Multi-Agent Reinforcement Learning (MARL) has shown significant promise in tackling complex cooperative tasks, largely due to parameter sharing among agents. However, while this sharing facilitates teamwork, it can also result in agent homogenization, which limits individualized behaviors. To address this issue, we introduce a novel method called Diverse Collaboration in Multi-Agent Reinforcement Learning via Self-Adaptive Method (DC-SA). DC-SA advances individualized behaviors by maximizing the mutual information between agents’ representations and their trajectories to enhance diversity collaboration. The method employs adaptive weights to balance collaboration and individualization, particularly in scenarios where collaboration is challenging. Our empirical results demonstrate that DC-SA outperforms five baselines on the StarCraft II micromanagement tasks.

In collaborative multi-agent reinforcement learning (MARL), agents need to reach good collaboration in an evolving environment. The introduction of the concept of role is an effective method to recognize the complex relationship between agents and invisibly guide collaboration, but current methods make it difficult to learn excellent policies in dynamic environments. Therefore, we propose a Self-Motivated learning via Role representations (SMR) frame. Firstly, we generate compact role representations based on the trajectories of agents and achieve rational dynamic role assignments by maximizing mutual information. Second, we use an attention mechanism to make action predictions based on observations and role representations and then generate intrinsic rewards based on their uncertainty about the dynamic environment, which in turn induces implicit collaboration. We conduct experiments and visualizations on different challenging benchmark platforms, and the experimental results show the superiority of our method.

Recently, location-based service has become a hot research topic. Mobile communication data records abundant information about users’ temporal and spatial characteristics. By modeling the users’ mobility based on mobile communication data, this can assist to understand human user patterns more accurately and deeply. Initially, this paper introduces three mainstream algorithms for user mobility modeling. Then this paper proposes a novel Markov chain based user mobility prediction scheme. The proposed scheme is implemented through four stages, including time and space division, Markov property examination, transition probability matrix calculation, Markov model weighting. Experimental results show that the proposed scheme can achieve higher accuracy compared with the traditional algorithms.

In the 5G era, mobile networks gradually become complex, and there are also high requirements for network operation and maintenance. As log data is important information to reflect the status of network devices, the monitoring of log data generated by network devices has become an important part of network operation and maintenance. But the massive amount of log data generated by large-scale network devices has already exceeded the range of human processing capabilities. And the introduction of artificial intelligence algorithms can optimize the detection of log anomalies and reduce network operation and maintenance costs under the challenges of high complexity of 5G networks. This paper proposes a Mahalanobis distance and Pauta criterion based log anomaly detection (MPLAD) algorithm for 5G mobile network. On the basis of solving the shortcomings of the existing log anomaly detection algorithms, it innovatively integrates the Mahalanobis distance algorithm and the Pauta criterion. Meanwhile, it also introduces the negative sample mechanism and the principal component analysis (PCA) method to achieve high accuracy, high efficiency and high compatibility towards 5G mobile network log anomaly detection.

Network slicing is a key technology in 5G. Generally, 5G networks employ slicing technology to provide the isolated and customizable network services for different scenarios (e.g., different vertical industries, different customers, different businesses etc.) in the form of virtual industry private networks. 5G slicing has the potential to meet the individual requirements of users and services, in terms of bandwidth, delay, reliability, and mobility. This paper gives an overall introduction to network slicing management, end-to-end processes, and wireless slicing capabilities. Then, this paper carries on algorithm research for wireless RB resource reservation and QoS scheduling. On one hand, the proposed algorithm clarifies the specific scheme of wireless RB resource reservation. On the other hand, the algorithm provides QoS scheduling parameter configuration. This lays a solid foundation for the implementation of slice differentiation capabilities in 5G wireless networks.

Data expansion is one of the commonly used steps in big data analysis applications. This paper proposes a data expansion method, which is based on operator data and considers multiple scenarios, multiple operating systems, and multiple operators in the target area. Factors such as the proportion of share and the difference in the proportion of users in the consumption power portrait are comprehensively expanded to obtain the full amount of user data of each target group in the target area. This method can be prepared to reflect changes in user data in time, and is applied to industries such as scene-based marketing and business planning.

With the rapid development of Internet industry, people are facing increasing challenge of information overload. Under this background, personalized recommendation has been comprehensively researched in order to provide a more time-saving and accurate way for information retrieval. In this paper, a novel hybrid recommendation scheme based on collaborative filtering and association rules is put forward to compensate the weaknesses of individual algorithms. This scheme is implemented through several steps. Firstly, it solves the problem of data sparsity with the help to association rules, and then employs the revised collaborative filtering to calculate the similarity among the items. Finally, it predicts user ratings for the unknown items based on item similarity and generates recommendation lists according to the prediction ratings. Experimental results show that the recommendation accuracy of this hybrid scheme has been dramatically improved compared to other traditional algorithms.

The economic expenditure of mobile network operators includes two parts, namely CAPEX and OPEX. CAPEX mainly includes the huge amount of capital invested in network infrastructure construction, while operating expenditure mainly includes expenditure for daily operation and maintenance. In order to achieve continuous coverage of wireless network, CAPEX needed for base station procurement is indispensable. Operators need to adopt more intelligent and scaled means to optimize the maintenance process of wireless network so as to better achieve the goal of cost reduction and efficiency increase. In this paper, a scheme of cell boundary prediction and base station location information verification based on machine learning is proposed, which innovatively introduces the machine learning algorithm into network optimization analysis and improve the verification efficiency and reduce the input of manpower.