To mitigate the impact of climate change and global warming, the use of renewable energies is increasing day by day significantly. A considerable amount of electricity is generated from renewable energy sources since the last decade. Among the potential renewable energies, photovoltaic (PV) has experienced enormous growth in electricity generation. A large number of PV systems have been installed in on-grid and off-grid systems in the last few years. The number of PV systems will increase rapidly in the future due to the policies of the government and international organizations, and the advantages of PV technology. However, the variability of PV power generation creates different negative impacts on the electric grid system, such as the stability, reliability, and planning of the operation, aside from the economic benefits. Therefore, accurate forecasting of PV power generation is significantly important to stabilize and secure grid operation and promote large-scale PV power integration. A good number of research has been conducted to forecast PV power generation in different perspectives. This paper made a comprehensive and systematic review of the direct forecasting of PV power generation. The importance of the correlation of the input-output data and the preprocessing of model input data are discussed. This review covers the performance analysis of several PV power forecasting models based on different classifications. The critical analysis of recent works, including statistical and machine-learning models based on historical data, is also presented. Moreover, the strengths and weaknesses of the different forecasting models, including hybrid models, and performance matrices in evaluating the forecasting model, are considered in this research. In addition, the potential benefits of model optimization are also discussed.

Forecasting of photovoltaic power generation and model optimization: A review

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 (PV) is one of the most promising renewable energy sources. To ensure secure operation and economic integration of PV in smart grids, accurate forecasting of PV power is an important issue. In this paper, we propose the use of long short-term memory recurrent neural network (LSTM-RNN) to accurately forecast the output power of PV systems. The LSTM networks can model the temporal changes in PV output power because of their recurrent architecture and memory units. The proposed method is evaluated using hourly datasets of different sites for a year. We compare the proposed method with three PV forecasting methods. The use of LSTM offers a further reduction in the forecasting error compared with the other methods. The proposed forecasting method can be a helpful tool for planning and controlling smart grids.

Accurate photovoltaic power forecasting models using deep LSTM-RNN

Due to the challenge of climate and energy crisis, renewable energy generation including solar generation has experienced significant growth. Increasingly high penetration level of photovoltaic (PV) generation arises in smart grid. Solar power is intermittent and variable, as the solar source at the ground level is highly dependent on cloud cover variability, atmospheric aerosol levels, and other atmosphere parameters. The inherent variability of large-scale solar generation introduces significant challenges to smart grid energy management. Accurate forecasting of solar power/irradiance is critical to secure economic operation of the smart grid. This paper provides a comprehensive review of the theoretical forecasting methodologies for both solar resource and PV power. Applications of solar forecasting in energy management of smart grid are also investigated in detail.

Photovoltaic and solar power forecasting for smart grid energy management

This paper proposes distributionally robust energy-reserve-storage co-dispatch model and method to facilitate the integration of variable and uncertain renewable energy. The uncertainties of renewable generation forecasting errors are characterized through an ambiguity set, which is a set of probability distributions consistent with observed historical data. The proposed model minimizes the expected operation costs corresponding to the worst case distribution in the ambiguity set. Distributionally robust chance constraints are employed to guarantee reserve and transmission adequacy. The more historical data are available, the smaller the ambiguity set is and the less conservative the solution is. The formulation is finally cast into a mixed integer linear programming whose scale remains unchanged as the number of historical data increases. Inactive constraint identification and convex relaxation techniques are introduced to reduce the computational burden. Numerical results and Monte Carlo simulations on IEEE 118-bus systems demonstrate the effectiveness and efficiency of the proposed method.

Data-Driven Distributionally Robust Energy-Reserve-Storage Dispatch

This paper proposes a data-driven affinely adjustable distributionally robust method for unit commitment considering uncertain load and renewable generation forecasting errors. The proposed formulation minimizes expected total operation costs, including the costs of generation, reserve, wind curtailment and load shedding, while guarantees the system security. Without any presumption about the probability distribution of the uncertainties, the proposed method constructs an ambiguity set of distributions using historical data and immunizes the operation strategies against the worst-case distribution in the ambiguity set. The more historical data is available, the smaller the ambiguity set is and the less conservative the solution is. The formulation is finally cast into a mixed integer linear programming whose scale remains unchanged as the amount of historical data increases. Numerical results and Monte Carlo simulations on the 118- and 1888-bus systems demonstrate the favorable features of the proposed method.

Data-driven Affinely Adjustable Distributionally Robust Unit Commitment

Due to the intermittency and randomness of solar Photovoltaic (PV) power outputs, it is necessary to find a precise method for PV power forecasting. However, conventional methods, using only temperature, humidity and wind speed data, failed to obtain high accuracy when used to predict PV power outputs under extreme weather conditions. Aerosol index which indicates particulate matter in the atmosphere has a strong correlation with PV generated energy. This paper proposes a novel photovoltaic power forecasting model considering aerosol index data as an additional input. Based on weather classification and back propagation artificial neural network approaches, the estimated results of the forecasting model show good coincidence with the measurement data. And the proposed model is able to improve the prediction accuracy of conventional methods using artificial neural network.

Photovoltaic power forecasting based on artificial neural network and meteorological data

Linear matrix inequality (LMI) based delay-dependent stability analysis/synthesis methods have been applied to power system load frequency control (LFC) which has communication networks in its loops. However, the computational burden of solving large-scale LMIs poses a great challenge to the application of those methods to real-world power systems. This paper investigates the computational aspect of delay-dependent stability analysis (DDSA) of LFC. The basic idea is to improve the numerical tractability of DDSA by exploiting the chordal sparsity and symmetry of the graph related to LFC loops. The graph-theoretic analysis yields the structure restrictions of weighting matrices needed for the LMIs to inherit the chordal sparsity of the control loops. By enforcing those structure restrictions on weighting matrices, the positive semidefinite constraints in the LMIs can be decomposed into smaller ones, and the number of decision variables can be greatly reduced. Symmetry in LFC control loops is also exploited to reduce the number of decision variables. Numerical studies show the proposed structure-exploiting techniques significantly improves the numerical tractability of DDSA at the cost of the introduction of acceptable minor conservatism.

Structure-Exploiting Delay-Dependent Stability Analysis Applied to Power System Load Frequency Control

Intermittent renewable sources and market-driven operation have brought many uncertainties into modern power systems. Power flow analysis tools are expected to be able to incorporate uncertainties into the solution process. Interval power flow (IPF) analysis which aims at obtaining the upper and lower bounds of power flow solutions under interval uncertainties, thereby emerges as a promising framework to meet such expectation. This paper describes a novel optimization-based method to obtain high-accuracy or even exact global solutions to IPF problems. At first, the IPF problems are formulated as polynomial optimization problems probably with rational objective functions. Then Lasserre’s hierarchy, or moment-SOS approach, is introduced to relax the non-convex problems to convex semidefinite programming (SDP) problems. Correlative sparsity in the polynomial optimization problems is exploited to improve numerical tractability and efficiency. Finally, case studies on IEEE 6-bus, 9-bus and 14-bus systems demonstrate the second-order moment relaxation is capable of obtaining exact global interval solutions on small-scale systems, and numerical results on IEEE 57-bus, 118-bus and 300-bus systems show the proposed method can significantly improve the interval solutions compared with recent Linear Programming (LP) relaxation method on larger systems.

Wanliang Fang

Papers

Data-Driven Distributionally Robust Energy-Reserve-Storage Dispatch

Data-driven Affinely Adjustable Distributionally Robust Unit Commitment

Photovoltaic power forecasting based on artificial neural network and meteorological data

Structure-Exploiting Delay-Dependent Stability Analysis Applied to Power System Load Frequency Control

Moment-SOS Approach to Interval Power Flow