.png){kind=icon}
.png){kind=icon}
Return
Electrical load forecasting in power systems based on quantum computing using time series-based quantum artificial intelligence
.png){kind=icon}
OA
AI
DOI：10.1038/s41598-025-89933-x.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
A proper, reliable, and economic operation of a power system relies on a precise energy management strategy. For a reliable energy management strategy, information about the power system including power production and power consumption is required. However, consumer behaviour can be unpredictable, which can result to a high level of uncertainties for the load profile. So, this type of issue (existence of the uncertainty in power system) makes the energy management a complex task. The knowledge about the future state of the power system (e.g., the values of loads) can reduce the difficulty of this task, and it can lead to a more efficient energy management. This paper implements quantum computing-based artificial neural network to predict the future values of loads. For this purpose, this paper uses hybrid quantum/classical artificial neural network for a short-term forecasting of loads. The implemented quantum computing-based strategy is deployed using time series-based technique without using extra information (e.g., the weather condition, and behaviour of the consumer), and it only uses the current and historical values of the load to predict the future value of that. To examine the effectiveness of the hybrid quantum/classical artificial neural network, two different types of loads are selected from an experimental lab and the quantum-based approach is tested on those loads. The obtained results can proof the potential of quantum artificial intelligence to be used for forecasting-based challenges in smart grids.
Keywords:
Quantum computing
Load forecasting
Artificial intelligence
Artificial neural networks
Smart grid
Residential load
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.9
Papers:
27.1W
Citations:
83.5W