Urban Household Energy Consumption Forecasting Based on Energy Price Impact Mechanism
Zhang Lianwei, Xiaoni Wen
Frontiers in Energy Research · 2021
doi:10.3389/fenrg.2021.802697 (opens in a new tab)
We email you when a new notice or a question about this paper appears.
Abstract
The energy price influence system is one of the key mechanisms in the study of energy consumption. China’s household energy consumption has obvious regional differences, and rising income levels and urbanisation have changed the willingness and ability of households to make energy consumption choices. Based on the linear price effect of household energy consumption, this paper explores the scenario characteristics of energy prices affecting energy consumption, taking electricity and natural gas consumption as examples. Based on household energy consumption statistics from 2005 to 2018 in 36 major cities across China, the accuracy and change trends of household energy consumption forecasts are investigated through the decision tree-support vector machine (DT-SVR) non-linear forecasting technique. The study shows that the non-linear forecasting technique accurately portrays the predicted trends of changes in total urban household electricity and natural gas consumption. Within the less developed regions of economic development, income levels are still the main constraint on changes in urban household energy consumption, and the stimulating effect of income levels on household energy consumption has not been seen in the process of economic development in these less developed regions. Urbanisation as an important factor in examining household energy consumption, different development patterns and development processes will gradually be reflected in scenario aspects such as the choice of urban household energy consumption and changes in total consumption.
Abstract licence: CC BY
References26
26 more references, whose wording the paper’s licence keeps private.
Reads
Read by people on this page
None yet.
Checked or read by AI through naulon
None yet.
A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.
Are you an author?
Is this your paper?
Claim it to add your note and be paid when agents cite it. Free.