Recent research published in the International Journal of Electrical Power & Energy Systems introduces a novel approach to balancing power supply and demand in new power systems, addressing the significant uncertainties associated with energy sources and loads. The study, led by Jiaxi Li from the State Grid Hunan Electric Power Company Limited Economic & Technical Research Institute, proposes an innovative optimization method known as ISAO-BiTCN-BiGRU-SA-IPBLS.
As the world transitions to more renewable energy sources, the unpredictability of these systems presents a challenge for energy providers. Traditional optimization methods often overlook the unique characteristics of various energy sources and loads, which can lead to inefficiencies and increased operational costs. The new method aims to enhance the accuracy of power supply predictions while also optimizing costs and maximizing renewable energy usage.
Li’s research incorporates the ISAO algorithm into hyperparameter optimization, significantly improving the accuracy of load and photovoltaic (PV) power predictions. The results indicate that the Mean Absolute Percentage Error (MAPE) for load and PV predictions decreased by 13.43% and 16.93%, respectively, after applying this new approach. This improvement is crucial for energy companies looking to enhance their forecasting capabilities, ultimately leading to better resource allocation and reduced costs.
The method employs a two-stage robust optimization process. In the first stage, it focuses on the daily planned output of adjustable power sources, targeting objectives such as minimizing operating costs and maximizing the delivery rate of renewable energy. The second stage optimizes the daily operation of energy storage systems, aiming to minimize potential losses during extreme scenarios. This dual approach not only bolsters the reliability of energy supply but also promotes the integration of renewable resources into the grid.
Commercially, this research opens up significant opportunities for energy providers and technology developers. As companies strive to meet regulatory requirements for renewable energy use, adopting such advanced optimization techniques can yield higher efficiency and lower operational risks. The study’s findings demonstrate that the new method can improve renewable energy delivery rates by 0.10 and 0.02 on peak load and renewable output days, respectively, while reducing maximum losses during extreme conditions by up to 76.75%.
“This research highlights the importance of considering uncertainty in power supply and demand optimization,” said Li. “By enhancing predictive accuracy and operational efficiency, we can better integrate renewable resources into the energy system.”
For energy companies, particularly those in regions with high renewable energy potential, implementing this optimization method can lead to lower costs and improved service reliability. As the energy sector continues to evolve, innovations like those presented by Li and his team will be critical in shaping a sustainable and efficient energy future.
