Baseline And Target Values For Pv Forecasts Toward Improved Solar Power Forecasting Preprint

Accurate solar power forecasting allows utilities to get the most out of the solar resources on their systems. To truly measure the improvements that any new solar forecasting methods can provide, it is important to first develop (or determine) baseline and target solar forecasting at different spatial and temporal scales. This paper aims to develop baseline and target values for solar forecasting metrics. These were informed by close collaboration with utility and independent system operator partners. The baseline values are established based on state-of-the-art numerical weather prediction models and persistence models. The target values are determined based on the reduction in the amount of reserves that must be held to accommodate the uncertainty of solar power output. forecasting metrics. These were informed by close collaboration with utility and independent system operator partners. The baseline values are established based on state-of-the-art numerical weather prediction models and persistence models. The target values are determined based on the reduction in the amount of reserves that must be held to accommodate the uncertainty of solar power output.

Accurate solar photovoltaic (PV) power forecasting allows utilities to reliably utilize solar resources on their systems. However, to truly measure the improvements that any new solar forecasting methods provide, it is important to develop a methodology for determining baseline and target values for the accuracy of solar forecasting at different spatial and temporal scales. This paper aims at developing a framework to derive baseline and target values for a suite of generally applicable, value-based, and custom-designed solar forecasting metrics. The work was informed by close collaboration with utility and independent system operator partners. The baseline values are established based on state-of-the-art numerical weather prediction models and persistence models in combination with a radiative transfer model. The target values are determined based on the reduction in the amount of reserves that must be held to accommodate the uncertainty of PV power output. The proposed reserve-based methodology is a reasonable and practical approach that can be used to assess the economic benefits gained from improvements in accuracy of solar forecasting. Lastly, the financial baseline and targets can be translated back to forecasting accuracy metrics and requirements, which will guide research on solar forecasting improvements toward the areas that are most beneficial to power systems operations.

Four major research objectives were completed over the course of this study. Three of the objectives were to evaluate three, new, state-of-the-art solar irradiance forecasting models. The fourth objective was to improve the California Independent System Operator’s (ISO) load forecasts by integrating behind-the-meter (BTM) PV forecasts. The three, new, state-of-the-art solar irradiance forecasting models included: the infrared (IR) satellite-based cloud motion vector (CMV) model; the WRF-SolarCA model and variants; and the Optimized Deep Machine Learning (ODML)-training model. The first two forecasting models targeted known weaknesses in current operational solar forecasts. They were benchmarked against existing operational numerical weather prediction (NWP) forecasts, visible satellite CMV forecasts, and measured PV plant power production. IR CMV, WRF-SolarCA, and ODML-training forecasting models all improved the forecast to a significant degree. Improvements varied depending on time of day, cloudiness index, and geographic location. The fourth objective was to demonstrate that the California ISO’s load forecasts could be improved by integrating BTM PV forecasts. This objective represented the project’s most exciting and applicable gains. Operational BTM forecasts consisting of 200,000+ individual rooftop PV forecasts were delivered into the California ISO’s real-time automated load forecasting (ALFS) environment. They were then evaluated side-by-side with operational load forecasts with no BTM-treatment. Overall, ALFS-BTM day-ahead (DA) forecasts performed better than baseline ALFS forecasts when compared to actual load data. Specifically, ALFS-BTM DA forecasts were observed to have the largest reduction of error during the afternoon on cloudy days. Shorter term 30 minute-ahead ALFS-BTM forecasts were shown to have less error under all sky conditions, especially during the morning time periods when traditional load forecasts often experience their largest uncertainties. This work culminated in a GO decision being made by the California ISO to include zonal BTM forecasts into its operational load forecasting system. The California ISO’s Manager of Short Term Forecasting, Jim Blatchford, summarized the research performed in this project with the following quote: ?The behind-the-meter (BTM) California ISO region forecasting research performed by Clean Power Research and sponsored by the Department of Energy’s SUNRISE program was an opportunity to verify value and demonstrate improved load forecast capability. In 2016, the California ISO will be incorporating the BTM forecast into the Hour Ahead and Day Ahead load models to look for improvements in the overall load forecast accuracy as BTM PV capacity continues to grow.?

Solar Energy Forecasting and Resource Assessment is a vital text for solar energy professionals, addressing a critical gap in the core literature of the field. As major barriers to solar energy implementation, such as materials cost and low conversion efficiency, continue to fall, issues of intermittency and reliability have come to the fore. Scrutiny from solar project developers and their financiers on the accuracy of long-term resource projections and grid operators’ concerns about variable short-term power generation have made the field of solar forecasting and resource assessment pivotally important. This volume provides an authoritative voice on the topic, incorporating contributions from an internationally recognized group of top authors from both industry and academia, focused on providing information from underlying scientific fundamentals to practical applications and emphasizing the latest technological developments driving this discipline forward. The only reference dedicated to forecasting and assessing solar resources enables a complete understanding of the state of the art from the world’s most renowned experts. Demonstrates how to derive reliable data on solar resource availability and variability at specific locations to support accurate prediction of solar plant performance and attendant financial analysis. Provides cutting-edge information on recent advances in solar forecasting through monitoring, satellite and ground remote sensing, and numerical weather prediction.

Solar photovoltaic (PV) capacity is rapidly growing across the world. However, the volatility of cloud movement introduces significant uncertainty in short-term solar PV output, which can complicate the operation of modern power systems. Cloudy days remain challenging for modern short-term solar forecasting algorithm. An improved short-term forecast benefits all participants of the sub-hourly power market. This work proposes a specialized convolutional neural network (CNN) "SUNSET" for short-term solar PV output forecasting. Its suitability is first tested on now-casting, i.e. inferring contemporaneous PV output from sky images. On a system with a rated capacity of 30.1 kW, the baseline SUNSET model achieved an RMSE of 1.01 kW on the sunny test set, 3.30 kW on the cloudy test set, and 2.40 kW overall. This validates the sky images' close correlation with PV panel outputs and that a CNN is suitable to extract this correlation. Extensive experiments are done to optimize the structure of SUNSET. In terms of depth, having three convolutional layers and one fully-connected layer produces the best result. Both types of neural nets are found to be crucial for model performance. In terms of width, 48 filters in the convolutional layers and 2048 neurons in the fully-connected layers provide the best performance. In terms of image resolution, 64 x 64 is the optimal point, as either finer or coarser resolution results in worse RMSE. Two further techniques are also found to be useful: drop-out increases the robustness for generalization while ensemble modeling decreases forecast error. For forecast, the SUNSET model is augmented in two key aspects, the usage of hybrid input and temporal history. PV output history is injected mid-way in the model to be joined with the processed image features. The temporal history of sky images are included by concatenating the images in the color channel. On a 1-year database, the "baseline'' model achieves a 15.7% forecast skill in all weather conditions, and a 16.3% forecast skill in the more demanding cloudy conditions, relative to a smart persistence forecast. Optimal input and output configurations for forecast are also explored. In terms of input, both sky images and PV output history are found to be crucial. Output-wise, training against PV output significantly out-performs training against clear sky indices (CSI). Careful down-sampling can reduce the training time by as much as 83% without affecting accuracy. For lag term configurations, using the same length of history as the forecast horizon is a good heuristic, while using slightly shorter history yields a modest 0.5% - 0.9% improvement. Last but not least, a two-stage optimization framework is proposed to quantify the value of short-term solar forecast. Design optimization in the first stage solves for resource capacity, while the receding horizon control (RHC) in the second stage simulates a power system's operation for a year. Within this framework, we consider a microgrid scenario which have battery as an option, and a demand charge scenario which allows grid import. In the settling process of the RHC stage, batteries can be utilized and redesigned to address forecast error in the microgrid scenario, while grid import is incurred in the demand charge scenario for the same purpose. For the microgrid scenario, a perfect forecast can reduce overall cost by 3.6% to 12.5% comparing to a persistence forecast. The largest cost savings are achieved with medium solar penetration of 30% to 60%. For the demand charge scenario, a perfect forecast can reduce total cost by 8.9% to 25.6%. For SUNSET with a forecast skill of 15.7%, we can expect a cost saving of 1-2% or 2-5% respectively in these two scenarios.

Forecasting solar energy generation is a challenging task due to the variety of solar power systems and weather regimes encountered. Forecast inaccuracies can result in substantial economic losses and power system reliability issues. This paper presents a suite of generally applicable and value-based metrics for solar forecasting for a comprehensive set of scenarios (i.e., different time horizons, geographic locations, applications, etc.). In addition, a comprehensive framework is developed to analyze the sensitivity of the proposed metrics to three types of solar forecasting improvements using a design of experiments methodology, in conjunction with response surface and sensitivity analysis methods. The results show that the developed metrics can efficiently evaluate the quality of solar forecasts, and assess the economic and reliability impact of improved solar forecasting.

The inherent intermittency in solar energy resources poses challenges to scheduling generation, transmission, and distribution systems. Energy storage devices are often used to mitigate variability in renewable asset generation and provide a mechanism to shift renewable power between periods of the day. In the absence of storage, however, time series forecasting techniques can be used to estimate future solar resource availability to improve the accuracy of solar generator scheduling. The knowledge of future solar availability helps scheduling solar generation at high-penetration levels, and assists with the selection and scheduling of spinning reserves. This study employs statistical techniques to improve the accuracy of solar resource forecasts that are in turn used to estimate solar photovoltaic (PV) power generation. The first part of the study involves time series forecasting of the global horizontal irradiation (GHI) in Phoenix, Arizona using Seasonal Autoregressive Integrated Moving Average (SARIMA) models. A comparative study is completed for time series forecasting models developed with different time step resolutions, forecasting start time, forecasting time horizons, training data, and transformations for data measured at Phoenix, Arizona. Approximately 3,000 models were generated and evaluated across the entire study. One major finding is that forecasted values one day ahead are near repeats of the preceding daydue to the 24-hour seasonal differencingindicating that use of statistical forecasting over multiple days creates a repeating pattern. Logarithmic transform data were found to perform poorly in nearly all cases relative to untransformed or square-root transform data when forecasting out to four days. Forecasts using a logarithmic transform followed a similar profile as the immediate day prior whereas forecasts using untransformed and square-root transform data had smoother daily solar profiles that better represented the average intraday profile. Error values were generally lower during mornings and evenings and higher during midday. Regarding one-day forecasting and shorter forecasting horizons, the logarithmic transformation performed better than untransformed data and square-root transformed data irrespective of forecast horizon for data resolutions of 1-hour, 30-minutes, and 15-minutes.

A framework for assessing the performance of short-term solar forecasting is presented in conjunction with a range of numerical results using global horizontal irradiation (GHI) from the open-source Surface Radiation Budget (SURFRAD) data network. A suite of popular machine learning algorithms is compared according to a set of statistically distinct metrics and benchmarked against the persistence-of-cloudiness forecast and a cloud motion forecast. Results show significant improvement compared to the benchmarks with trade-offs among the machine learning algorithms depending on the desired error metric. Training inputs include time series observations of GHI for a history of years, historical weather and atmospheric measurements, and corresponding date and time stamps such that training sensitivities might be inferred. Prediction outputs are GHI forecasts for 1, 2, 3, and 4 hours ahead of the issue time, and they are made for every month of the year for 7 locations. Photovoltaic power and energy outputs can then be made using the solar forecasts to better understand power system impacts.