The co-development of hardware and software in industrial embedded systems frequently leads to compilation errors during continuous integration (CI). Automated repair of such failures is promising, but existing techniques rely on test cases, which are not available for non-compilable code. We employ an automated repair approach for compilation errors driven by large language models (LLMs). Our study encompasses the collection of more than 40000 commits from the product's source code. We assess the performance of an industrial CI system enhanced by four state-of-the-art LLMs, comparing their outcomes with manual corrections provided by human programmers. LLM-equipped CI systems can resolve up to 63% of the compilation errors in our baseline dataset. Among the fixes associated with successful CI builds, 83% are deemed reasonable. Moreover, LLMs significantly reduce debugging time, with the majority of successful cases completed within 8 minutes, compared to hours typically required for manual debugging.

There is an evident need to complement embedded critical control logic with AI inference, but today's AI-capable hardware, software, and processes are primarily targeted towards the needs of cloud-centric actors. Telecom and defense airspace industries, which make heavy use of specialized hardware, face the challenge of manually hand-tuning AI workloads and hardware, presenting an unprecedented cost and complexity due to the diversity and sheer number of deployed instances. Furthermore, embedded AI functionality must not adversely affect real-time and safety requirements of the critical business logic. To address this, end-to-end AI pipelines for critical platforms are needed to automate the adaption of networks to fit into resource-constrained devices under critical and real-time constraints, while remaining interoperable with de-facto standard AI tools and frameworks used in the cloud. We present two industrial applications where such solutions are needed to bring AI to critical and resource-constrained hardware, and a generalized end-to-end AI pipeline that addresses these needs. Crucial steps to realize it are taken in the industry-academia collaborative FASTER-AI project.

Industrial embedded systems often require special-ized hardware. However, software engineers have access to such domain-specific hardware only at the continuous integration (CI) stage and have to use simulated hardware otherwise. This results in a higher proportion of compilation errors at the CI stage than in other types of systems, warranting a deeper study. To this end, we create a CI diagnostics solution called 'Shadow Job' that analyzes our industrial CI system. We collected over 40000 builds from 4 projects from the product source code and categorized the compilation errors into 14 error types, showing that the five most common ones comprise 89 % of all compilation errors. Additionally, we analyze the resolution time, size, and distance for each error type, to see if different types of compilation errors are easier to localize or repair than others. Our results show that the resolution time, size, and distance are independent of each other. Our research also provides insights into the human effort required to fix the most common industrial compilation errors. We also identify the most promising directions for future research on fault localization.

Faults in the automated continuous integration (CI) process can seriously impact the development of industrial code. To reduce manual intervention in automated CI processes, we want to understand better the CI systems' failure distribution to improve efficiency, reliability, and maintainability. This paper investigates failures in CI in four large industrial projects. We gather 11 731 builds over six months, identifying 1 414 failing builds. We also identify the distribution of different types of build failures in each of the four CI projects. Our results show that compilation is the most significant individual cause of failure with 47 %, followed by testing at 36 %. The checkout step with associated checks also incurs a non-negligible portion of failures with 12 %. Furthermore, we identify 14 distinct types of failures in the testing step. We conclude that configuration problems are a significant issue, as pipeline scripting and dependency errors make up a large number of failures.

Artificial intelligence and its subfield machine learning offer well-established techniques for solving historically difficult multi-parameterization problems. Used correctly, these techniques have tremendous potential to overcome complex cross-domain automation challenges in radio networks.

Our ongoing research reveals that an integrated framework of software enablers will be essential to success.

The number of connected mobile devices is increasing rapidly with more than 10 billion expected by 2022. Their total aggregate energy consumption poses a significant concern to society. The current 3gpp (3rd Generation Partnership Project) LTE/LTE-Advanced standard incorporates an energy saving technique called discontinuous reception (DRX). It is expected that 5G will use an evolved variant of this scheme. In general, the single selection of DRX parameters per device is non trivial. This paper describes how to improve energy efficiency of mobile devices by selecting DRX based on the traffic profile per device. Our particular approach uses a two phase data-driven strategy which tunes the selection of DRX parameters based on a smart fast energy model. The first phase involves the off-line selection of viable DRX combinations for a particular traffic mix. The second phase involves an on-line selection of DRX from this viable list. The method attempts to guarantee that latency is not worse than a chosen threshold. Alternatively, longer battery life for a device can be traded against increased latency. We built a lab prototype of the system to verify that the technique works and scales on a real LTE system. We also designed a sophisticated traffic generator based on actual user data traces. Complementary method verification has been made by exhaustive off-line simulations on recorded LTE network data. Our approach shows significant device energy savings, which has the aggregated potential over billions of devices to make a real contribution to green, energy efficient networks.