Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This study introduces a novel Hadamard neural network optimized with quantum blackhole techniques (QB-HNN) to enhance workload prediction and resource reservation in industry clouds. By transforming workload data into qubits and utilizing a deep network of qubit neurons with a Hadamard-gated activation function, the model effectively captures complex patterns in high-dimensional workloads. The QB-HNN demonstrates significant improvements in prediction accuracy, reducing prediction errors by up to 36.36% compared to existing LSTM and EQNN models, thereby addressing critical resource management challenges in cloud environments.
Achieving up to 36.36% lower prediction error, this quantum-optimized neural network redefines resource management in dynamic cloud environments.
Accurate workload prediction and proactive resource reservation are crucial for industry clouds. However, the conventional machine learning (CML) models with limited learning capabilities often fail to predict diverse, high-dimensional workloads with sudden changes in resource demand, leading to excessive power consumption and resource management issues. In this context, this article proposes a novel Hadamard neural network with quantum blackhole (QB-HNN) optimization. This model combines the computational efficiency of quantum mechanics with the persuasive learning capability of neural networks (NNs). The workload information is transformed into qubits and propagated via a deep network of qubit neurons comprising a Hadamard-gated activation function to fetch superposition within the QB-HNN model for intuitive pattern learning. Furthermore, a novel quantum blackhole biphase optimization (QB-BiO) algorithm is introduced to train and optimize qubit neural weights. The performance of the proposed model is comprehensively evaluated and compared with five state-of-the-art approaches using six benchmark datasets of three heterogeneous varieties of cloud workloads. The prediction accuracy achieved for an extensive range of workloads confirms its influential performance by minimizing the prediction error up to 36.36% and 22.83% over existing LSTM- and EQNN-based prediction approaches, respectively.