| 作成者 |
|
|
|
| 本文言語 |
|
| 出版者 |
|
|
|
| 発行日 |
|
| 収録物名 |
|
| 巻 |
|
| 号 |
|
| 開始ページ |
|
| 終了ページ |
|
| 出版タイプ |
|
| アクセス権 |
|
| Crossref DOI |
|
| 権利関係 |
|
| 概要 |
Meeting the escalating energy demand poses a contemporary challenge, and the utilization of renewable energy resources (RERs) has emerged as a compelling solution to this imperative issue. These resou...rces can be strategically deployed within households, serving as decentralized generators at the consumer’s end. In the current era, with households consuming nearly 40% of total energy, it is imperative to transition to smart appliances capable of adjusting according to provided signals. A demand response program stands out as a pivotal facet of smart grid technology, instrumental in optimizing the assimilation of RERs. Given the inherently intermittent nature of these sources, the resulting output exhibits considerable stochasticity. Hence, forecasting parameters for renewable power generation become indispensable for informed decision-making and the formulation of effective policies. This paper elucidates a research work that deploys a real time pricing-based demand response program, strategically orchestrating the scheduling of diverse general-purpose appliances within a smart household to minimize electricity expenditure. The work specifically leverages forecasted weather parameters for solar photovoltaic (PV) generation in the context of New Delhi, India. Forecasting is achieved through the synergistic application of a hybrid model, combining a convolutional neural network and a long short-term memory type recurrent neural network. The calculated payback period for the deployed PV panel has been determined to be 5.112 years. The comprehensive diminution in costs exhibited a noteworthy reduction of approximately 53.5% in comparison to the selected base case.続きを見る
|
Mendeley出力
p3243-3253