In the context of energy resource scarcity and environmental pressures, accurately forecasting energy consumption and optimizing financial strategies in smart grids are crucial. The high dimensionality and dynamic nature of the data present significant challenges, hindering accurate prediction and strategy optimization.
This paper proposes a fusion algorithm for smart grid enterprise decision-making and economic benefit analysis, aiming to enhance decision-making accuracy and predictive capability. The method combines deep reinforcement learning (DRL), long short-term memory (LSTM) networks, and the Transformer algorithm. LSTM is utilized to process and analyze time series data, capturing historical patterns of energy prices and usage. Subsequently, DRL and the Transformer algorithm are employed to further analyze the data, enabling the formulation and optimization of energy purchasing and usage strategies.
Experimental results demonstrate that the proposed approach outperforms traditional methods in improving energy cost prediction accuracy and optimizing financial strategies. Notably, on the EIA Dataset, the proposed algorithm achieves a reduction of over 48.5% in FLOP, a decrease in inference time by over 49.8%, and an improvement of 38.6% in MAPE.
This research provides a new perspective and tool for energy management in smart grids. It offers valuable insights for handling other high-dimensional and dynamically changing data processing and decision optimization problems. The significant improvements in prediction accuracy and strategy optimization highlight the potential for widespread application in the energy sector and beyond.