Performance Evaluation of Probabilistic Methods Based on Bootstrap and Quantile Regression to Quantify PV Power Point Forecast Uncertainty

Long Short-Term Memory-Based Twin Support Vector Regression for Probabilistic Load Forecasting

A probabilistic load forecast that is accurate and reliable is crucial to not only the efficient operation of power systems but also to the efficient use of energy resources. In order to estimate the uncertainties in forecasting models and nonstationary electric load data, this study proposes a probabilistic load forecasting model, namely BFEEMD-LSTM-TWSVRSOA. This model consists of a data filtering method named fast ensemble empirical model decomposition (FEEMD) method, a twin support vector regression (TWSVR) whose features are extracted by deep learning-based long short-term memory (LSTM) networks, and parameters optimized by seeker optimization algorithms (SOAs). We compared the probabilistic forecasting performance of the BFEEMD-LSTM-TWSVRSOA and its point forecasting version with different machine learning and deep learning algorithms on Global Energy Forecasting Competition 2014 (GEFCom2014). The most representative month data of each season, totally four monthly data, collected from the one-year data in GEFCom2014, forming four datasets. Several bootstrap methods are compared in order to determine the best prediction intervals (PIs) for the proposed model. Various forecasting step sizes are also taken into consideration in order to obtain the best satisfactory point forecasting results. Experimental results on these four datasets indicate that the wild bootstrap method and 24-h step size are the best bootstrap method and forecasting step size for the proposed model. The proposed model achieves averaged 46%, 11%, 36%, and 44% better than suboptimal model on these four datasets with respect to point forecasting, and achieves averaged 53%, 48%, 46%, and 51% better than suboptimal model on these four datasets with respect to probabilistic forecasting.

Behind-the-Meter Load and PV Disaggregation via Deep Spatiotemporal Graph Generative Sparse Coding With Capsule Network

Nowadays, rooftop photovoltaic (PV) panels are getting enormous attention as clean and sustainable sources of energy due to the increasing energy demand, depreciating physical assets, and global environmental challenges. In residential areas, the large-scale integration of these generation resources influences the customer load profile and introduces uncertainty to the distribution system's net load. Since such resources are typically located behind the meter (BtM), an accurate estimation of BtM load and PV power will be crucial for distribution network operation. This article proposes the spatiotemporal graph sparse coding (SC) capsule network that incorporates SC into deep generative graph modeling and capsule networks for accurate BtM load and PV generation estimation. A set of neighboring residential units are modeled as a dynamic graph in which the edges represent the correlation among their net demands. A generative encoder-decoder model, i.e., spectral graph convolution (SGC) attention peephole long short-term memory (PLSTM), is devised to extract the highly nonlinear spatiotemporal patterns from the formed dynamic graph. Later, to enrich the latent space sparsity, a dictionary is learned in the hidden layer of the proposed encoder-decoder, and the corresponding sparse codes are procured. Such sparse representation is used by a capsule network to estimate the BtM PV generation and the load of the entire residential units. Experimental results on two real-world energy disaggregation (ED) datasets, Pecan Street and Ausgrid, demonstrate more than 9.8% and 6.3% root mean square error (RMSE) improvements in BtM PV and load estimation over the state-of-the-art, respectively.

A Stochastic Recurrent Encoder Decoder Network for Multistep Probabilistic Wind Power Predictions

In this article, a stochastic recurrent encoder decoder neural network (SREDNN), which considers latent random variables in its recurrent structures, is developed for the first time for the generative multistep probabilistic wind power predictions (MPWPPs). The SREDNN enables the stochastic recurrent model under the encoder-decoder framework to engage exogenous covariates to produce better MPWPP. The SREDNN consists of five components, the prior network, the inference network, the generative network, the encoder recurrent network, and the decoder recurrent network. The SREDNN is equipped with two critical advantages compared with conventional RNN-based methods. First, the integration over the latent random variable builds an infinite Gaussian mixture model (IGMM) as the observation model, which drastically increases the expressiveness of the wind power distribution. Secondly, hidden states of the SREDNN are updated in a stochastic way, which builds an infinite mixture of the IGMM for describing the ultimate wind power distribution and enables the SREDNN to model complex patterns across wind speed and wind power sequences. Computational experiments are conducted on a dataset of a commercial wind farm having 25 wind turbines (WTs) and two publicly assessable WT datasets to verify the advantages and effectiveness of the SREDNN for MPWPP. Experimental results show that the SREDNN achieves a lower negative form of the continuously ranked probability score (CRPS*) as well as a superior sharpness and comparable reliability of prediction intervals by comparing against considered benchmarking models. Results also show the clear benefit gained from considering latent random variables in SREDNN.

Probabilistic Causal Effect Estimation With Global Neural Network Forecasting Models

We introduce a novel method to estimate the causal effects of an intervention over multiple treated units by combining the techniques of probabilistic forecasting with global forecasting methods using deep learning (DL) models. Considering the counterfactual and synthetic approach for policy evaluation, we recast the causal effect estimation problem as a counterfactual prediction outcome of the treated units in the absence of the treatment. Nevertheless, in contrast to estimating only the counterfactual time series outcome, our work differs from conventional methods by proposing to estimate the counterfactual time series probability distribution based on the past preintervention set of treated and untreated time series. We rely on time series properties and forecasting methods, with shared parameters, applied to stacked univariate time series for causal identification. This article presents DeepProbCP, a framework for producing accurate quantile probabilistic forecasts for the counterfactual outcome, based on training a global autoregressive recurrent neural network model with conditional quantile functions on a large set of related time series. The output of the proposed method is the counterfactual outcome as the spline-based representation of the counterfactual distribution. We demonstrate how this probabilistic methodology added to the global DL technique to forecast the counterfactual trend and distribution outcomes overcomes many challenges faced by the baseline approaches to the policy evaluation problem. Oftentimes, some target interventions affect only the tails or the variance of the treated units' distribution rather than the mean or median, which is usual for skewed or heavy-tailed distributions. Under this scenario, the classical causal effect models based on counterfactual predictions are not capable of accurately capturing or even seeing policy effects. By means of empirical evaluations of synthetic and real-world datasets, we show that our framework delivers more accurate forecasts than the state-of-the-art models, depicting, in which quantiles, the intervention most affected the treated units, unlike the conventional counterfactual inference methods based on nonprobabilistic approaches.

Photovoltaic Power Prediction Based on Hybrid Deep Learning Networks and Meteorological Data

Conventional point prediction methods encounter challenges in accurately capturing the inherent uncertainty associated with photovoltaic power due to its stochastic and volatile nature. To address this challenge, we developed a robust prediction model called QRKDDN (quantile regression and kernel density estimation deep learning network) by leveraging historical meteorological data in conjunction with photovoltaic power data. Our aim is to enhance the accuracy of deterministic predictions, interval predictions, and probabilistic predictions by incorporating quantile regression (QR) and kernel density estimation (KDE) techniques. The proposed method utilizes the Pearson correlation coefficient for selecting relevant meteorological factors, employs a Gaussian Mixture Model (GMM) for clustering similar days, and constructs a deep learning prediction model based on a convolutional neural network (CNN) combined with a bidirectional gated recurrent unit (BiGRU) and attention mechanism. The experimental results obtained using the dataset from the Australian DKASC Research Centre unequivocally demonstrate the exceptional performance of QRKDDN in deterministic, interval, and probabilistic predictions for photovoltaic (PV) power generation. The effectiveness of QRKDDN was further validated through ablation experiments and comparisons with classical machine learning models.

Optimal Operation of Energy Hub Systems under Resiliency Response Options

The economic and resilient operation of power systems has always been one of the main priorities of energy systems. In spite of improvements in various fields of energy systems, especially power systems, the issue of resilience has become more important. For this purpose, this paper proposes a multiobjective optimization model to improve the economic performance of energy hub systems and improve the resilience of electrical consumers. Also, consumer welfare, which is a function of the energy not supplied index, is maximized over a 24-hour period by considering extreme weather conditions. The ε-constraint method is applied to solve the proposed model by transforming the multiobjective optimization problem into several single-objective optimization problems. The max-min fuzzy method is also used to select the optimal solution among the Pareto solutions. A sample hub system is made up of electrical, thermal, and gas loads, electrical and thermal energy sources, and storage systems employed as a test system. A group of actions is applied to improve the resilience of the system, which may be affected by outages caused by storms under the resilience response program (RRP). The results proved the efficiency of the proposed RRP in improving economics and resilience.

Multi-Objective Optimal Planning for Distribution Network Considering the Uncertainty of PV Power and Line-Switch State

With the construction of the smart grid, the distribution network with high penetration of the photovoltaic (PV) generator relies more and more on cyber systems to achieve active control; thus, the uncertainty of PV power and the line-switch state will inevitably affect the distribution network. To avoid the situation, a min–max multi-objective two-level planning model is proposed. Firstly, the uncertainty of PV power is considered, and a multi-time PV power model is established. Followed by the analysis of the line-switch state uncertainty in the distribution network, and according to Claude Shannon’s information theory, the line-switch state uncertainty model is established under multiple scenarios. After the distribution network reconfiguration, the Latin hypercube sampling (LHS) method is used to determine the line-switch state when the uncertainty budget is different. Finally, considering the worstcase by the uncertainty of PV power and line-switch status, the control model is proposed to improve the stability of the distribution network with the minimal maintenance cost. The model feasibility is verified by the test system and the characteristics of PV power uncertainty, the line-switch state uncertainty is analyzed, and the influence of the scheduling strategy is discussed, thus providing practical technical support for the distribution network.

Investigation of a Real-Time Dynamic Model for a PV Cooling System

The cooling of PV models is an important process that enhances the generated electricity from these models, especially in hot areas. In this work, a new, active cooling algorithm is proposed based on active fan cooling and an artificial neural network, which is named the artificial dynamic neural network Fan cooling algorithm (DNNFC). The proposed system attaches five fans to the back of a PV model. Subsequently, only two fans work at any given time to circulate the air under the PV model in order to cool it down. Five different patterns of working fans have been experimented with in this work. To select the optimal pattern for any given time, a back propagation neural network model was trained. The algorithm is a dynamic algorithm since it re-trains the model with new recorded surface temperatures over time. In this way, the model automatically adapts to any weather and environmental conditions. The model was trained with an indoor dataset and tested with an outdoor dataset. An accuracy of more than 97% has been recorded, with a mean square error of approximately 0.02.

A State-of-Art-Review on Machine-Learning Based Methods for PV

In the current era, Artificial Intelligence (AI) is becoming increasingly pervasive with applications in several applicative fields effectively changing our daily life. In this scenario, machine learning (ML), a subset of AI techniques, provides machines with the ability to programmatically learn from data to model a system while adapting to new situations as they learn more by data they are ingesting (on-line training). During the last several years, many papers have been published concerning ML applications in the field of solar systems. This paper presents the state of the art ML models applied in solar energy’s forecasting field i.e., for solar irradiance and power production forecasting (both point and interval or probabilistic forecasting), electricity price forecasting and energy demand forecasting. Other applications of ML into the photovoltaic (PV) field taken into account are the modelling of PV modules, PV design parameter extraction, tracking the maximum power point (MPP), PV systems efficiency optimization, PV/Thermal (PV/T) and Concentrating PV (CPV) system design parameters’ optimization and efficiency improvement, anomaly detection and energy management of PV’s storage systems. While many review papers already exist in this regard, they are usually focused only on one specific topic, while in this paper are gathered all the most relevant applications of ML for solar systems in many different fields. The paper gives an overview of the most recent and promising applications of machine learning used in the field of photovoltaic systems.

Short-Term Solar Power Forecasting: A Combined Long Short-Term Memory and Gaussian Process Regression Method

Solar power is considered a promising power generation candidate in dealing with climate change. Because of the strong randomness, volatility, and intermittence, its safe integration into the smart grid requires accurate short-term forecasting with the required accuracy. The use of solar power should meet requirements proscribed by environmental law and safety standards applied for consumer protection. First, time-series-based solar power forecasting (SPF) model is developed with the time element and predicted weather information from the local meteorological station. Considering the data correlation, long short-term memory (LSTM) algorithm is utilized for short-term SPF. However, the point prediction provided by LSTM fails in revealing the underlying uncertainty range of the solar power output, which is generally needed in some stochastic optimization frameworks. A novel hybrid strategy combining LSTM and Gaussian process regression (GPR), namely LSTM-GPR, is proposed to obtain a highly accurate point prediction with a reliable interval estimation. The hybrid model is evaluated in comparison with other algorithms in terms of two aspects: Point prediction accuracy and interval forecasting reliability. Numerical investigations confirm the superiority of LSTM algorithm over the conventional neural networks. Furthermore, the performance of the proposed hybrid model is demonstrated to be slightly better than the individual LSTM model and significantly superior to the individual GPR model in both point prediction and interval forecasting, indicating a promising prospect for future SPF applications.

Key Operational Issues on the Integration of Large-Scale Solar Power Generation—A Literature Review

Solar photovoltaic (PV) power generation has strong intermittency and volatility due to its high dependence on solar radiation and other meteorological factors. Therefore, the negative impact of grid-connected PV on power systems has become one of the constraints in the development of large scale PV systems. Accurate forecasting of solar power generation and flexible planning and operational measures are of great significance to ensure safe, stable, and economical operation of a system with high penetration of solar generation at transmission and distribution levels. In this paper, studies on the following aspects are reviewed: (1) this paper comprehensively expounds the research on forecasting techniques of PV power generation output. (2) In view of the new challenge brought by the integration of high proportion solar generation to the frequency stability of power grid, this paper analyzes the mechanisms of influence between them and introduces the current technical route of PV power generation participating in system frequency regulation. (3) This section reviews the feasible measures that facilitate the inter-regional and wide-area consumption of intermittent solar power generation. At the end of this paper, combined with the actual demand of the development of power grid and PV power generation, the problems that need further attention in the future are prospected.