Search

In 5G, 6G and beyond networks, tenants need capabilities to reconfigure network slices since they must react quickly to changing network conditions and end-users' demands to meet Service Level Agreements. Offering reconfiguration operations to tenants is challenging since those functions must be autonomous and governed by high-level network management policies. Existing approaches face the network slice reconfiguration problem from the provider perspective, disregarding the importance of providing slice reconfiguration capabilities to tenants. This paper presents an approach called ATRAP to demonstrate the feasibility of using an autonomic control loop and automated planning for reconfiguring network slices from the tenant perspective. ATRAP introduces a tenant-oriented architecture based on the monitor-analyze-plan-execute-knowledge method and automated planning for computing reconfiguration plans autonomously. An ATRAP's plan aims to turn a network from a source configuration where one or more intents representing high-level network management policies are unmet into a target configuration in which the network meets the intents again. As ATRAP represents a network slice as a Service Function Chain comprising Virtual Network Functions (VNFs) and virtual links connecting them, a reconfiguration plan involves tasks to migrate VNFs and virtual links into the substrate network in a particular order. Results revealed as ATRAP computes plans with few migrations of VNFs and their adjacent links, leading to low reconfiguration costs related to short service disruptions. Also, results showed as ATRAP's planning time depends on the size of the substrate network and the tenant's slices. The results evidence that ATRAP is an attractive and feasible solution for the in-tenant reconfiguration of network slices. • An architecture based on MAPE-K and AP for reconfiguring network slices autonomously. • A State Transition System-based model for the in-tenant slice reconfiguration problem. • AP-problems in PDDL that enables further AP exploration to reconfigure network slices. [ABSTRACT FROM AUTHOR]

Vulnerability assessment and security configuration activities are heavily reliant on expert knowledge. This requirement often results in many systems being left insecure due to a lack of analysis expertise and access to specialist resources. It has long been known that a system’s event logs provide historical information depicting potential security breaches, as well as recording configuration activities. However, identifying and utilising knowledge within the event logs is challenging for the non-expert. In this paper, a novel technique is developed to process security event logs of a computer that has been assessed and configured by a security professional, extract key domain knowledge indicative of their expert decision making, and automatically apply learnt knowledge to previously unseen systems by non-experts. The technique converts event log entries into an object-based model and dynamically extracts associative rules. The rules are further improved in terms of quality using a temporal metric to autonomously establish temporal-association rules and acquire a domain model of expert configuration tasks. The acquired domain model and problem instance generated from a previously unseen system can then be used to produce a plan-of-action, which can be exploited by non-professionals to improve their system’s security. Empirical analysis is subsequently performed on 20 event logs, where identified plan traces are discussed in terms of accuracy and performance. [ABSTRACT FROM AUTHOR]

Modern organizations execute processes to deliver product and services, whose enactment needs to adhere to laws, regulations and standards. Conformance checking is the problem of pinpointing where deviations are observed. This paper shows how instances of the conformance checking problem can be represented as planning problems in PDDL (Planning Domain Definition Language) for which planners can find a correct solution in a finite amount of time. If conformance checking problems are converted into planning problems, one can seamlessly update to the recent versions of the best performing automated planners, with evident advantages in term of versatility and customization. The paper also reports on results of experiments conducted on two real-life case studies and on eight larger synthetic ones, mainly using the Fast-downward planner framework to solve the planning problems due to its performances. Some experiments were also repeated though other planners to concretely showcase the versatility of our approach. The results show that, when process models and event logs are of considerable size, our approach outperforms existing ones even by several orders of magnitude. Even more remarkably, when process models are extremely large and event log traces very long, the existing approaches are unable to terminate because they run out of memory, while our approach is able to properly complete the alignment task. [ABSTRACT FROM AUTHOR]

Traveling recommendation systems have become very popular applications for organizing and planning tourist trips. Among other challenges, these applications are faced with the task of maintaining updated information about popular tourist destinations, as well as providing useful tourist guides that meet the users preferences. In this work we present the PlanTour , a system that creates personalized tourist plans using the human-generated information gathered from the minube 1 1 www.minube.com traveling social network. The system follows an automated planning approach to generate a multiple-day plan with the most relevant points of interest of the city/region being visited. Particularly, the system collects information of users and points of interest from minube , groups these points with clustering techniques to split the problem into per-day sub-problems. Then, it uses an off-the-shelf domain-independent automated planner that finds good quality tourist plans. Unlike other tourist recommender systems, the PlanTour planner is able to organize relevant points of interest taking into account user’s expected drives, and user scores from a real social network. The paper also highlights how to use human provided recommendations to guide the search for solutions of combinatorial tasks. The resulting intelligent system opens new possibilities of combining human-generated knowledge with efficient automated techniques when solving hard computational tasks. From an engineering perspective we advocate for the use of declarative representations of problem solving tasks that have been shown to improve modeling and maintenance of intelligent systems. [ABSTRACT FROM AUTHOR]

Many automated planning systems allow users to specify their preferences in order to generate plans that are of high quality according to specified preferences. However, specifying preferences upfront can be time-consuming and difficult for users as their preferences can be complex, not be known in advance, or largely incomplete, especially in complex and large applications. Although many preference representation models and elicitation methods have been proposed in the literature, their adaptation to planning is non-trivial and work in this area has been somewhat limited. In this work, we present a preference elicitation framework for automated planning. This framework allows for interaction with a user through a limited number of low burden comparison type queries and for subsequent learning of a preference relation predictor based on the user's responses. To help the user explore possible planning solutions and to assist them to easily discover and articulate their preferences, the framework prompts the user with planning solutions for small problems and attempts to learn the user's preference through a variety of small planning problems from a particular domain. The learned preferences can then be generalised to infer preferences for planning solutions to larger planning problems. We evaluate the framework using a variety of different benchmark planning domains. The results suggest that our framework can efficiently learn user preferences when provided with a limited number of preference queries in small problems, and generalise the user preferences with high accuracy to larger planning problems. • We present a preference elicitation framework for automated planning. • It allows users to explore small and simple planning problems to elicit preferences. • It interacts with users through low burden comparison type queries. • It then learns from user query responses using machine learning techniques. • Our findings suggest that our framework can efficiently learn from user preferences. [ABSTRACT FROM AUTHOR]

Error mapping of machine tools is a multi-measurement task that is planned based on expert knowledge. There are no intelligent tools aiding the production of optimal measurement plans. In previous work, a method of intelligently constructing measurement plans demonstrated that it is feasible to optimise the plans either to reduce machine tool downtime or the estimated uncertainty of measurement due to the plan schedule. However, production scheduling and a continuously changing environment can impose conflicting constraints on downtime and the uncertainty of measurement. In this paper, the use of the produced measurement model to minimise machine tool downtime, the uncertainty of measurement and the arithmetic mean of both is investigated and discussed through the use of twelve different error mapping instances. The multi-objective search plans on average have a 3% reduction in the time metric when compared to the downtime of the uncertainty optimised plan and a 23% improvement in estimated uncertainty of measurement metric when compared to the uncertainty of the temporally optimised plan. Further experiments on a High Performance Computing (HPC) architecture demonstrated that there is on average a 3% improvement in optimality when compared with the experiments performed on the PC architecture. This demonstrates that even though a 4% improvement is beneficial, in most applications a standard PC architecture will result in valid error mapping plan. [ABSTRACT FROM AUTHOR]

In this work we propose a planning and acting architecture endowed with a module which learns to select subgoals with Deep Q-Learning. This allows us to decrease the load of a planner when faced with scenarios with real-time restrictions. We have trained this architecture on a video game environment used as a standard test-bed for intelligent systems applications, testing it on different levels of the same game to evaluate its generalization abilities. We have measured the performance of our approach as more training data is made available, as well as compared it with both a state-of-the-art, classical planner and the standard Deep Q-Learning algorithm. The results obtained show our model performs better than the alternative methods considered, when both plan quality (plan length) and time requirements are taken into account. On the one hand, it is more sample-efficient than standard Deep Q-Learning, and it is able to generalize better across levels. On the other hand, it reduces problem-solving time when compared with a state-of-the-art automated planner, at the expense of obtaining plans with only 9% more actions. • Deep Q-Learning is used by a planning agent to learn to select subgoals. • Our approach reduces planning time in online execution. • Our approach generalizes better than standard Deep Q-Learning. • Our approach is more sample-efficient than standard Deep Q-Learning. [ABSTRACT FROM AUTHOR]

Highlights: [•] We present a Framework for automated composition of Advanced Telecom Services. [•] We describe a metamodel for user context information. [•] We translate requests in Natural language into automated planning instances. [ABSTRACT FROM AUTHOR]

Highlights: [•] A formalization of instructional design for CSCL using HTN planning is proposed. [•] We used the proposed formalization to model and design adaptive CSCL scenarios. [•] To validate our approach a CSCL courseware generator was created. [•] Case studies are presented showing that the generator can automatically design personalized CSCL scenarios. [ABSTRACT FROM AUTHOR]

Abstract: With the current trend towards cognitive manufacturing systems to deal with unforeseen events and disturbances that constantly demand real-time repair decisions, learning/reasoning skills and interactive capabilities are important functionalities for rescheduling a shop-floor on the fly taking into account several objectives and goal states. In this work, the automatic generation and update through learning of rescheduling knowledge using simulated transitions of abstract schedule states is proposed. Deictic representations of schedules based on focal points are used to define a repair policy which generates a goal-directed sequence of repair operators to face unplanned events and operational disturbances. An industrial example where rescheduling is needed due to the arrival of a new/rush order, or whenever raw material delay/shortage or machine breakdown events occur are discussed using the SmartGantt prototype for interactive rescheduling in real-time. SmartGantt demonstrates that due date compliance of orders-in-progress, negotiating delivery conditions of new orders and ensuring distributed production control can be dramatically improved by means of relational reinforcement learning and a deictic representation of rescheduling tasks. [Copyright &y& Elsevier]

Abstract: The automatic generation of individualized plans in specific domains is an open problem that combines aspects related to automated planning, machine learning or recommendation systems technology. In this paper, we focus on a specific instance of that task; that of generating e-learning courses adapted to students’ profiles, within the automated planning paradigm. One of the open problems in this type of automated planning application relates to what is known as oversubscription: given a set of goals, each one with a utility, obtain a plan that achieves some (or all) the goals, maximizing the utility, as well as minimizing the cost of achieving those goals. In the generation of e-learning designs there is only one goal: generating a course design for a given student. However, in order to achieve the goal, the course design can include many different kinds of activities, each one with a utility (that depend on the student profile) and cost. Furthermore, these activities are usually grouped into clusters, so that at least one of the activities in each cluster is needed, though many more can be used. Finally, there is also an overall cost threshold (usually in terms of student time). In this paper, we present our work on building an individualized e-learning design. We pose each course design as a variation of the oversubscription problem, that we call the clustered-oversubscription problem, and we use linear programming for assisting a planner to generate the design that better adapts to the student. [Copyright &y& Elsevier]

Abstract: Although new AI planning algorithms and techniques are being developed and improved rapidly, there is a lack of efficient and easy to use systems able to incorporate and utilize them. Furthermore, while visual representation facilitates design, maintenance and comprehension of planning domains and problems, very few systems incorporate it. This paper presents VLEPPO, an integrated system aiming at visually modeling planning domains and problems through a convenient graphical interface, while maintaining compatibility with the Planning Domain Definition Language (PDDL), with import and export features. Solutions to planning problems can be obtained by invoking different planners employing the web services technology. The demonstration of the system is performed through a case study involving web service composition viewed as a planning problem. [Copyright &y& Elsevier]