In autonomous driving, perception plays a critical role as it serves as a fundamental requirement for both planning and control. Currently, most perception tasks are processed independently, which requires designing multiple models and networks to handle multiple tasks. This division leads to multiple sub-tasks in real-world environments, making it difficult to ensure real-time performance and communication between tasks. The paper introduces an innovative neural network architecture termed CUTransNet, which presents a unified approach capable of simultaneously detecting drivable areas, lane markings, and traffic objects, achieving multi-task processing with a single model. To build a more robust feature encoder, we proposed the CUT module that combines the global context ability of Transformers. The module is integrated into the convolutional neural network’s backbone to compensate for the low-level visual clues lost by Transformers and achieve higher detection accuracy. Experimental results on BDD100K demonstrate that CUT model surpasses traditional multi-task networks in both task accuracy and computational efficiency while maintaining high real-time performance.

Through mean-field optimization, mean-field reinforcement learning provides an applicable method for the environment of many agents. However, mean-field reinforcement learning uses only the mean action of the population as a basis, which may result in the conformity effect for individual decision-making and is challenging to implement in the complex real world with multi-agent systems. The main purpose of the study is to reduce the influence of the conformity effect using the signed safety field model to describe the population’s state. The comprehensive understanding of the information available to the population is aimed at enhancing individual decision-making. The state of the population guides the actions of local agents. The signed safety framework was also established, including the signed safety field Q and the AC learning algorithm. In addition, we demonstrated that these two algorithms could converge to the point of Nash equilibrium. The experiments in three situations were conducted to show the signed safety field method outperforms other baseline algorithms.

Removing bad weather effects from images is crucial for environmental perception, as it can provide clear and high-quality input for various downstream computer vision tasks. However, existing approaches are constrained to single weather removal or relying on multiple pre-trained weight sets to tackle different types of adverse weather scenarios. To addresses this challenge, We propose a two-stage knowledge learning mechanism utilizing knowledge distillation and feature alignment including knowledge teaching and knowledge examination. We also proposed RestoreCUFormer, an innovative model which merges the capabilities of CNN and Transformer to more accurately estimate the statistical patterns between the original and restored images. Experiments on multiple datasets achieve satisfactory results. The experimental findings demonstrate that the RestoreCUFormer model exhibits excellent performance in simultaneous adverse weather removal.

The machine learning-based decision algorithms commonly used in autonomous driving have led to the Safety of the Intended Functionality(SOTIF) issues due to their potential lack of functionality. To address these limitations, we propose M-DRTA, a distributed runtime assurance framework based on machine learning, which can provide safety assurance for multi-autonomous vehicles by making functional improvements to narrow the vehicle safety zone. We secure the entire multi-vehicle driving system by maintaining safety in local vehicles. In the M-DRTA, an independent runtime assurance framework is provided for each autonomous vehicle through redundant functional modules that include a deep neural network-based advanced controller, a recoverable safety controller, and a monitoring and assurance module. Monitor SOTIF risks by identifying trigger conditions, under-function status, etc., and provide safety through permission handover without unduly sacrificing performance. We tested and evaluated M-DRTA for the different number of vehicle states in a driving task. The experimental results show that M-DRTA can strike a proper balance between safety and efficiency compared to the baseline approach.

In the autonomous driving (AD) system, complex data dependencies exist between tasks with different activation rates, making it very hard to analyze systems’ real-time behaviors. This paper formulates the AD system as a multi-rate DAG and proposes an integrated framework to co-analyze the schedulability of individual tasks and the end-to-end latency of task chains in the multi-rate DAG. Integer linear programming (ILP) techniques are developed to guide how to drop redundant workload to increase the chance that timing requirements can be met. This paper proposed one analysis framework which enables an automated process in which designs of the AD system are created, analyzed and refined in an iterative way, i.e., the analysis result in the last iteration provides valuable guidance to redesign the AD system in the next iteration. Experiments are conducted to evaluate the performance of our analysis method.

Autonomous machines are commonly subject to real-time constraints. ROS 2, a widely-used robotics framework, considers real-time capabilities as a critical factor and is constantly evolving to address these challenges, e.g., the end-to-end timing guarantee and the real-time data fusion, etc. This paper studies the ROS message synchronizer, an integral component for multi-sensor data fusion, and provides a potential direction for the synchronizer's evolution in future versions of ROS 2. For effective data fusion, input data from different sensors must be sampled at time points that align within a specific range. This paper proposes a novel message synchronization policy to meet this requirement, called the SEAM, which Synchronizes the Earliest Arrival Messages once they fall within the specified range. Unlike traditional ROS synchronizers, the SEAM does not rely on prediction information for complex optimization. Instead, it uses information from already-arrived messages to construct a feasible synchronization scheme. We demonstrate the optimality of the SEAM by proving that it always finds a feasible scheme if one indeed exists. We incorporate the SEAM into ROS 2 and conduct experiments to evaluate its effectiveness compared to traditional ROS synchronizers.

With widespread use of common-off-the-shelf components and the drive towards connection with external environments, the real-time systems are facing more and more security problems. In particular, the real-time systems are vulnerable to the schedule-based attacks because of their predictable and deterministic nature in operation. In this paper, we present a security-aware real-time scheduling scheme to counteract the schedule-based attacks by preventing the untrusted tasks from executing during the attack effective window (AEW). In order to minimize the AEW untrusted coverage ratio for the system with uncertain AEW size, we introduce the protection window to characterize the system protection capability limit due to the system schedulability constraint. To increase the opportunity of the priority inversion for the security-aware scheduling, we design an online feasibility test method based on the busy interval analysis. In addition, to reduce the run-time overhead of the online feasibility test, we also propose an efficient online feasibility test method based on the priority inversion budget analysis to avoid online iterative calculation through the offline maximum slack analysis. Owing to the protection window and the online feasibility test, our proposed approach can efficiently provide best-effort protection to mitigate the schedule-based attack vulnerability while ensuring system schedulability. Experiments show the significant security capability improvement of our proposed approach over the state-of-the-art coverage oriented scheduling algorithm.

Automotive systems are often subjected to stringent requirements on the maximum data age of certain cause-effect chains. In this paper, we present an efficient method for formally analyzing maximum data age of cause-effect chains. In particular, we decouple the problem of bounding the maximum data age of a chain into a problem of bounding the releasing interval of successive Last-to-Last data propagation instances in the chain. Owing to the problem decoupling, a relatively tighter data age upper bound can be effectively obtained in polynomial time. Experiments demonstrate that our approach can achieve high precision analysis with lower computational cost.

Mobile edge computing enables users to run resource-intensive applications at the network edge equipped with small server clusters. The mobile services are heterogeneous and edge servers are generally resource-limited. Only a subset of services can be processed by an edge server in a time slot. In this paper, we study the joint service placement and computation scheduling (JSPCS) problem to optimize both service quality and operation cost. We formulate the optimization problem to maximize the worst utility among all the services, under the constraints of multiple types of resources, and the JSPCS problem is proved to be NP-hard. By linear relaxation, we provide a dual decomposition approach to decouple this hard problem into a sequence of tractable sub-problems. We propose the Lagrange duality based joint optimal service placement and computation scheduling (LD-JSPCS) algorithm to derive the optimal solution to JSPCS problem with linear relaxation. By iteratively solving a series of feasibility problems, we prove the proposed algorithm guarantees the convergence to the optimum. Theoretical analysis and extensive simulations are performed, validating the efficiency of LD-JSPCS in service provision with limited resources.

Deep Neural Networks (DNNs) are increasingly deployed in battery-powered and resource-constrained devices. However, the most accurate DNNs usually require millions of parameters and operations, making them computation-heavy and energy-expensive, so it is an important topic to develop energy efficient DNN models. In this paper, we present an efficient DNN training framework under energy constraint to improve the energy efficiency of DNN inference. The key idea of this research is inspired by the observation that the input data of DNNs is usually inherently sparse and such sparsity can be exploited by sparse tensor DNN accelerators to eliminate ineffectual data access and compute. Therefore, we can enhance the inference accuracy within the energy budget by strategically controlling the sparsity of the input data. We build an energy consumption model for the sparse tensor DNN accelerator to quantify the inference energy consumption from the perspective of data access and data processing. In particular, we define a metric (named sporadic degree) to characterise the influence of the number of sporadic values in the sparse input on the energy consumption of data access for the sparse tensor DNN accelerator. Based on the proposed quantitative energy consumption model, we present an efficient pooling-based input mask training algorithm to optimize the energy efficiency of DNN inference by enhancing the input sparsity and reducing the number of sporadic values in the masked input. Experiments show that compared with the state-of-the-art methods, our proposed method can achieve higher inference accuracy with lower energy consumption and storage requirement owing to higher sparsity and lower sporadic degree of the masked input.

Directed acyclic graph (DAG) becomes a popular model for modern real-time embedded software. It is really a challenge to bound the worst-case response time (WCRT) of DAG task. Parallelism, dependencies and mutual exclusion become three of the most critical properties of real-time parallel tasks. Recent work applied prioritizing techniques to reduce DAG task's WCRT bound, which has well studied the first two properties, i.e., parallelism and dependencies, but leaves the mutually exclusive property as an open problem. This paper focuses on all the three properties of real-time parallel software, and investigates how to estimate the WCRT of the DAG task model with mutually exclusive vertices and under prioritized list scheduling algorithms. We derive a reasonable WCRT bound for such a complicated DAG task, and prove that the corresponding WCRT bound computation problem is strongly NP-hard. It means that there are no pseudo-polynomial time algorithms to compute the WCRT bound. For the prioritized DAG with a constant number of mutual exclusive vertices, we develop a dynamic programming algorithm that is able to estimate the WCRT bound within pseudo-polynomial time. Experiments are conducted to evaluate the performance of our analysis method implemented with different priority assignment policies against the state-of-the-art.

Multi-agent reinforcement learning (MARL) based methods for adaptive traffic signal control (ATSC) have shown promising potentials to solve the heavy traffic problems. The existing MARL methods adopt centralized or distributed strategies. The former only models the environment as an agent and suffers from the exponential growth of action and state space. The latter extends the independent reinforcement learning methods, such as DQN, to multiple interactions directly or propagates information, such as state and policy, without taking their qualities into account. In this paper, we propose a multi-agent transfer reinforcement learning method to enhance the performance of MARL for ATSC, which is termed as multi-agent transfer soft actor-critic with the multi-view encoder (MT-SAC). The MT-SAC combines centralized and distributed strategies. In MT-SAC, we propose a multi-view state encoder and a transfer learning paradigm with guidance. The encoder processes input states from multiple perspectives and uses an attention mechanism to weigh the neighborhood information. While the paradigm enables the agents to handle different conditions for improving generalization abilities by transfer learning. Experimental studies on different scale road networks show that the MT-SAC outperforms the state-of-the-art algorithms and makes the traffic signal controllers more collaborative and robust.

OpenMP is a promising framework for developing parallel real-time software on multi-cores. Recently, many graph-based task models representing realistic features of OpenMP task systems have been proposed and analyzed. However, all previous studies did not model the loop structures, which is common in OpenMP task systems. In this paper, we formulate the workload of OpenMP task systems with loop structures as the cyclic graph model and study how to compute safe upper bounds for the worstcase response time (WCRT). The loop structures combined with the creation of tasks and conditional branches result in a large state space. Simply unrolling the loop and/or enumerating all the possible execution flows would be computationally intractable. As the major technical contribution, we develop a linear-time dynamic programming algorithm to compute the WCRT bound without unrolling loops or explicitly enumerating the execution flows. Experiments with both synthetic task graphs and realistic OpenMP programs are conducted to evaluate the performance of our method.

Research on modeling and analysis of real-time computing systems has been done in two areas, model checking and real-time scheduling theory. In model checking, an expressive modeling formalism such as timed automata (TA) is used to model complex systems, but the analysis is typically very expensive due to state-space explosion. In real-time scheduling theory, the analysis techniques are highly efficient, but the models are often restrictive. In this paper, we aim to exploit the possibility of applying efficient analysis techniques rooted in real-time scheduling theory to analysis of real-time task systems modeled by timed automata with tasks (TAT). More specifically, we develop efficient techniques to analyze the feasibility of TAT-based task models (i.e., whether all tasks can meet their deadlines on single-processor) using demand bound functions (DBF), a widely used workload abstraction in real-time scheduling theory. Our proposed analysis method has a pseudo-polynomial time complexity if the number of clocks used to model each task is bounded by a constant, which is much lower than the exponential complexity of the traditional model-checking based analysis approach (also assuming the number of clocks is bounded by a constant). We apply dynamic programming techniques to implement the DBF-based analysis framework, and propose state space pruning techniques to accelerate the analysis process. Experimental results show that our DBF-based method can analyze a TAT system with 50 tasks within a few minutes, which significantly outperforms the state-of-the-art TAT-based schedulability analysis tool TIMES.

End-to-end latency analysis is one of the key problems in the automotive embedded system design. In this paper, we propose an efficient worst-case end-to-end latency analysis method for data chains of periodic real-time tasks executed on multiprocessors under a partitioned fixed-priority preemptive scheduling policy. The key idea of this research is to improve the analysis efficiency by transforming the problem of bounding the worst-case latency of the data chain to a problem of bounding the releasing interval of data propagation instances for each pair of consecutive tasks in the chain. In particular, we derive an upper bound on the releasing interval of successive data propagation instances to yield the desired data chain latency bound by a simple accumulation. Based on the above idea, we present an efficient latency upper bound analysis algorithm with polynomial time complexity. Experiments with randomly generated task sets based on a generic automotive benchmark show that our proposed approach can obtain a relatively tighter data chain latency upper bound with lower computational cost.

Autonomous driving is one of the most important AI applications and has attracted extensive interest in recent years. A large number of studies have successfully applied reinforcement learning techniques in various aspects of autonomous driving, ranging from low-level control of driving maneuvers to higher level of strategic decision-making. However, comparatively less progress has been made in investigating how co-existing autonomous vehicles would interact with each other in a common environment and how reinforcement learning can be helpful in such situations by applying multiagent reinforcement learning techniques in the high-level strategic decision-making of the following or overtaking for a group of autonomous vehicles in highway scenarios. Learning to achieve coordination among vehicles in such situations is challenging due to the unique feature of vehicular mobility, which renders it infeasible to directly apply the existing coordinated learning approaches. To solve this problem, we propose using dynamic coordination graph to model the continuously changing topology during vehicles' interactions and come up with two basic learning approaches to coordinate the driving maneuvers for a group of vehicles. Several extension mechanisms are then presented to make these approaches workable in a more complex and realistic setting with any number of vehicles. The experimental evaluation has verified the benefits of the proposed coordinated learning approaches, compared with other approaches that learn without coordination or rely on some traditional mobility models based on some expert driving rules.

Multiprocessor platforms have been widely applied in safety-critical domains to accommodate the increasing computation requirement of modern real-time applications. In this paper, we present a workload-aware harmonic partitioned multiprocessor scheduling scheme for periodic real-time tasks with constrained deadlines under the fixed-priority preemptive scheduling policy. In particular, two grouping metrics effectively integrating both harmonicity and workload characteristic are designed to guide our task partition. With those metrics, our scheme can greatly improve system utilization by taking advantage of the combination of harmonic relationship exploration and workload awareness. Experiments show that our proposed scheme significantly outperforms existing approaches in terms of schedulability.

Achieving coordination is crucial in organizational control. This paper investigates a middle ground solution between decentralized interactions and centralized administrations for coordinating agents beyond inefficient behavior. We first propose the price of governance (PoG) to evaluate how such a middle ground solution performs in terms of effectiveness and cost. We then propose a hierarchical supervision framework to explicitly model the PoG, and define step by step how to realize the core principle of the framework and compute the optimal PoG for a control problem. Two illustrative case studies are carried out to exemplify the applications of the proposed framework and its methodology. Results show that the hierarchical supervision framework is capable of promoting coordination among agents while bounding administrative cost to a minimum in different kinds of organizational control problems.

Researches have shown difficulties in obtaining proximity while maintaining diversity for many-objective optimization problems. Complexities of the true Pareto front pose challenges for the reference vector-based algorithms for their insufficient adaptability to the diverse characteristics with no priori. This paper proposes a many-objective optimization algorithm with two interacting processes: cascade clustering and reference point incremental learning (CLIA). In the population selection process based on cascade clustering (CC), using the reference vectors provided by the process based on incremental learning, the nondominated and the dominated individuals are clustered and sorted with different manners in a cascade style and are selected by round-robin for better proximity and diversity. In the reference vector adaptation process based on reference point incremental learning, using the feedbacks from the process based on CC, proper distribution of reference points is gradually obtained by incremental learning. Experimental studies on several benchmark problems show that CLIA is competitive compared with the state-of-the-art algorithms and has impressive efficiency and versatility using only the interactions between the two processes without incurring extra evaluations.

Multiprocessor platforms, widely adopted to realize real-time systems nowadays, bring the probabilistic characteristic to such systems because of the performance variations of complex chips. In this paper, we present a harmonic partitioned scheduling scheme with workload awareness for periodic probabilistic realtime tasks on multiprocessors under the fixed-priority preemptive scheduling policy. The key idea of this research is to improve the overall schedulability by strategically arranging the workload among processors based on the exploration of the harmonic relationship among probabilistic real-time tasks. In particular, we define a harmonic index to quantify the harmonicity among probabilistic real-time tasks. This index can be obtained via the harmonic period transformation and probabilistic cumulative worst case utilization calculation of these tasks. The proposed scheduling scheme first sorts tasks with respect to the workload, then packs them to processors one by one aiming at minimizing the increase of harmonic index caused by the task assignment. Experiments with randomly generated task sets show significant performance improvement of our proposed approach over the existing harmonic partitioned scheduling algorithm for probabilistic real-time systems.

Advances of mobile technology and global booming of “smartphone economy” promote a tremendous growth of smartphone-oriented applications with an exponential increase of mobile traffic in the past decade, resulting in expectable saturation of LTE spectrum in the next few years. Mobile-to-mobile (M2M) communications, capable of extending LTE capacity with enhanced spectrum efficiency, have been considered as a promise solution to this problem. One popular approach to deploy the M2M technology is to establish an M2M subsystem as an underlay to the current LTE network so that the M2M link can share the same radio resource with LTE regular links. Although this scheme can further explore the spectrum efficiency, it is challenging to design such an M2M subsystem without harmful interference to LTE regular users. We propose in this paper a novel proactive interference cancellation mechanism to form an interference-free underlay. The major innovation of the proposed framework is to use the codebook-based precoding technique to design appropriate precoders for eNB and M2M transmitter in order to achieve maximal reception interference suppression proactively at the transmitter side. Since the codebook-based precoding technique has already been employed in LTE, the proposed scheme is compatible to current LTE systems and applicable for real-world implementation. This is in strong contrast to several existing interference cancellation M2M schemes that highly rely on the unrealistic assumption on theoretical-oriented channel state information (CSI) feedback. Preliminary simulation results demonstrate the efficiency of the proposed scheme.

Single materials have colors which form straight lines in RGB space. However, in severe shadow cases, those lines do not intersect the origin, which is inconsistent with the description of most literature. This paper is concerned with the detection and correction of the offset between the intersection and origin. First, we analyze the reason for forming that offset via an optical imaging model. Second, we present a simple and effective way to detect and remove the offset. The resulting images, named ORGB, have almost the same appearance as the original RGB images while are more illumination-robust for color space conversion. Besides, image processing using ORGB instead of RGB is free from the interference of shadows. Finally, the proposed offset correction method is applied to road detection task, improving the performance both in quantitative and qualitative evaluations.

Abstract In this paper, we present an innovative, animated traffic simulation method that we designed to feature an enhanced sense of reality and diversity of traffic flows. Instead of the typical one‐off initialization, our simulation method includes continuous, real trajectory data input providing an interactive control function that maximizes the characteristics of real‐world traffic flows. Our fusion models represent a comprehensive integration of the interactions among real‐data‐driven and virtual vehicles, thus depicting accurately the irregularity of traffic flows. Test results showed that animations generated via our proposed method depict inverse and irregular vehicle driving behaviors throughout the entire traffic flow.

Large scale optimization problems arise in diverse fields. Decomposing the large scale problem into small scale subproblems regarding the variable interactions and optimizing them cooperatively are critical steps in an optimization algorithm. To explore the variable interactions and perform the problem decomposition tasks, we develop a two stage variable interaction reconstruction algorithm. A learning model is proposed to explore part of the variable interactions as prior knowledge. A marginalized denoising model is proposed to construct the overall variable interactions using the prior knowledge, with which the problem is decomposed into small scale modules. To optimize the subproblems and relieve premature convergence, we propose a cooperative hierarchical particle swarm optimization framework, where the operators of contingency leadership, interactional cognition, and self-directed exploitation are designed. Finally, we conduct theoretical analysis for further understanding of the proposed algorithm. The analysis shows that the proposed algorithm can guarantee converging to the global optimal solutions if the problems are correctly decomposed. Experiments are conducted on the CEC2008 and CEC2010 benchmarks. The results demonstrate the effectiveness, convergence, and usefulness of the proposed algorithm.

Road detection algorithms constitute a basis for intelligent vehicle systems which are designed to improve safety and efficiency for human drivers. In this paper, a novel road detection approach intended for tackling illumination-related effects is proposed. First, a grayscale image of modified saturation is derived from the input color image during preprocessing, effectively diminishing cast shadows. Second, the road boundary lines are detected, which provides an adaptive region of interest for the following lane-marking detection. Finally, an improved feature-based method is employed to identify lane-markings from the shadows. The experimental results show that the proposed approach is robust against illumination-related effects.

Multiagent learning (MAL) is a promising technique for agents to learn efficient coordinated behaviors in multiagent systems (MASs). In MAL, concurrent multiple distributed learning processes can make the learning environment nonstationary for each individual learner. Developing an efficient learning approach to coordinate agents' behaviors in this dynamic environment is a difficult problem, especially when agents do not know the domain structure and have only local observability of the environment. In this paper, a coordinated MAL approach is proposed to enable agents to learn efficient coordinated behaviors by exploiting agent independence in loosely coupled MASs. The main feature of the proposed approach is to explicitly quantify and dynamically adapt agent independence during learning so that agents can make a trade-off between a single-agent learning process and a coordinated learning process for an efficient decision making. The proposed approach is employed to solve two-robot navigation problems in different scales of domains. Experimental results show that agents using the proposed approach can learn to act in concert or independently in different areas of the environment, which results in great computational savings and near optimal performance.

Social dilemmas have attracted extensive interest in the research of multiagent systems in order to study the emergence of cooperative behaviors among selfish agents. Understanding how agents can achieve cooperation in social dilemmas through learning from local experience is a critical problem that has motivated researchers for decades. This paper investigates the possibility of exploiting emotions in agent learning in order to facilitate the emergence of cooperation in social dilemmas. In particular, the spatial version of social dilemmas is considered to study the impact of local interactions on the emergence of cooperation in the whole system. A double-layered emotional multiagent reinforcement learning framework is proposed to endow agents with internal cognitive and emotional capabilities that can drive these agents to learn cooperative behaviors. Experimental results reveal that various network topologies and agent heterogeneities have significant impacts on agent learning behaviors in the proposed framework, and under certain circumstances, high levels of cooperation can be achieved among the agents.

Broadcast transmission is an effective approach for safe-related information transmission to achieve cooperative driving in Inter-Vehicle Communication (IVC), especially in the scenario of an urban intersection. In the past, several approaches have been proposed to solve the broadcast storm problem in multi-hop wireless networks. However, none of them take the traffic phase and traffic signal lights of real-world scenarios into consideration. In this paper, we propose An Intersection Broadcast Scheme Based on Traffic Phase (IBSTP), which extends the CLMP protocol only conceiving for single-direction environments. Moreover, it resolves several fundamental challenges such as message redundancy, hidden terminals, and broadcast storms. When there is an intersection in the path of the message dissemination, IBSTP ensures that a relaying node is selected to initialize directional broadcast along every road segment. The intersection is divided into several areas according to the traffic phase information from traffic lights. We define the valid areas and only the vehicles in valid areas can participate in contending for relaying nodes. Since every road has a relaying node broadcasting message to the next intersection, the reliability of transmitting emergency message is improved, and the time of broadcasting message to the next intersection decreases. Network simulator (NS-2) simulation results are given to confirm our analysis that the IBSTP not only can improve reliability of initializing directional broadcast but can reduce the time of broadcasting to around intersections.

AIM is one of the leading Autonomous Intersection Management mechanisms based on Multiagent System (MAS) for alleviating traffic congestion specially at intersections. One of the concerned problems on AIM, however, lies in the communication complexity of the system. Previously, the driver agent has no choice, but to completely retransmit its adjusted request information when the former reservation is rejected by the intersection manager, which results in the increase of interaction complexity between agents and the plenty of redundant data transmission. In this paper, we present an incremental data synchronization policy ksync for driver agent to avoid such redundant retransmission. In particular, we first introduce the basic properties of ksync policy. Second, we demonstrate how ksync could be well integrated into the knowledge base of driver agent as one of its essential policies. Third, we prove by experimental evaluation that the average data compression rate can be improved by over 80% exploiting ksync. Finally, we propose some of the most significant research prospects on ksync using the techniques in data mining and machine learning.

Cloud endows application with the ability of controlling runtime environment dynamically. Comparing with traditional one, Cloud APPlication (CAPP) could be more dynamic and autonomic. However, enabling CAPP to handle problems such as performance optimization or resources utility efficiency improvement in complex cloud environment with existing technologies is difficult and problematic. To address this problem, we propose a BDI (Belief-Desire-Intention) model and multi-agent oriented approach to decouple autonomous management functionality with CAPP, and simplify the management policy configuration process. We use the BDI agent paradigm to specify application and environment fact as belief, the CAPP's SLOs (Service Level Objectives) and Cloud Environment (CE) resources utility improvement desire as goal, means to achieve goal as action plan. A BDI agent oriented architecture and a Bayesian Network based belief inference model for the process of reasoning in intelligent agent is proposed to tackle CAPP autonomic management problem in cloud environment also. A prototype of this design is applied to automatically manage several multi-tiered web applications running in cloud environment to demonstrate the effectiveness of our design.

This paper addresses the problem of how routers efficiently select the optimal routes in large-scale networks. For the first time, it proposes Aggregation Tree Routing Model (ATRM) for dynamic topology changes. Aggregation Tree is first constructed in this model based on various parameter characteristics of links between routers, which greatly narrows the searching space of the routing procedure within much smaller domains. When network state changes, protocol calls the increment solution presented in this paper, updating the both two kinds of state changes in dynamic networks including link cost changes with time and topology structure changes with time. This solution is composed of three sub-algorithms-Link Deletion Algorithm, Link Addition Algorithm and Link Change Algorithm, and merely modifies affected information of links without re-routing in the whole network, as well as satisfying QoS constrains. The work achieves a logarithmic reduction in communication complexity and the simulation demonstrates that this model obtains high performance in routing accuracy as expected.

Software Architecture (SA) is emerging as an important research area in software engineering and forms the backbone for building successful softwareintensive systems. Based on practical requirements, especially the requirements of distributed applications and Internet applications, a new architectural style referred to as TreeSA is proposed. The primary elements of TreeSA and he message routing mechanism are discussed. Finally, an application based on TreeSA is outlined.