An assessment of the renewable energy potential using a clustering based data mining method. Case study in Romania

Grigoraș, Gheorghe; Scarlatache, Florina

doi:10.1016/j.energy.2014.12.054

Cited by 39 publications

(17 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The literature mentions numerous data mining tools, but the most important are [11]- [18], [20]: classification methods, cluster analysis, search for association rules, aggregation and approximation methods, time series analysis, dependency analysis, and prediction analysis. Another classification, based on the machine learning field, is given by dividing the data mining methods into two groups: supervised and unsupervised learning methods.…”

Section: Data Mining For Larmentioning

confidence: 99%

“…The advantage of the unsupervised learning methods is that interesting structures can be found directly from the data without any background knowledge. From this category, the best known methods are the clustering techniques [8], [15], [19], [20].…”

Section: Data Mining For Larmentioning

confidence: 99%

“…From these, the test based on the Silhouette Global Index calculation is one of the most used [8], [15], [19], [20]. This calculates the silhouette width for each sample, average silhouette width for each cluster and overall average silhouette width for the entire data set.…”

Section: Data Mining For Larmentioning

confidence: 99%

See 2 more Smart Citations

Processing of smart meters data for peak load estimation of consumers

Grigoraș

Scarlatache

2015

2015 9th International Symposium on Advanced Topics in Electrical Engineering (ATEE)

Self Cite

View full text Add to dashboard Cite

The paper presents a Mining Data peak load estimation of household consum uses an unsupervised learning method (clu the polynomial regression. With K-means cl the consumption categories of household determined. The input data for the consume consumption categories (monthly energy cons loads) are obtained from processing the ty provided by Smart Meters. For each consu polynomial regression model is built for peak household consumers equipped with cla obtained results demonstrate that the metho with the success in peak load estimation customers from distribution systems when i poor (based on the data provided by classic m

show abstract

Section: Data Mining For Larmentioning

confidence: 99%

Section: Data Mining For Larmentioning

confidence: 99%

See 1 more Smart Citation

Processing of smart meters data for peak load estimation of consumers

Grigoraș

Scarlatache

2015

2015 9th International Symposium on Advanced Topics in Electrical Engineering (ATEE)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Portugal (PT) Grigoras and Scarlatache [45], Ţăpurică and Tache [46], Zamfir et al [47]. Romania (RO) Al-Mansour et al [48].…”

Section: Study (Journal Publication)mentioning

confidence: 99%

“…One of the Romanian support schemes is applied to the energy sector and a second one offers subsidy programs in the agricultural sector [65]. Romania has a huge resource potential for wind, solar and hydro energy [45]. As such, the Romanian support for bioenergy via cogeneration investments is relative low, when compared with solar and wind energy for electricity production [46].…”

Section: Leading Countries (Group 1)mentioning

confidence: 99%

Five years left – How are the EU member states contributing to the 20% target for EU's renewable energy consumption; the role of woody biomass

Proskurina

Sikkema

Heinimö

et al. 2016

Biomass and Bioenergy

View full text Add to dashboard Cite

The European Union has set ambitious targets of raising the share of EU energy consumption produced from renewable resources from 20% by 2020 to 27% by 2030. The aim of this paper is to assess the role of woody biomass in renewable energy as gross final energy consumption in the European Union (the EU-28). The paper identifies leading and lagging countries in biomass development by focusing on their current biomass use and forecasts future perspectives. The research compares and evaluates the role of biomass in renewable energy in the EU-28 focusing on countries' potential resources and policy support. The study shows that all countries are making efforts to reach the 20% target in 2020 and exhibit a trend of increasing renewable energy as gross final energy consumption towards the new target of 2030. Solid biomass plays an important role in reaching the EU's renewable energy targets. The majority of the EU-28 countries are close to reaching their national renewable energy targets and show a very attractive biomass development. Unless energy consumption decreases however, some member states will face serious problems in reaching their renewable energy target in 2020. Following our analysis, the largest problems occur in those MS having a relative highenergy consumption pattern: France, Germany and the United Kingdom. It is unlikely that they can comply with expected renewable energy demand, unless they mobilize more woody biomass from their available domestic potential (France, Germany) or considerably increase their woody biomass imports (mostly wood pellets) from elsewhere (United Kingdom). Keywords Definitions Bioenergy: Bioenergy refers to energy derived from biofuels. Biomass: Refers to the biodegradable fraction of products, waste and residues from agricultural (including vegetal and animal substances), forestry and related industries, as well as the biodegradable fraction of industrial and municipal waste.  Bioliquids. Refers to the liquid fuels made from biomass for energy purposes other than transport (i.e.heating and electricity). Gross inland consumption of energy (GIC) is the first aggregate in the national energy balances. It refers to "apparent" consumption and is derived from the formula that takes into account primary production, exports, imports and stock changes. It includes the primary energy from fossil fuels, from renewable energies (biomass, wind, solar, hydro), derived heat and trade of electrical energy. Gross final energy consumption (GFEC) is calculated from national energy balances. GFEC starts with the GIC data, after which transformation losses, distribution losses and own consumption of electricity and heat within the energy sector are subtracted. The GFEC data can be divided over the sectors involved in the energy consumption, after the subtraction of non-energy consumption (e.g. use of cokes for chemical products). At the end, we remain with final energy consumption by industry, transport and households [3].4

show abstract