Predicting Electricity Consumption Using Time Series Algorithms and Utilizing Energy Storage : Mitigating Negative Price Impacts to Encourage New Investments in the Finnish Electricity Market

annif.suggestionsrenewable energy sources|storage|electricity market|markets (systems)|time series|prices|time-series analysis|energy consumption (energy technology)|forecasts|energy management|enen
annif.suggestions.linkshttp://www.yso.fi/onto/yso/p20762|http://www.yso.fi/onto/yso/p6576|http://www.yso.fi/onto/yso/p16837|http://www.yso.fi/onto/yso/p1865|http://www.yso.fi/onto/yso/p12290|http://www.yso.fi/onto/yso/p750|http://www.yso.fi/onto/yso/p22747|http://www.yso.fi/onto/yso/p2382|http://www.yso.fi/onto/yso/p3297|http://www.yso.fi/onto/yso/p2388en
dc.contributor.authorAhmed, Abdelwahed
dc.contributor.facultyfi=Tekniikan ja innovaatiojohtamisen yksikkö|en=School of Technology and Innovations|-
dc.contributor.organizationfi=Vaasan yliopisto|en=University of Vaasa|
dc.date.accessioned2025-04-24T14:54:34Z
dc.date.accessioned2025-06-25T17:50:04Z
dc.date.available2025-04-24T14:54:34Z
dc.date.issued2025-04-10
dc.description.abstractThe Finnish electricity market is undergoing a significant transformation with the increasing integration of renewable energy sources such as wind and solar. While these developments align with global decarbonization goals, they have introduced challenges like price volatility and negative pricing, deterring investments in grid infrastructure and renewable energy pro-jects. This thesis explores a dual approach to address these issues by combining advanced time series forecasting models with battery energy storage systems (BESS). Three forecasting models—ARIMA, Support Vector Machines (SVM), and Long Short-Term Memory (LSTM)—are employed to predict electricity consumption with high accuracy, lever-aging hourly consumption data segmented by seasons. The results demonstrate that the machine learning model, particularly LSTM, outperforms ARIMA in capturing nonlinear and temporal patterns, achieving average accuracy of 99.93%. These forecasts provide critical insights for grid operators to balance supply and demand effectively. Additionally, the study investigates the role of BESS in stabilizing the Finnish electricity mar-ket. BESS mitigates price volatility by storing excess electricity during low-demand periods and discharging it during peak demand, reducing financial losses from negative prices and enhancing renewable energy integration. The economic feasibility, environmental benefits, and regulatory landscape for BESS deployment in Finland are analyzed, emphasizing their potential to support a sustainable and resilient energy market. This research contributes to the field of smart grid analytics by demonstrating how advanced forecasting models and energy storage solutions can address the unique challenges of re-newable energy integration. The findings have implications for policymakers, grid operators, and investors, offering a pathway to stabilize the Finnish electricity market and foster in-vestments in renewable energy, aligning with Finland's broader climate and energy goals.-
dc.format.bitstreamtrue
dc.format.extent80-
dc.identifier.olddbid22862
dc.identifier.oldhandle10024/19074
dc.identifier.urihttps://osuva.uwasa.fi/handle/11111/12095
dc.identifier.urnURN:NBN:fi-fe2025041025643-
dc.language.isoeng-
dc.rightsCC BY 4.0-
dc.source.identifierhttps://osuva.uwasa.fi/handle/10024/19074
dc.subject.degreeprogrammeMaster's Programme in Industrial Systems Analytics-
dc.subject.disciplinefi=Tuotantotalous (tekniikka)|en=Industrial Management and Engineering|-
dc.titlePredicting Electricity Consumption Using Time Series Algorithms and Utilizing Energy Storage : Mitigating Negative Price Impacts to Encourage New Investments in the Finnish Electricity Market-
dc.type.ontasotfi=Pro gradu -tutkielma|en=Master's thesis|sv=Pro gradu -avhandling|-

Tiedostot

Näytetään 1 - 1 / 1
Ladataan...
Name:
Uwasa_2025_Ahmed_Abdelwahed.pdf
Size:
3.49 MB
Format:
Adobe Portable Document Format