Publication

Network time series forecasting in photovoltaics power production

Jelena Simeunovic
2024
EPFL thesis
Abstract

Accurate forecasting of photovoltaic (PV) power production is crucial for the integration of more renewable energy sources into the power grid. PV power production is highly intermittent, due to the stochastic cloud behaviour and cloud dynamics. Previous works focused on predicting the dynamics by combining inputs from ground-based cameras, satellite images and numerical weather predictions with physical or statistical models. However, they are costly or have coarse resolution. The focus of this thesis is to advance the state-of-the-art on short-term solar resources forecasting. We take past PV power from a dense network of PV stations as the main input for forecasting. We leverage a graph signal processing perspective and model multi-site PV production data as signals on a graph to capture their spatio-temporal dependencies and achieve higher spatial and temporal resolution forecasts. In our first contribution two graph neural networks, based on graph convolutional layers to exploit the spatial information, are proposed for deterministic multi-site PV forecasting: the graph-convolutional long short-term memory (GCLSTM) and the graph-convolutional transformer (GCTrafo). These methods rely only on production data and exploit the intuition that PV systems provide a network of virtual weather stations. We show that the proposed models outperform state-of-the-art methods for intra-day forecasting with high spatial and temporal resolution. However, they are difficult to interpret. Utility operators and grid managers could use insights derived from interpretable models to make more informed decisions. Therefore, we introduce a novel interpretable temporal-spatial multi-windows graph attention network (TSM-GAT) for predicting future PV power. TSM-GAT captures different dynamical spatio-temporal correlations for different parts of the forecasting horizon. Thus, it is possible to interpret which PV stations have the most influence when making a prediction for short-, medium- and long-term intra-day forecasts. We show that the proposed model outperforms multi-site state-of-the-art models for four to six hours ahead predictions and that it yields predicted signals with a closer shape to ground truth. Although machine learning models for PV production achieve high resolution forecasts without loss in accuracy using only PV power data, they are often black box models, leading to overly smoothed predictions. These models might overlook the impact of variable weather conditions on PV power, indicating the model cannot fully capture cloud dynamics. Since physically informed neural networks have shown great success when modelling physical phenomena, we introduce a physics-informed graph neural network (PING) for forecasting the future concentrations in the advection-diffusion processes on an irregular grid. PING captures the dynamics by estimating historical velocities. It outperforms baseline models for forecasting cloud concentration index and when combined with GCLSTM outperforms baselines for forecasting PV production. In this thesis, we introduce state-of-the-art models for high resolution and interpretable PV power production forecasts. Even though the accuracy of the physics-informed model is not better than state of the art, it provides insight into the physical behaviour of the cloud dynamics. This insight into cloud dynamics holds potential for future integration with deep learning models to further enhance forecasting capabilities.

About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.
Related concepts (38)
Rooftop solar power
A rooftop solar power system, or rooftop PV system, is a photovoltaic (PV) system that has its electricity-generating solar panels mounted on the rooftop of a residential or commercial building or structure. The various components of such a system include photovoltaic modules, mounting systems, cables, solar inverters and other electrical accessories. Rooftop mounted systems are small compared to utility-scale solar ground-mounted photovoltaic power stations with capacities in the megawatt range, hence being a form of distributed generation.
Photovoltaic system
A photovoltaic system, also PV system or solar power system, is an electric power system designed to supply usable solar power by means of photovoltaics. It consists of an arrangement of several components, including solar panels to absorb and convert sunlight into electricity, a solar inverter to convert the output from direct to alternating current, as well as mounting, cabling, and other electrical accessories to set up a working system. It may also use a solar tracking system to improve the system's overall performance and include an integrated battery.
Growth of photovoltaics
Between 1992 and 2022, the worldwide usage of photovoltaics (PV) increased exponentially. During this period, it evolved from a niche market of small-scale applications to a mainstream electricity source. When solar PV systems were first recognized as a promising renewable energy technology, subsidy programs, such as feed-in tariffs, were implemented by a number of governments in order to provide economic incentives for investments. For several years, growth was mainly driven by Japan and pioneering European countries.
Show more
Related publications (98)

Distributional justice, effectiveness, and costs of current and alternative solar PV incentive schemes in Switzerland

Philippe Thalmann

Like many other countries, Switzerland offers various incentives to promote residential solar PV, but not all households have equal access to them. Using a microsimulation approach based on merged data from the Swiss Household Budget Survey and Household E ...
2024

Intrinsic performance loss rate: Decoupling reversible and irreversible losses for an improved assessment of photovoltaic system performance

Christophe Ballif, Alessandro Francesco Aldo Virtuani, Hugo James André Quest

Solar electricity is set to play a pivotal role in future energy systems. In view of a market that may soon reach the terawatt (TW) scale, a careful assessment of the performance of photovoltaic (PV) systems becomes critical. Research on PV fault detection ...
Wiley2024

Intraday solar irradiance forecasting using public cameras

Demetri Psaltis, Mario Paolone, Christophe Moser, Luisa Lambertini

With the significant increase in photovoltaic (PV) electricity generation, more attention has been given to PV power forecasting. Indeed, accurate forecasting allows power grid operators to better schedule and dispatch their assets, such as energy storage ...
Pergamon-Elsevier Science Ltd2024
Show more
Related MOOCs (12)
SES Swiss-Energyscope
La transition énergique suisse / Energiewende in der Schweiz
SES Swiss-Energyscope
La transition énergique suisse / Energiewende in der Schweiz
Neuronal Dynamics - Computational Neuroscience of Single Neurons
The activity of neurons in the brain and the code used by these neurons is described by mathematical neuron models at different levels of detail.
Show more

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.