For secure and effective Internet access, the Border Gateway Protocol (BGP) must be able to recognize and stop strange coincidences in real time. Regardless, over the past ten years, more study has focused on spotting BGP abnormalities; because of the rise of new bizarre behaviour from both hackers and network configuration errors, it continues to be more challenging. This work goes with the parametric and non parametric analysis of RHMFO based Optimal Detection of BGP Anomalieswith two major steps (i) Feature Extraction (ii) Anomaly Detection". Initially, extensive features such "statistical features, higher order statistical features, and correntropy features" are extracted during the feature extraction stage. For the detection process, an optimized DBN is proposed to define the presence of attack. Here, a hybrid optimization model known as RHMFO is introduced to fine-tune the weight of DBN in order to enhance the detection accuracy. The traditional Rider Optimization Method (ROA) and the MFO algorithm are conceptually combined to create the suggested RHMFO paradigm. Finally, in this paper, parametric and non-parametric analysis is performed. By varying the parameters of RHMFO, the performance of the suggested work is evaluated.