Text messaging-based conversational agents (CAs), popularly called chatbots, received significant attention in the last two years. However, chatbots are still in their nascent stage: They have a low penetration rate as 84% of the Internet users have not used a chatbot yet. Hence, understanding the usage patterns of first-time users can potentially inform and guide the design of future chatbots. In this paper, we report the findings of a study with 16 first-time chatbot users interacting with eight chatbots over multiple sessions on the Facebook Messenger platform. Analysis of chat logs and user interviews revealed that users preferred chatbots that provided either a 'human-like' natural language conversation ability, or an engaging experience that exploited the benefits of the familiar turn-based messaging interface. We conclude with implications to evolve the design of chatbots, such as: clarify chatbot capabilities, sustain conversation context, handle dialog failures, and end conversations gracefully.

Text messaging-based conversational systems, popularly called chatbots, have seen massive growth lately. Recent work on evaluating chatbots has found that there exists a mismatch between the chatbot's state of understanding (also called context) and the user's perception of the chatbot's understanding. Users found it difficult to use chatbots for complex tasks as the users were uncertain of the chatbots' intelligence level and contextual state. In this work, we propose Convey (CONtext View), a window added to the chatbot interface, displaying the conversational context and providing interactions with the context values. We conducted a usability evaluation of Convey with 16 participants. Participants preferred using chatbot with Convey and found it to be easier to use, less mentally demanding, faster, and more intuitive compared to a default chatbot without Convey. The paper concludes with a discussion of the design implications offered by Convey.

One of the major challenges confronting the widespread adoption of solar energy is the uncertainty of production. The energy generated by photo-voltaic systems is a function of the received solar irradiance which varies due to atmospheric and weather conditions. A key component required for forecasting irradiance accurately is the clear sky model which estimates the average irradiance at a location at a given time in the absence of clouds. Current methods for modelling clear sky irradiance are either inaccurate or require extensive atmospheric data, which tends to vary with location and is often unavailable. In this paper, we present a data-driven methodology, Blue Skies, for modelling clear sky irradiance solely based on historical irradiance measurements. Using machine learning techniques, Blue Skies is able to generate clear sky models that are more accurate spatio-temporally compared to the state of the art, reducing errors by almost 50%.

The connectivity model of a power distribution network can easily become outdated due to system changes occurring in the field. Maintaining and sustaining an accurate connectivity model is a key challenge for distribution utilities worldwide. This work shows that voltage time series measurements collected from customer smart meters exhibit correlations that are consistent with the hierarchical structure of the distribution network. These correlations may be leveraged to cluster customers based on common ancestry and help verify and correct an existing connectivity model. Additionally, customers may be clustered in combination with voltage data from circuit metering points, spatial data from the geographical information system, and any existing but partially accurate connectivity model to infer customer to transformer and phase connectivity relationships with high accuracy.

Virtual Power Plants (VPPs) are fast emerging as a suitable means of integrating small and distributed energy resources (DERs), like wind and solar, into the electricity supply network (Grid). VPPs are formed via the aggregation of a large number of such DERs, so that they exhibit the characteristics of a traditional generator in terms of predictability and robustness. In this work, we promote the formation of such "cooperative'' VPPs (CVPPs) using multi-agent technology. In particular, we design a payment mechanism that encourages DERs to join CVPPs with large overall production. Our method is based on strictly proper scoring rules and incentivises the provision of accurate predictions from the CVPPs---and in turn, the member DERs---which aids in the planning of the supply schedule at the Grid. We empirically evaluate our approach using the real-world setting of 16 commercial wind farms in the UK. We show that our mechanism incentivises real DERs to form CVPPs, and outperforms the current state of the art payment mechanism developed for this problem.

Self-organizing multi-agent systems provide a suitable paradigm for developing autonomic computing systems that manage themselves. Towards this goal, we demonstrate a robust, decentralized approach for structural adaptation in explicitly modeled problem solving agent organizations. Based on self-organization principles, our method enables the autonomous agents to modify their structural relations to achieve a better allocation of tasks in a simulated task-solving environment. Specifically, the agents reason about when and how to adapt using only their history of interactions as guidance. We empirically show that, in a wide range of closed, open, static, and dynamic scenarios, the performance of organizations using our method is close (70–90%) to that of an idealized centralized allocation method and is considerably better (10–60%) than the current state-of-the-art decentralized approaches.

This paper reports on a novel decentralized technique for planning agent schedules in dynamic task allocation problems. Specifically, we use a stochastic game formulation of these problems in which tasks have varying hard deadlines and processing requirements. We then introduce a new technique for approximating this game using a series of static potential games, before detailing a decentralized method for solving the approximating games that uses the distributed stochastic algorithm. Finally, we discuss an implementation of our approach to a task allocation problem in the RoboCup Rescue disaster management simulator. The results show that our technique performs comparably to a centralized task scheduler (within 6% on average), and also, unlike its centralized counterpart, it is robust to restrictions on the agents’ communication and observation ranges.