Search

A Dynamic Bayesian network (DBN) model for solar power generation forecasting in photovoltaic (PV) solar plants is proposed in this paper. The key idea is to fuse sensor data, operational indicators, meteorological data, lagged output power information, and model errors for more accurate short-term (e.g., hours) and mid-term (e.g., days to weeks) power generation forecasting. The proposed DBN augments automated data-driven structure learning with expert knowledge encoding using continuous and categorical data given constraints to represent causal relationships within a solar inverter system. In addition, an error compensation mechanism that uses an error node to capture the temporal fluctuation caused by system degradation or failures is proposed to capture temporal fluctuation. The effectiveness of the DBN on solar power generation forecasting was evaluated by rolling window analysis with one-year testing data collected from a local solar plant. The proposed DBN is compared with four state-of-art methods including support-vector regression (SVR), k-nearest neighbors (kNN), artificial neural network (ANN), and long short-term memory (LSTM) models. The results show that the proposed DBN achieves better accuracy in general, and it is not as data-hungry as some neural network-based models. The proposed DBN is also shown to have robust and consistent forecasting power with different forecasting horizons. The accuracy is 92 %–95 % from 1 h to one week ahead forecasting. • A Dynamic Bayesian Network (DBN) with multi-source information fusion is proposed. • Automated data-driven structure learning is augmented with expert knowledge. • Error compensation mechanism increases forecasting accuracy. • Proposed DBN outperforms other state-of-the-art methods with fewer data. • Proposed DBN delivers multi-horizon solar power generation forecasts. [ABSTRACT FROM AUTHOR]

As countries worldwide seek to reach net zero emissions within the coming decades, data center sustainability measures are becoming increasingly important as these facilities consume substantial amounts of electricity to support globally expanding digital infrastructure. Yet, local renewable energy production and waste heat utilization are still rarely used in data centers, even though recent high electricity prices have considerably increased the economic value of self-generation and energy efficiency investments. The benefits and cost-effectiveness of data center sustainability measures have also not yet been thoroughly researched in cold-climate regions, where the data center industry is currently growing rapidly. Thus, this paper assesses how solar photovoltaics (PV) and waste heat utilization can effectively be integrated into different cold climate data centers, with a case study analyzing data centers in Finland and northern Japan. The modelled results indicate that solar PV systems can cost-effectively be used to provide renewable electricity to data centers in both Finland and northern Japan, with electricity prices having the largest influence on economic performance. The use of larger external PV systems is shown to be cost-effective at the higher electricity prices seen in 2022, whereas smaller rooftop PV systems and grid electricity provide more economic benefits at 2019 price levels. Selling surplus PV electricity to the grid and using waste heat for district heating is also shown to be effective in data centers located in Finland, whereas battery storage and snow melting are better suited to utilize surplus PV electricity and data center waste heat in northern Japan. [Display omitted] • Solar photovoltaic systems can cost-effectively reduce data center emissions in cold climate countries. • Data center waste heat can provide value in district heating and snow melting applications. • The cost-effectiveness of data center sustainability measures is largely influenced by electricity prices. • The option to sell surplus electricity to the grid incentives larger solar photovoltaic investments in data centers. [ABSTRACT FROM AUTHOR]

In order to meet global sustainability goals, in particular, the rapid decarbonisation of the energy sector in combination with geopolitical energy security issues, as well as further improvement in regional air quality-the so-called renewable energy sources are becoming increasingly critical and important. Photovoltaic power (PV) generation is clearly the most widely deployed (non-hydro) renewable energy source globally, which still has a significant growth potential in many countries, including Hungary. However, due to the intermittent nature and the strong dependency of photovoltaic power production on meteorological factors, continuous adjustment of electric power in the electric grid is needed. This, in turn, requires the most accurate forecast of the photovoltaic energy to be produced in the ultra-short term (15 min) and short term (1 day) in order to minimise last-minute and high-price energy acquisition or unplanned kicks-in of gas-fired auxiliary power plants. In this paper, we evaluate the impacts of large-scale dust transport episodes on the accuracy of forecasts of PV power generation. The numbers and intensities of Saharan dust storm events reaching Central Europe have increased over the last decade, hitting a new record in 2022 with 16 (!) African dust episodes observed over Hungary. We have shown that the semi-direct effect of atmospheric dust particles on high-level cloud formation rather than their direct irradiance-reducing effect is responsible for the reduced accuracies of e short-term (24-h) PV energy production forecasts during these events. • 16 Saharan dust events (SDEs) were identified in Hungary in 2022. • SDEs caused photovoltaic (PV) generation drops and forecast errors. • Indirect effect of dust on irradiance (through cloud formation) was the dominant. [ABSTRACT FROM AUTHOR]