Efficiency Beyond Limits: LSTM and k-NN Synergy for Forecasting Energy Needs in Data Centers

The objective of this study is to examine the effectiveness of a hybrid methodology that combines Long Short-Term Memory (LSTM) and k-Nearest Neighbors (k-NN) models in the context of energy prediction within data centres. The objective of this study is to improve the accuracy of predictions and the efficiency of operations by utilising the combined capabilities of these two machine learning approaches. The proposed LSTM-kNN model has superior performance compared to individual LSTM and k-NN models, as evidenced by a thorough assessment on sample data. It achieves a Mean Absolute Error (MAE) of 9.45, Root Mean Square Error (RMSE) of 12.97, and a coefficient of determination (R²) value of 0.89. The importance of model synergy in enhancing the accuracy of energy forecasts is shown by comparative analysis. The results of this study provide a significant contribution to the advancement of energy management methods in data centres. These findings provide vital insights for stakeholders, enabling them to optimise resource allocation, capacity planning, and sustainability initiatives. Proactive energy optimisation measures and cost-effective operational decisions are examples of practical applications. Potential avenues for future study encompass the exploration of supplementary machine learning techniques and the examination of the influence exerted by external factors on patterns of energy usage. In summary, this work highlights the significance of incorporating machine learning methods to tackle intricate issues in energy prediction and control in data centre settings.