Open Radio Access Network (O-RAN) architectures enable flexible, scalable, and cost-efficient mobile networks by disaggregating and virtualizing baseband functions. However, this flexibility introduces significant challenges for resource management, requiring joint optimization of functional split selection and virtualized unit placement under dynamic demands and complex topologies. Existing solutions often address these aspects separately or have limitations in large and real-world scenarios. In this work, we propose a novel Graph-Augmented Proximal Policy Optimization (GPPO) framework that leverages Graph Neural Networks (GNNs) for topology-aware feature extraction and integrates action masking to efficiently navigate the combinatorial decision space. Our approach jointly optimizes functional split and placement decisions, capturing the full complexity of O-RAN resource allocation. Extensive experiments on both small- and large-scale O-RAN scenarios demonstrate that GPPO consistently outperforms state-of-the-art baselines, achieving up to $18 \%$ lower deployment cost and $25 \%$ higher reward in multitopology evaluations, while maintaining perfect reliability. These results highlight the effectiveness and scalability of GPPO for practical O-RAN deployments.

Network Digital Twins (NDTs) are increasingly relying on data-driven approaches for modeling complex network dynamics. Traffic forecasting is crucial for NDTs to provide timely insights for automated network reconfiguration. Existing spatiotemporal forecasting methods, while effective, often rely on pre-constructed graphs, limiting their flexibility in dynamic network environments. This paper introduces Flex+ , an inductive graph-based learning model designed for traffic prediction in data-scarce scenarios. Flex+ focuses on individual eNodeB traffic prediction by extracting local spatial correlations from k-hop subgraphs, combined with temporal information. Its inductive design allows it to operate on unseen nodes during training, enabling adaptability to evolving network topologies. Empirical studies on a large-scale cellular traffic dataset demonstrate that Flex+ achieves a 5.9% improvement in accuracy in inductive settings and a 22% reduction in error in data-scarce scenarios when trained with only 3 days of traffic data. Notably, a Knowledge Distillation (KD) framework is introduced to reduce model size and accelerate inference time up to 10 times while maintaining prediction accuracy.

From a telecommunication standpoint, the surge in users and services challenges next-generation networks with escalating traffic demands and limited resources. Accurate traffic prediction can offer network operators valuable insights into network conditions and suggest optimal allocation policies. Recently, spatio-temporal forecasting, employing Graph Neural Networks (GNNs), has emerged as a promising method for cellular traffic prediction. However, existing studies, inspired by road traffic forecasting formulations, overlook the dynamic deployment and removal of base stations, requiring the GNN-based forecaster to handle an evolving graph. This work introduces a novel inductive learning scheme and a generalizable GNN-based forecasting model that can process diverse graphs of cellular traffic with one-time training. We also demonstrate that this model can be easily leveraged by transfer learning with minimal effort, making it applicable to different areas. Experimental results show up to ${9. 8 \%}$ performance improvement compared to the state-of-the-art, especially in rare-data settings with training data reduced to below $20 \%$.

IoT applications can be naturally modeled as a graph where the edges represent the interactions between devices, sensors, and their environment. Thing'in11https://www.thinginthefuture.com/ is a platform, initiated by Orange22Orange is a French multinational telecommunication operator. The platform manages a graph of millions of connected and non-connected objects using a commercial graph database. The graph of Thing'in is dynamic because loT devices create temporary connections between each other. Analyzing the history of these connections paves the way to new promising applications such as object tracking, anomaly detection, and forecasting the future behavior of devices. However, existing com-mercial graph databases are not designed with native temporal support which limits their usability in such use cases. In this paper, we discuss the design of a temporal graph management system Clock-G and introduce a new space-efficient storage technique δ-Copy+Log, Clock-G is designed by the devel-opers of the Thing'in platform and is currently being deployed into production. It differentiates from existing temporal graph management systems by adopting the δ-Copy+Log technique. This technique targets the mitigation of the apparent trade-off between the conflicting goals of the reduction of space usage and acceleration of query execution time. Our experimental results demonstrate that the δ-Copy+Log presents an overall better performance as compared to traditional storage methods in terms of space usage and query evaluation time.

Graph partitioning, a preliminary step of distributed graph processing, has been attracting increasing attention in the last decade. A high quality graph partitioning algorithm should facilitate graph processing by minimizing the communication overhead and maintaining the load balancing among distributed computing units. Offline partitioning algorithms usually require the knowledge of a complete graph, and therefore, are not adaptive to handle massive graph-structured data. On the contrary, streaming partitioning algorithms take edges or vertices as a stream and make partitioning decisions on the fly. However, the streaming manner faces dilemmas from time to time because of a lack of knowledge. Furthermore, an unmindful partitioning decision in such a dilemma could significantly decrease the partition quality. In this paper, we propose a novel window-based streaming graph partitioning algorithm (WSGP). WSGP leverages a greedy-based heuristic to perform edge partitioning. When facing a decision dilemma, WSGP utilizes a size-bounded window to buffer the edges. When the window is fully filled, an edge is poped and assigned to a partition. The assignment is decided by knowledge obtained from both the edges already settled and the ones still cached in the buffer window. Our experiments take into account various real-world benchmark graphs. The experimental results demonstrate that WSGP consistently has a smaller replication factor than the state-of-the-art algorithms by up to 23%, at a limited cost in terms of memory and comprehensive running time.

Fog computing consists in extending Cloud services down to the network edge by using resources such as base stations, routers and switches. It presents a dense, heterogeneous and geo-distributed infrastructure which pushes to investigate how data are placed within this infrastructure in order to minimize service latency, network utilization and energy consumption. iFogSim is a Fog and IoT environments simulator dedicated to manage IoT services in a Fog infrastructure. In this paper, we present an extension to iFogSim to be able to model and simulate scenarios with strategies aiming to optimize data placement in Fog and IoT contexts. Data placement problem is NP-Hard due to the large number of Fog nodes and the high amount of data to be placed. Thus, we added a support to divide and conquer strategies to subdivide the issued infrastructure into several parts hence reducing the data placement computing time. Moreover, the extension involves a generic smart city scenario with different workloads making it possible for the users to investigate the behavior of their strategies using various workloads. In order to optimize the execution time of the simulations, we parallelized the Floyd-Warshall algorithm. This algorithm is used in iFogSim to compute all shortest paths between nodes in order to simulate data transmission. We have evaluated this extension using the proposed smart city scenario with various infrastructure configurations. The experiments show that our extension has a small overhead in terms of simulation time and memory utilization.

Internet of Things (IoT) will be one of the driving application for digital data generation in the next years as more than 50 billions of objects will be connected by 2020. IoT data can be processed and used by different devices spread all over the network. The traditional way of centralizing data processing in the Cloud can hardly scale because it cannot satisfy many of the latency critical IoT applications. In addition, it generates a too high network traffic when the number of objects and services increase. Fog infrastructure provides a beginning of an answer to such an issue. In this paper, we present a data placement strategy for Fog infrastructures called iFogStor. The objective of iFogStor is to take profit of the heterogeneity and location of Fog nodes to reduce the overall latency of storing and retrieving data in a Fog. We formulated the data placement problem as a Generalized Assignment Problem (GAP) and proposed two ways to solve it: 1) an exact solution using integer programming and 2) a heuristic one based on geographical zoning to reduce the solving time. Both solutions proved very good performance as they reduced the latency by more than 86% as compared to a Cloud based solution and by 60% as compared to a naive Fog solution. Using geographical zoning heuristic can allow solving problems with large number of Fog nodes efficiently and in a couple of seconds making iFogStor feasible in runtime and scalable.

The k-set agreement problem is a generalization of the consensus problem: each process proposes a value, and each non-faulty process has to decide a value such that a decided value is a proposed value, and no more than k different values are decided. This paper focuses on the k-set agreement problem in the context of synchronous systems where up to t < n processes can experience crash or send omission failures (n being the total number of processes). The paper presents a k-set agreement protocol for this failure model (the first to our knowledge) which has two main outstanding features. (1) It provides the following early deciding and stopping property: no process decides or halts after the round min(/spl lfloor/f/k/spl rfloor/ + 2, /spl lfloor/t/k/spl rfloor/ + 1) where f is the number of actual crashes (0 /spl les/ f /spl les/ t). (2) It is decision-optimal. This new optimality criterion, suited to the omission failure model, concerns the number of processes that decide, namely, the protocol forces all the processes that do not crash to decide (regardless of whether they commit omission faults or not). It is noteworthy that each of these properties (early deciding/stopping vs decision-optimality) is not obtained at the detriment of the other. Last but not least, the protocol enjoys another first-class property, namely, simplicity.

In this paper, we design self-* novel solutions to the minimal connected sensor cover problem. The concept of self-* is used to include fault-tolerant properties like self-configuring, self-reconfiguring/self-healing, etc. We present two self-stabilizing, fully distributed, strictly localized, and scalable solutions, and show that these solutions are both self-configuring and self-healing. The proposed solutions are space optimal in terms of the number of states used per node. Another feature of the proposed algorithms is that the faults are contained only within the neighborhood of the faulty nodes. This paper also includes a comparison of the performance of the two proposed solutions in terms of the stabilization time, cover size metrics, and ability to cope with transient and permanent faults.

Consensus is a central problem of fault-tolerant distributed computing that, in the context of synchronous distributed systems, has received a lot of attention in the crash failure model and in the Byzantine failure model. This paper considers synchronous distributed systems made up of n processes, where up to t can commit failures by crashing or omitting to send or receive messages when they should ("process omission" failure model). It presents a protocol solving uniform consensus in such a context. This protocol has several noteworthy features. First, it is particularly simple. Then, it is optimal both in (1) the number of communication steps needed for processes to decide and stop, namely, min(f+2,t+1) where f is the actual number of faulty processes, and (2) the number of processes that can be faulty, namely t

Several approaches have been proposed to circumvent the impossibility to solve consensus in asynchronous distributed systems prone to process crash failures. Among them, randomization, unreliable failure detectors, and leader oracles have been particularly investigated. Recently a new approach (called “condition-based”) has been proposed. Let an input vector be a vector whose i-th entry contains the value proposed by process pi. The conditionbased approach consists in stating conditions on input vectors that make consensus solvable despite up to f process crashes. Several conditions have been proposed. (As an example, one of them requires that the greatest value in an input vector appears more than f times.) This paper presents an evaluation of the condition-based approach to solve consensus. It shows that this approach is particularly attractive and very efficient when the probability of process crashes is low (a common fact in practice). In these cases, the probability for the condition-based protocol to terminate is practically equal to 1.

No abstract available.