Many cybersecurity dangers exist for modern computer networks, which emphasize how crucial Network Intrusion Detection (NID) is necessary. The ever-changing threat landscape has made it difficult for traditional intrusion detection systems (IDS) to remain successful, which emphasizes the growing significance of artificial intelligence (AI) solutions. To improve threat detection effectiveness, the paper used Deep Learning-powered network intrusion detection (DL-powered NID) in this study. The tests utilized two datasets: the Canadian Institute for Cybersecurity 2017 (CICIDS2017) dataset and Internet of Things network traffic (IOT23) captures to verify the efficacy of this technique. Preprocessing the dataset entails applying the Preprocessing and Minimax Scaling (PMS) method, which includes filtering, transforming, and normalizing the data. The paper offer the NID-VGGI6 framework, a 16-convolution-layer network intrusion detection visual geometry group based on Convolutional Neural Networks (CNNs), for feature extraction. In order to provide a class and scale-invariant architecture, this framework combines multilevel and multiscale features with data augmentation approaches. During NID-VGGI6 training, the focal loss function solves class imbalance, and the Flatten-T Swish (FTS) activation function reduces gradient vanishing and explosion problems. In order to improve decision-making in NID, a one-dimensional CNN-based Bidirectional Long Short-Term Memory (1DCNN-BiLSTM) model is used for classification after feature extraction. The paper utilized the Orca Prediction Optimization Algorithm (OPOA) to fine-tune classification hyperparameters for maximum accuracy. The findings show that the suggested model performs better than the existing ones and reaches an impressive 99.9% accuracy rate for both the datasets.