In power system， the trust evaluation of terminals is a key technology to grade the access and securely collect data， which is critical to ensure the safe and stable operation of the power grid. Traditional trust evaluation models usually calculate the trust score directly based on identification， running states and interaction histories， etc. of the terminals， and show poor performance with indirect attacks and node collusion. To address these problems， an Adaptive Interaction Feedback based Trust evaluation （AIFTrust） mechanism was proposed. In the proposed mechanism， device trust level was measured comprehensively based on direct trust evaluation module， trust recommendation module and trust aggregation module， and accurate trust evaluation for massive collaborative terminals in power information systems was achieved. First， the interaction cost was introduced by the direct trust evaluation module， and the direct trust score of the malicious target terminal was calculated on the basis of the trust decay policy. Then， the experience similarity was introduced by the trust recommendation evaluation module， and similar terminals were recommended through secondary clustering to improve the reliability of the recommendation trust scoring. After the above， the trust aggregation module was used to adaptively aggregate the direct trust score and the recommendation trust score based on the trust score accuracy. Simulation results on real datasets and synthetic datasets show that when attack probability is 30% and trust decay rate is 0.05， AIFTrust improves the recommendation accuracy by 13.30% and 14.81% compared to the similarity-based trust evaluation method SFM （Similarity FraMework） and the trust evaluation method based on objective information entropy CRT （Reputation Trusted based on Cooperation）， respectively.

Aiming at the dependencies between items are difficult to be captured by the present session-based recommendation models from short sessions， with complex item interactions and dynamic user interest changes considered， a Session-based Recommendation of Enhanced Capsule Network （SR-ECN） model was proposed. First， session sequence data was processed by using the Graph Neural Network （GNN） to obtain embedded vector of each item. Then， the dynamic routing mechanism of the capsule network was used to aggregate high-level user preferences from the interaction history. In addition， a self-attention network was introduced by the proposed model to further consider potential information about users and items， thereby recommending more suitable items for users. Experimental results show that， on Yoochoose dataset， the proposed model is superior to all comparison models such as Session-based Recommendation with GNN （SR-GNN）， Target Attentive GNN （TAGNN）， and the proposed model improves 0.92 and 0.45 percentage points compared to the Lossless Edge-order preserving aggregation and Shortcut graph attention for Session-based Recommendation （LESSR） model in terms of recommendation recall and Mean Reciprocal Rank （MRR） respectively.

In multi-classifier decision fusion, there is great warp when using limited training data to estimate the probability parameters of classifier. For dealing with this problem, a multi-classifier decision fusion method based on D-S (Dempster-Shafer) Evidential Reasoning (ER) was presented. The method utilized the advantages of D-S theory to describe uncertainty of classifiers. To solve the paradox problem in high conflict circumstance among multiple classifiers, a reliability weighted fusion algorithm was proposed to realize the traffic identification decision fusion. The experimental results show that the accuracy rate of majority voting and Bayes maximum posteriori probability are 78.3% and 81.7% respectively, while the proposed algorithm can improve the accuracy rate up to 82.2%-91.6%, and remain the reject rate between 4.1% and 6.2%.

Considering the complexity and poor real-time quality of classification algorithms based on the statistical characteristics of network traffic, a new traffic identification method was proposed based on transport-layer topology. According to the different host connection characteristics in terms of application types at aggregation point, the proposed method extracted topological characteristics of application types by capturing the transport layer connection information, and then produced application type pools based on Deep-in Packet Inspection (DPI) technique, finally identified the application types of traffic combining the pools and heuristic rules. The experimental results show that the proposed method gains precision higher than 85% for identifying main application types and reduces ratio of un-identified flows from 18% to 7%. It utilizes transport-layer topology information of different application types and can enhance the recognition accuracy of application types.