Napoved odjema in prenosnih izgub električne energije za slovenski prenosni elektroenergetski sistem

VOLARIČ, TOMAŽ (avtor), Pantoš, Miloš (mentor)

V študiji smo se osredotočili na napovedovanje prenosnih izgub z namenom zmanjšanja pogreška in optimizacije stroškov nakupa električne energije za pokrivanje izgub. Za dosego tega cilja smo se odločili razviti in preizkusiti popolnoma novo rešitev, ki bi torej omogočala natančnejše napovedi in s tem pripomogla k zmanjšanju stroška nakupa električne energije za pokrivanje prenosnih izgub. Z novo metodo smo ločeno obravnavali severnoprimorski del in preostali del Slovenije, s čimer smo dosegli natančnejše napovedovanje prenosnih izgub v severnoprimorskem delu, ki se pojavijo zaradi obratovanja črpalne hidroelektrarne Avče. V vsakem delu Slovenije smo izvedli ločene napovedi prenosnih izgub, da bi ugotovili, ali lahko tako izboljšamo napoved prenosnih izgub. V okviru naše raziskave smo izvedli tudi napoved za celotno Slovenijo, s čimer smo omogočili direktno primerjavo dveh pristopov. Rezultati so pokazali, da se je za bolj natančno izkazala metoda, ki napoveduje prenosne izgube za celotno državo. Ta ugotovitev kaže na pomembnost celostnega pristopa k napovedovanju prenosnih izgub, saj je ta metoda sposobna bolje zajeti različne vplive in vzorce po celotnem omrežju. Poglobili smo se tudi v razloge za slabe napovedi v severnoprimorski regiji in ugotovili, da je ključni dejavnik nenatančna napoved obratovanja črpalne hidroelektrarne Avče. Slaba vpetost severnoprimorske zanke v elektroenergetski sistem povzroča velik delež prenosnih izgub v severnoprimorski zanki; natančen vpogled v njeno obratovanje pa je ključnega pomena za izboljšanje napovedi v severnoprimorski zanki. Izbrali smo si testno obdobje, za katero smo preizkusili novo metodo. Ugotovili smo, da ta metoda omogoča natančnejše napovedovanje prenosnih izgub v primerjavi z metodo, ki se trenutno uporablja. Ta ugotovitev kaže, da je prihodnost uporabe strojnega učenja za izboljšanje napovednih modelov zelo obetavna.

• Jezik: Slovenski jezik
• Ključne besede: Prenosne izgube, umetna inteligenca, LSTM, XGBoost, napoved prenosnih izgub.
• Vrsta gradiva: Magistrsko delo/naloga
• Organizacija: FE - Fakulteta za elektrotehniko
• Leto izida: 2023
• PID: 20.500.12556/RUL-150466
• COBISS.SI-ID: 165266947
• Datum objave v RUL: 18.09.2023

Sekundarni jezik

• Jezik: Angleški jezik
• Naslov: Forecast of electricity demand and transmission losses for the Slovenian transmission electricity system

Izvleček

In this study, we focused on predicting transmission losses with the aim of reducing errors and optimizing the costs of their purchase. To achieve this goal, we decided to develop and test a completely new approach that would enable predictions that are more accurate and thus contribute to reducing the cost of purchasing transmission losses. Our approach involved dividing Slovenia into two parts: the northwestern region (Severna Primorska) and the rest of the country. In each part, we carried out separate predictions of transmission losses to determine if this approach could improve the accuracy of the predictions. As part of our research, we also made predictions for the entire country, allowing a direct comparison between the two approaches. The results showed that the method that predicts transmission losses for the entire country was more accurate. This finding highlights the importance of a holistic approach to predicting transmission losses, as this method is better able to capture various influences and patterns throughout the entire network. We also delved into the reasons for poor predictions in the northwestern region and found that the key factor was the inaccurate prediction of the operation of the Avče pump hydroelectric power plant. This power plant represents a significant part of the transmission losses in the northwestern loop, and obtaining accurate insights into its operation is crucial for improving predictions in this region. During the testing period, we evaluated the created method that utilizes the XGBoost algorithm and found that it predicted transmission losses more accurately than the method that is currently used. This observation indicates promising results for the application of machine learning to enhance predictive models.

• Ključne besede: Transmission losses, artificial intelligence, LSTM, XGBoost, prediction of transmission losses