Long-term electrical energy consumption formulating and forecasting via optimized gene expression programming

Over the past decade, energy forecasting applications not only on the grid side of electric power systems but also on the customer side for load and demand prediction purposes have become ubiquitous after the advancements in the smart grid technologies. Within this context, short-term electrical energy consumption forecasting is a requisite for energy management and planning of all buildings from households and residences in the small-scale to huge building complexes in the large-scale. Today’s popular machine learning algorithms in the literature are commonly used to forecast short-term building electrical energy consumption by generating an abstruse analytical expression between explanatory variables and response variables. In this study, gene expression programming (GEP) and group method of data handling (GMDH) networks are meticulously employed for creating genuine and easily understandable mathematical models among predictor variables and target variables and forecasting short-term electrical energy consumption, belonging to a large hospital complex situated in the Eastern Mediterranean. Consequently, acquired results yielded mean absolute percentage errors of 0.620% for GMDH networks and 0.641% for GEP models, which reveal that the forecasting process can be accomplished and formulated simultaneously via proposed algorithms without the need of applying feature selection methods.

Download Full-text

Predicted vs Long-Term Electrical Energy Consumption Pre and Post Energy Conservation Measures: A Case Study of One-story House in Dhahran, Saudi Arabia

4th International Energy Conversion Engineering Conference and Exhibit (IECEC) ◽

10.2514/6.2006-4044 ◽

2006 ◽

Author(s):

Ibraheem Al-Mofeez

Keyword(s):

Saudi Arabia ◽

Energy Consumption ◽

Energy Conservation ◽

Electrical Energy ◽

Electrical Energy Consumption ◽

Conservation Measures ◽

Energy Conservation Measures

Download Full-text

Peramalan Beban pada Gardu Induk Mantingan dalam Penentuan Kapasitas Transformator dengan Metode Regresi Linear

Electrician ◽

10.23960/elc.v15n2.2165 ◽

2021 ◽

Vol 15 (2) ◽

pp. 64-72

Author(s):

Jimmy Trio Putra ◽

Nisaun Fadhilah ◽

Muhammad Arrofiq

Keyword(s):

Operating System ◽

Energy Consumption ◽

Linear Regression ◽

Historical Data ◽

Electrical Energy ◽

Electric Load ◽

Electrical Energy Consumption ◽

Electricity Load ◽

Current Operating

Intisari — Pertumbuhan beban kelistrikan di wilayah Ngawi dan Magetan meningkat seiring rencana pemerintah dalam membangun beberapa infrastruktur dan kawasan industri. Penyedia kelistrikan harus mampu memprediksi kemampuan sistem dalam melayani konsumen. Perencanan pembangunan Gardu Induk (GI) memiliki tujuan dalam memastikan persebaran semua beban listrik yang dilayani dapat diakomodasi dengan baik. Penelitian ini menggunakan data historis dalam memprediksi besarnya permintaan kelistrikan di area GI Mantingan tahun 2019 hingga tahun 2026. Metode yang digunakan adalah metode regresi linear dengan perencanaan satu tahap, yaitu periode 8 tahun (jangka panjang). Hasil penelitian merekomendasikan bahwa sistem yang beroperasi saat ini membutuhkan persebaran beban listrik dengan memindahkan tiga penyulang di GI Magetan dan GI Ngawi ke GI Mantingan. Tiga penyulang tersebut yaitu penyulang Walikukun dan Trinil yang mendapatkan sumber dari GI Ngawi dan penyulang Sine yang mendapat sumber dari GI Magetan. Area calon pembangunan GI Mantingan yaitu didaerah Widodaren, Mantingan, Karanganyar, Ngrambe dan Sine. Penelitian menunjukan bahwa GI baru dibangun dengan kapasitas 60 MVA dan besar nilai pembebanan trafo Gardu Induk Mantingan selama 8 tahun memiliki rata-rata sebesar 41,41% serta biaya pokok penyediaan listik (BPP) rata-rata sebesar Rp. 2.101. Kata kunci — kapasitas trafo, konsumsi energi listrik, regresi linear. Abstract — The growth of electricity load in Ngawi and Magetan areas has increased due to the government's plan to build several infrastructure and industrial areas. The electricity provider must be able to predict the system's ability to serve consumers. The planning for the construction of substations (GI) is carried out to ensure that all electricity loads served can be properly accommodated. This research uses historical data in predicting the amount of electricity demand in the Mantingan substation area from 2019 to 2026. The method used is a linear regression with one-stage planning, which is for 8 years (long term). The results recommend that the current operating system requires an electric load by moving three feeders in Magetan substation and Ngawi substation to Mantingan substation. The three feeders, namely the Walikukun and Trinil feeders, were sourced from the Ngawi substation and the Sine feeders which were sourced from the Magetan substation. The prospective areas for the construction of the Mantingan Substation are Widodaren, Mantingan, Karanganyar, Ngrambe, and Sine areas. Research shows that a newly built substation with a capacity of 60 MVA and the load value of the Mantingan substation transformer for 8 years has an average of 41.41% and an average of biaya pokok penyedia listrik (BPP) of Rp. 2,101. Keywords— transformer capacity, electrical energy consumption, linear regression.

Download Full-text