Spain

Power grid data are going “big” with the deployment of various sensors. The big data in power grids create huge opportunities for applying artificial intelligence technologies to improve resilience and reliability. This presentation introduces multiple real-world applications based on artificial intelligence and big data to improve power grid situational awareness and resilience. These applications include event detection, inertia estimation, event location and magnitude estimation, data authentication, control, and stability assessment. These applications are operating on a real-world system called FNET/GridEye, which is a wide-area measurement network and arguably the world-largest cyber-physical system that collects power grid big data. These applications showed much better performance compared with conventional approaches, and accomplished new tasks that are impossible to realized using conventional technologies. These encouraging results demonstrate that combining power grid big data and artificial intelligence can uncover and capture the non-linear correlation between power grid data and its stability indices, and will potentially enable many advanced applications that can significantly improve power grid resilience. 

ECAI 2020

Build Smart Grids on Big Data and Artificial Intelligence — A Real-world Example 

ECAI2020 featured a full programme of technical papers, as well as many AI-related events of interest for researchers, students and all attendants who are interested on contemporary AI, including:




**An extensive programme of workshops, tutorials, and invited speakers**

**The Prestigious Applications of Intelligent Systems conference (PAIS)**

**The Frontiers in AI track sessions**

**The Lab To Market event**

**The Women in AI time**

**The EU Challenges forum**

… and many more!

ECAI 2020 featured a full programme of technical papers, as well as many AI-related events of interest for researchers, students and all attendants who are interested on contemporary AI.

technical paper

"Utility companies have a great interest in identifying fraudulent
activity such as Non-Technical Losses (NTL). Typically, they resort
to machine learning solutions in order to automate the identifica-
tion of such losses. In this paper, we extend and improve an NTL-
detection framework: by including knowledge-based NTL segmen-
tation, we are able to not only provide more accurate predictions but
also to include better explanations for them. Our improved models
focus on specific types of NTL and, therefore, the explanations pro-
vided are easier to interpret, allowing the Stakeholders to make more
informed decisions. Our improvements and results may benefit other
industrial frameworks."

Knowledge-Based Segmentation to Improve Accuracy and Explainability in Non-Technical Losses Detection

Buildings' energy consumption has dramatically increased over the last decade, accounting for more than 35\% of global energy use. In this article, RESPOND's approach to improve building operation is shown for reducing energy demand peaks. Namely, RESPOND develops an Artificial Intelligent system to dispatch optimal Demand Response events maximizing the renewable energy generation and leveraging energy storage units. Furthermore, with views to ensuring dwellers' engagement with the project, the proposed DR events are aimed to generate the least disturbance in their every-day activities.

An Artificial Intelligent System for Demand Response in Neighbourhoods

Milgram's reality-virtuality continuum applies to interaction in the physical space dimension, going from real to virtual. However, interaction has a social dimension as well, that can go from real to artificial depending on the companion with whom the user interacts. In this paper we present our vision of the Reality-Artificiality bidimensional Continuum (RAC), we identify some challenges in its design and development and we discuss how reliable interactions might be supported inside RAC.

Engineering Reliable Interactions in the Reality-Artificiality Continuum

"Robots are often so complex that one person may not know all the ins and outs of the system. Inheriting software and hardware infrastructure with limited documentation and/or practical robot experience presents a costly challenge for an engineer or researcher.  The choice is to either re-build existing systems, or invest in learning the existing framework. No matter the choice, a reliable system which produces expected outcomes is necessary, and while rebuilding may at first appear easier than learning the system, future users will be faced with the same choice. This paper provides a method to allow for increased documentation of the robotic system, which in turn can be used to contribute in overall robot reliability.
To do this we propose the identification of a robot's core behaviors for use in Capability Analysis Tables (CATs).  CATs are a form of tabular documentation that connect the hardware and software inputs and outputs to the robot's core behaviors.  Unlike existing methods, CATs are flexible, easy to build, and understandable by non-expert robot users. We demonstrate this documentation method with an experimental example using an Unmanned Aerial Vehicle (UAV). "

Establishing Reliable Robot Behavior using Capability Analysis Tables

Long-term autonomy requires autonomous systems to adapt as their capabilities no longer perform as expected. To achieve this, a system must first be capable of detecting such changes. In this position paper presentation, we describe a system architecture for BDI autonomous agents capable of adapting to changes in a dynamic environment and outline the required research.

Adaptable and Verifiable BDI Reasoning

The main purpose of this work is to explore and investigate the main challenges that arise when we want to handle percepts and control the actuators of a robot with agent-oriented abstractions. In particular, the presentation focuses on how to program an autonomous robot with Jadescript.

Exploratory Experiments on Programming Autonomous Robots in Jadescript

Robots are soon going to be deployed in non-industrial environments. Before society can take such a step, it is necessary to endow complex robotic systems with mechanisms that make them reliable enough to operate in situations where the human factor is predominant. This calls for the development of robotic frameworks that can soundly guarantee that a collection of properties are verified at all times during operation. While developing a mission plan, robots should take into account factors such as human physiology. In this paper, we present an example of how a robotic application that involves human interaction can be modeled through hybrid automata, and analyzed by using statistical model-checking. We exploit statistical techniques to determine the probability with which some properties are verified, thus easing the state-space explosion problem. The analysis is performed using the Uppaal tool. In addition, we used Uppaal to run simulations that allowed us to show non-trivial time dynamics that describe the behavior of the real system, including human-related variables. Overall, this process allows developers to gain useful insights into their application and to make decisions about how to improve it to balance efficiency and user satisfaction.

Statistical Model Checking of Human-Robot Interaction Scenarios

Semi-supervised learning improves the performance of supervised machine learning by leveraging methods  from  unsupervised  learning  to  extract  information  not  explicitly  available  in  the  labels.Through the design of a system that enables a robot to learn inspection strategies from a human operator, we present a hybrid semi-supervised system capable of learning interpretable and verifiable models from demonstrations.  The system induces a controller program by learning from immersive demonstrations using sequential importance sampling.  These visual servo controllers are parametrised  by  proportional  gains  and  are  visually  verifiable  through  observation  of  the  robot’s position in the environment.  Clustering and effective particle size filtering allows the system to dis-cover goals in the state space. These goals are used to label the original demonstration for end-to-end learning of behavioural models.  The behavioural models are used for autonomous model predictive control and scrutinised for explanations. We implement causal sensitivity analysis to identify salient objects and generate counterfactual conditional explanations. These features enable decision making interpretation and post hoc discovery of the causes of a failure.  The proposed system expands on previous approaches to program synthesis by incorporating repellers in the attribution prior of the sampling process.  We successfully learn the hybrid system from an inspection scenario where an unmanned ground vehicle has to inspect, in a specific order, different areas of the environment. The system induces an interpretable computer program of the demonstration that can be synthesised to produce novel inspection behaviours.  Importantly, the robot successfully runs the synthesised pro-gram on an unseen configuration of the environment while presenting explanations of its autonomous behaviour.

Semi-supervised Learning From Demonstration Through Program Synthesis: An Inspection Robot Case Study

Automated machine learning (AutoML) systems aim at finding the best machine learning (ML) pipeline that automatically matches the task and data at hand. We investigate the robustness of machine learning pipelines generated with three AutoML systems, TPOT, H2O, and AutoKeras. In particular, we study the influence of dirty data on accuracy, and consider how using dirty training data may help create more robust solutions. Furthermore, we also analyze how the structure of the generated pipelines differs in different cases.

Testing the Robustness of AutoML Systems

"Human-Robot Collaboration (HRC) is rapidly replacing the traditional application of robotics in the manufacturing industry. Robots and human operators no longer have to perform their tasks in segregated areas and are capable of working in close vicinity and performing hybrid tasks---performed partially by humans and by robots.

We have presented a methodology in an earlier work to promote and facilitate formally modeling HRC systems, which are notoriously safety-critical. Relying on temporal logic modeling capabilities and automated model checking tools, we built a framework to formally model HRC systems and verify the physical safety of human operator against ISO 10218-2 standard. In order to make our proposed formal verification framework more appealing to safety engineers, whom are usually not very fond of formal modeling and verification techniques, we decided to couple our model checking approach with a 3D simulator that demonstrates the potential hazardous situations to the safety engineers in a more transparent way. This paper reports our co-simulation approach, using Morse simulator and Zot model checker."

Build Smart Grids on Big Data and Artificial Intelligence — A Real-world Example

Downloads

Next from ECAI 2020

Knowledge-Based Segmentation to Improve Accuracy and Explainability in Non-Technical Losses Detection

Similar lecture

Knowledge-Based Segmentation to Improve Accuracy and Explainability in Non-Technical Losses Detection

Build Smart Grids on Big Data and Artificial Intelligence — A Real-world Example

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ECAI 2020

Knowledge-Based Segmentation to Improve Accuracy and Explainability in Non-Technical Losses Detection

Similar lecture

Knowledge-Based Segmentation to Improve Accuracy and Explainability in Non-Technical Losses Detection

Downloads