Optimizing Building Management Systems with DNC-Aided SCL-Flip Decoding of Polar Codes

Abstract

Building Management Systems (BMS) play a pivotal role in optimizing energy usage and enhancing occupant comfort in commercial and residential buildings. This paper proposes a novel approach to improving the efficiency and reliability of BMS by leveraging Deep Neural Network (DNN) aided SCL-Flip decoding of Polar Codes. Polar Codes have emerged as a promising error correction technique for communication systems due to their capacity achieving properties. By integrating DNNs into the Successive Cancellation List (SCL) decoding process and employing flipping algorithms, the proposed method enhances the decoding performance of Polar Codes, thereby improving the reliability of data transmission in BMS applications. Through extensive simulations and experimental validation, the effectiveness of the proposed approach is demonstrated, highlighting its potential to revolutionize building automation and energy management systems.