Comparative analysis of AI-based models for short-term photovoltaic power forecasting in energy cooperatives

2021 ◽  
pp. 1-15
Author(s):  
Nikos Dimitropoulos ◽  
Zoi Mylona ◽  
Vangelis Marinakis ◽  
Panagiotis Kapsalis ◽  
Nikolaos Sofias ◽  
...  
Keyword(s):  
Comparative Analysis ◽  
Historical Data ◽  
Renewable Energy Sources ◽  
Energy Transition ◽  
Added Value ◽  
Short Term ◽  
Production Forecast ◽  
Performance Accuracy ◽  
Solar Plant ◽  
Electricity Mix

Energy communities can support the energy transition, by engaging citizens through collective energy actions and generate positive economic, social and environmental outcomes. Renewable Energy Sources (RES) are gaining increasing share in the electricity mix as the economy decarbonises, with Photovoltaic (PV) plants to becoming more efficient and affordable. By incorporating Artificial Intelligence (AI) techniques, innovative applications can be developed to provide added value to energy communities. In this context, the scope of this paper is to compare Machine Learning (ML) and Deep Learning (DL) algorithms for the prediction of short-term production in a solar plant under an energy cooperative operation. Three different cases are considered, based on the data used as inputs for forecasting purposes. Lagged inputs are used to assess the historical data needed, and the algorithms’ accuracy is tested for the next hour’s PV production forecast. The comparative analysis between the proposed algorithms demonstrates the most accurate algorithm in each case, depending on the available data. For the highest performing algorithm, its performance accuracy in further forecasting horizons (3 hours, 6 hours and 24 hours) is also tested.

scholarly journals Data Analytics for Profiling Low-Voltage Customers with Smart Meter Readings

2021 ◽  
Vol 11 (2) ◽  
pp. 500
Author(s):  
Fabrizio Pilo ◽  
Giuditta Pisano ◽  
Simona Ruggeri ◽  
Matteo Troncia
Keyword(s):  
Energy Demand ◽  
Data Analytics ◽  
Distribution Systems ◽  
Low Voltage ◽  
Renewable Energy Sources ◽  
A Priori ◽  
Energy Transition ◽  
Smart Meters ◽  
Large Databases ◽  
A New Technique

The energy transition for decarbonization requires consumers’ and producers’ active participation to give the power system the necessary flexibility to manage intermittency and non-programmability of renewable energy sources. The accurate knowledge of the energy demand of every single customer is crucial for accurately assessing their potential as flexibility providers. This topic gained terrific input from the widespread deployment of smart meters and the continuous development of data analytics and artificial intelligence. The paper proposes a new technique based on advanced data analytics to analyze the data registered by smart meters to associate to each customer a typical load profile (LP). Different LPs are assigned to low voltage (LV) customers belonging to nominal homogeneous category for overcoming the inaccuracy due to non-existent coincident peaks, arising by the common use of a unique LP per category. The proposed methodology, starting from two large databases, constituted by tens of thousands of customers of different categories, clusters their consumption profiles to define new representative LPs, without a priori preferring a specific clustering technique but using that one that provides better results. The paper also proposes a method for associating the proper LP to new or not monitored customers, considering only few features easily available for the distribution systems operator (DSO).

scholarly journals Performance Evaluation of Neural Network-Based Short-Term Solar Irradiation Forecasts

Energies ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 3030
Author(s):  
Simon Liebermann ◽  
Jung-Sup Um ◽  
YoungSeok Hwang ◽  
Stephan Schlüter
Keyword(s):  
Neural Network ◽  
Goodness Of Fit ◽  
Renewable Energy Sources ◽  
Weather Conditions ◽  
Solar Irradiation ◽  
Weather Data ◽  
Short Term ◽  
Climate Conditions ◽  
Lstm Network ◽  
The Time Domain

Due to the globally increasing share of renewable energy sources like wind and solar power, precise forecasts for weather data are becoming more and more important. To compute such forecasts numerous authors apply neural networks (NN), whereby models became ever more complex recently. Using solar irradiation as an example, we verify if this additional complexity is required in terms of forecasting precision. Different NN models, namely the long-short term (LSTM) neural network, a convolutional neural network (CNN), and combinations of both are benchmarked against each other. The naive forecast is included as a baseline. Various locations across Europe are tested to analyze the models’ performance under different climate conditions. Forecasts up to 24 h in advance are generated and compared using different goodness of fit (GoF) measures. Besides, errors are analyzed in the time domain. As expected, the error of all models increases with rising forecasting horizon. Over all test stations it shows that combining an LSTM network with a CNN yields the best performance. However, regarding the chosen GoF measures, differences to the alternative approaches are fairly small. The hybrid model’s advantage lies not in the improved GoF but in its versatility: contrary to an LSTM or a CNN, it produces good results under all tested weather conditions.

scholarly journals The Energy Transition in the Visegrad Group Countries

Energies ◽  
2021 ◽  
Vol 14 (8) ◽  
pp. 2212
Author(s):  
Ewelina Kochanek
Keyword(s):  
Renewable Energy Sources ◽  
Mining Industry ◽  
Energy Transition ◽  
Green Energy ◽  
Political Elite ◽  
Energy Transformation ◽  
Diagnostic Features ◽  
Difficult Situation ◽  
Starting Point ◽  
Visegrad Group

The aim of the research is to analyse the energy transition in the Visegrad Group countries, because they depend on the production of energy from the burning of fossil fuels, and transition is a huge challenge for them. The diversity of the energy transformation in the V4 countries was examined by using two qualitative methods, including literature analysis and comparative analysis. The timeframe of the study was set for the period from 2020 to 2030, as these years are crucial for the implementation of the European Green Deal Programme. Four diagnostic features were taken into account in the analysis: the share of RES in final energy consumption, reduction of CO2 emissions in the non-Emissions Trading System (ETS) sector, date of withdrawal of coal from the economy, and energy efficiency. The analysis shows that the V4 countries have different approaches and levels of energy transformation in their economies. Poland is in the most difficult situation, being the most dependent on the production of electricity from coal, as well as having the largest number of employees in the coal and around coal sector. The other countries of the group can base their transformation on nuclear energy, as each of them has at least four such power units. The increased use of biomass for energy and heat production is the most important stimulus for Renewable Energy Sources (RES) growth in the analysed countries. The ambivalent attitude of the political elite to unconventional sources in the four analysed countries significantly hinders the development of certain forms of green energy. However, it has been observed that an increasing proportion of the population, especially those living in regions of the country where there is no fossil fuel mining industry, has a positive attitude towards energy transformation. The study is the first that shows the state of involvement in the process of systemic change of the Visegrad Group countries. The results can serve as a starting point for understanding the reticence of this group of European countries towards the transformation phenomenon, as well as contributing to further research on the implementation of closed-circuit economies in the Visegrad Group countries.

scholarly journals Legitimating power: Solar energy rollout, sustainability metrics and transition politics

2021 ◽  
pp. 251484862110249
Author(s):  
Siddharth Sareen
Keyword(s):  
Solar Energy ◽  
Political Ecology ◽  
Global Climate ◽  
Renewable Energy Sources ◽  
Energy Transition ◽  
Analytical Framework ◽  
Solar Irradiation ◽  
Low Carbon ◽  
Sustainability Metrics ◽  
Energy Transitions

Increasing recognition of the irrefutable urgency to address the global climate challenge is driving mitigation efforts to decarbonise. Countries are setting targets, technological innovation is making renewable energy sources competitive and fossil fuel actors are leveraging their incumbent privilege and political reach to modulate energy transitions. As techno-economic competitiveness is rapidly reconfigured in favour of sources such as solar energy, governance puzzles dominate the research frontier. Who makes key decisions about decarbonisation based on what metrics, and how are consequent benefits and burdens allocated? This article takes its point of departure in ambitious sustainability metrics for solar rollout that Portugal embraced in the late 2010s. This southwestern European country leads on hydro and wind power, and recently emerged from austerity politics after the 2008–2015 recession. Despite Europe’s best solar irradiation, its big solar push only kicked off in late 2018. In explaining how this arose and unfolded until mid-2020 and why, the article investigates what key issues ambitious rapid decarbonisation plans must address to enhance social equity. It combines attention to accountability and legitimacy to offer an analytical framework geared at generating actionable knowledge to advance an accountable energy transition. Drawing on empirical study of the contingencies that determine the implementation of sustainability metrics, the article traces how discrete acts legitimate specific trajectories of territorialisation by solar photovoltaics through discursive, bureaucratic, technocratic and financial practices. Combining empirics and perspectives from political ecology and energy geographies, it probes the politics of just energy transitions to more low-carbon and equitable societal futures.

scholarly journals Secondary Science Teachers’ Views on Environmental Citizenship in The Netherlands

2021 ◽  
Vol 13 (14) ◽  
pp. 7963
Author(s):  
Michiel van Harskamp ◽  
Marie-Christine P. J. Knippels ◽  
Wouter R. van Joolingen
Keyword(s):  
Science Teachers ◽  
Citizenship Education ◽  
Renewable Energy Sources ◽  
Explicit Representation ◽  
Secondary Science ◽  
Added Value ◽  
Face To Face ◽  
Secondary Science Teachers ◽  
Environmental Citizenship ◽  
Teacher Professional

Environmental Citizenship (EC) is a promising aim for science education. EC enables people not only to responsibly make decisions on sustainability issues—such as use of renewable energy sources—but also to take action individually and collectively. However, studies show that education for EC is challenging. Because our understanding of EC practice remains limited, an in-depth, qualitative view would help us better understand how to support science teachers during EC education. This study aims to describe current EC education practices. What do secondary science teachers think sustainability and citizenship entail? What are their experiences (both positive and negative) with education for EC? A total of 41 Dutch science teachers were interviewed in an individual, face-to-face setting. Analysis of the coded transcripts shows that most teachers see the added value of EC but struggle to fully implement it in their teaching. They think the curriculum is unsuitable to reach EC, and they see activities such as guiding discussions and opinion forming as challenging. Furthermore, science teachers’ interpretation of citizenship education remains narrow, thus making it unlikely that their lessons are successful in fostering EC. Improving EC education therefore may be supported by explicit representation in the curriculum and teacher professional development directed at its implementation.

scholarly journals The cost-effectiveness of an energy storage system using hydrogen and underground gas storage

2019 ◽  
Vol 137 ◽  
pp. 01007 ◽  
Author(s):  
Sebastian Lepszy
Keyword(s):  
Cost Effectiveness ◽  
Energy Storage ◽  
Historical Data ◽  
Renewable Energy Sources ◽  
Storage System ◽  
Energy Storage System ◽  
Electricity Production ◽  
Energy Market ◽  
The Cost ◽  
Random Nature

Due to the random nature of the production, the use of renewable energy sources requires the use of technologies that allow adjustment of electricity production to demand. One of the ways that enable this task is the use of energy storage systems. The article focuses on the analysis of the cost-effectiveness of energy storage from the grid. In particular, the technology was evaluated using underground hydrogen storage generated in electrolysers. Economic analyzes use historical data from the Polish energy market. The obtained results illustrate, among other things, the proportions between the main technology modules selected optimally in technical and economic terms.

scholarly journals Comparative Analysis of Existing Tools for Assessment of Post-Earthquake Short-Term Lodging Needs

2016 ◽  
Vol 161 ◽  
pp. 2217-2221 ◽  
Author(s):  
Annibale Vecere ◽  
Ricardo Monteiro ◽  
Walter J. Ammann
Keyword(s):  
Comparative Analysis ◽  
Short Term

A Comparison of the Application of the SMED Methodology in Two Different Cutting Lines

2021 ◽  
Vol 25 (1) ◽  
pp. 124-149
Author(s):  
Alexandre Silva ◽  
José C. Sá ◽  
Gilberto Santos ◽  
Francisco J.G. Silva ◽  
Luís P. Ferreira ◽  
...  
Keyword(s):  
Data Collection ◽  
Continuous Improvement ◽  
Video Analysis ◽  
Historical Data ◽  
Action Plan ◽  
Video Recording ◽  
Operating Mode ◽  
Added Value ◽  
Output Rate ◽  
Production Output

Purpose: This study was carried out in a cork company and its purpose was to observe and analyze the practices and methods used during the tools/series change moments and to propose improvements and alternatives to these same procedures so that the time needed to carry out the setup is reduced by 15% in both lines. Methodology/Approach:The methodology included the following phases: 1st - historical data collection and setup video recording, 2nd - footage analysis and conduction of informal interviews with employees, 3rd - flow, Gantt, and spaghetti charts creation and making of an action plan based on the waste and improvement opportunities identified in video analysis, 4th - validation with the line workers of the new operating mode created with the Single Minute Exchange of Dies (SMED) tool and communication to the Maintenance department about their role in this project, 5th - making and placement of plasticized cards on the cutting lines to ensure that new operating mode is followed and carrying out the actions identified in the action plan. Findings: Throughout this project using observations, video recording and its subsequent analysis, as well as interviews to the workers operating in the line, it was found the existence of several actions carried out by them during the setups which did not add value to the product, lack of adequate tools for the work to be performed and lack of work tools in general Research Limitation/implication: The study was limited by the lines and products under study and by the duration of the curricular internship, which was about five months. Originality/Value of paper: The article demonstrates the added value in terms of product quality and production output rate that SMED methodology can bring to companies that adopt the lean philosophy and in particular this continuous improvement tool.

Sign in / Sign up

Export Citation Format

Share Document