insights in photovoltaic power forecast initiatives, especially in the use of hybrid artificial neural networks and evolutionary algorithms.

A review and evaluation of the state-of-the-art in PV solar power forecasting:Techniques and optimization

Photovoltaic power generation forecasting is an important topic in the field of sustainable power system design, energy conversion management, and smart grid construction. Difficulties arise while the generated PV power is usually unstable due to the variability of solar irradiance, temperature, and other meteorological factors. In this paper, a hybrid ensemble deep learning framework is proposed to forecast short-term photovoltaic power generation in a time series manner. Two LSTM neural networks are employed working on temperature and power outputs forecasting, respectively. The forecasting results are flattened and combined with a fully connected layer to enhance forecasting accuracy. Moreover, we adopted the attention mechanism for the two LSTM neural networks to adaptively focus on input features that are more significant in forecasting. Comprehensive experiments are conducted with recently collected real-world photovoltaic power generation datasets. Three error metrics were adopted to compare the forecasting results produced by attention LSTM model with state-of-art methods, including the persistent model, the auto-regressive integrated moving average model with exogenous variable (ARIMAX), multi-layer perceptron (MLP), and the traditional LSTM model in all four seasons and various forecasting horizons to show the effectiveness and robustness of the proposed method.

Short-term photovoltaic power forecasting based on long short term memory neural network and attention mechanism

A survey on applications and variants of the cuckoo search algorithm

Solar photovoltaic power forecasting using optimized modified extreme learning machine technique

Variational mode decomposition based low rank robust kernel extreme learning machine for solar irradiation forecasting

A new hybrid model combining the kernel functions along with the random vector functional link neural network (RVFLN) is proposed in this paper for an effective solar power prediction. The conventional RVFLN is known for its fast learning speed, simple architecture and good generalization capabilities and allows direct connection between input and output nodes along with nonlinear enhancement nodes with random weights. However, the bottleneck of selecting the number of hidden enhancement nodes and mapping functions is still a challenging problem. To overcome these deficiencies of the conventional RVFLN, kernel functions are used for both the direct links and the hidden nodes to provide better stability, generalization and regression accuracy. Instead of using a single kernel for the enhancement nodes, this paper proposes an optimal kernel function that comprises a linear combination of weighted local kernel and a global kernel to improve the prediction accuracy of the solar power generation. This optimal kernel will be known as multi-kernel RVFLN (MK-RVFLN), and its parameters are optimized using an efficient metaheuristic evaporation-based water cycle (EVWCA-MKRVFLN) to provide accurate prediction of solar power. To validate its superior prediction accuracy, two solar power plants of 25 and 100 MW capacity in the states of New York and California are considered for 5-min- and 60-min-ahead prediction in the months of January, April, July and October. The result analysis shows that the MK-RVFLN algorithm attains better performance than many other techniques.

Short-term solar power prediction using multi-kernel-based random vector functional link with water cycle algorithm-based parameter optimization

In present scenario the energy system face various challenges as the demand for energy is increasing significantly and the resources in terms of fossil fuels are limited, need for renewable resources have became very much vital at present. Accurate and reliable solar power forecasting is essential for the legitimate functioning of the power system. Given momentous uncertainties involved in solar power generation due to variation of temperature and irradiance, forecasting provides a unique solution for the uncertainties and variability's in solar data. In this paper a forecasting method has been mentioned that is contingent on a hybrid empirical mode decomposition (EMD) and Extreme Learning Machine (ELM). The non stationary time series is further decomposed into distinct intrinsic mode functions (IMF). A short term forecasting is also carried out in this work to prove the accuracy of the given model. This model is implemented in MATLAB/SCRIPT environment.

Solar power forecasting using a hybrid EMD-ELM method

This study proposes an efficient local energy management system (LEMS) based on the generalised power prediction model for the uncertain operation of renewable distributed generations (DGs)-based microgrid. Photovoltaic with battery energy storage, and wind power generation are considered as primary DGs to compensate intermittency. Conventional direct power prediction models are limited to specific DG applications, where the plant data acquisition system is a necessity. Solar irradiance and wind speed are considered here as prediction targets to cope with such additional expenditure for a microgrid. To ensure a robust reduction in prediction error (ep ), a short-term prediction model is developed by virtue of the proposed robust regularised random vector functional link network. A maximum-likelihood estimator using Huber's cost function is employed to attain the robustness of this model. Further, a direct renewable energy source-power calculation is opted to address model accuracy under local uncertainties. The LEMS operation is completed by compensating ep with distributed adaptive droop-based primary controllers for multi-DG based microgrid. To ensure the performance of the prediction model, solar irradiance, wind speed and power at different atmospheric conditions (seasonal volatility) and time span (i.e. 5, 10 and 60 min) have been implemented in MATLAB and real time.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-gtd.2019.1114

Irani Majumder

Papers

Solar photovoltaic power forecasting using optimized modified extreme learning machine technique

Variational mode decomposition based low rank robust kernel extreme learning machine for solar irradiation forecasting

Short-term solar power prediction using multi-kernel-based random vector functional link with water cycle algorithm-based parameter optimization

Solar power forecasting using a hybrid EMD-ELM method

Intelligent energy management in microgrid using prediction errors from uncertain renewable power generation