While polyhedral compilers have shown success in implementing advanced code transformations, they still face challenges in selecting the ones that lead to the most profitable speedups. This has motivated the use of machine learning based cost models to guide the search for polyhedral optimizations. State-of-the-art polyhedral compilers have demonstrated a viable proof-of-concept of such an approach. While promising, this approach still faces significant limitations. Existing polyhedral compilers using deep learning cost models typically support only a small subset of affine transformations, limiting their ability to explore complex code transformations. Furthermore, their applicability does not scale beyond simple programs, thus excluding many program classes from their scope, such as those with non-rectangular iteration domains or multiple loop nests. These limitations significantly impact the generality of such compilers and autoschedulers, raising questions about the overall approach. In this paper, we introduce LOOPER, the first polyhedral autoscheduler that uses a deep learning based cost model and covers a large space of affine transformations and programs. LOOPER allows the optimization of an extensive set of programs while being effective at applying complex sequences of polyhedral transformations. We implement and evaluate LOOPER and show that it achieves competitive speedups over the state-of-the-art. On the PolyBench benchmarks, LOOPER achieves a geometric mean speedup of $\mathbf{1 . 8 4} \mathbf{x}$ over the Tiramisu autoscheduler and $\mathbf{1 . 4 2} \mathbf{x}$ over Pluto, two state-of-the-art polyhedral autoschedulers.

The increasing reliance on advanced power systems in critical infrastructure highlights the need to enhance cybersecurity resilience. This study tackles this crucial issue through Exploratory Data Analysis (EDA) and Representation Learning (RL). Several real-world, complex power system datasets characterized by their large size, dynamic nature, and high imbalance are examined. EDA serves as a fundamental step to provide insights into power system event scenarios, supported by a comprehensive preprocessing strategy that includes managing missing values, reducing dimensionality, denoising, removing outliers, and addressing class imbalance. Missing values are thoughtfully handled by evaluating mean values. Dimensionality reduction involves removing insignificant features that might provide misleading information, along with integrating Principal Component Analysis (PCA). Class-specific denoising and outlier removal follow, with denoising utilizing various algorithms and a diverse range of wavelet functions to improve data quality. Robust outlier removal is achieved through iterative analyses and distance-based techniques. To address class imbalance, the Synthetic Minority Over-Sampling Technique (SMOTE) is employed, ensuring a balanced and representative dataset. For RL, deep learning models such as Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Gated Recurrent Units (GRU), and their Multiverse Recurrent Expansions with Multiple Repeats (MV-REMR) are used in a comparative study. The results demonstrate promising and satisfactory outcomes for all models, with MV-REMR delivering the best performance. This study integrates diverse techniques into a unified EDA and RL approach, offering valuable insights into power system cybersecurity forensics, addressing current challenges, and promoting resilient and adaptive cybersecurity measures in power systems.

Smart grids have emerged as a complex structure integrating communication networks, distributed energy resources, and intelligent devices. However, this integration has resulted in the manifestation of various vulnerabilities, raising signifi-cant security concerns and challenges. Present-day smart grids are vulnerable to various cyberattacks, and researchers have dedicated efforts to detect, mitigate, and prevent these attacks using diverse techniques. This paper focuses specifically on replay attacks within smart grids, recognizing the critical need to address this particular threat. Through a comprehensive review of existing literature regarding the detection, mitigation, and prevention of replay attacks across smart grids, microgrids, and cyber-physical systems (CPSs), we aim to provide insights into effective defense strategies applicable to various interconnected energy infrastructures.

In this paper, we analyze the results of two hyper-heuristics HHGA and HHabs that generate per-instances genetic algorithms for the permutation flow shop problem. They are competitive with literature approaches for most of instances of the benchmark of Taillard. Nevertheless, they are not effective enough for some difficult instances. For this purpose, we propose a workflow to analyse GAs configurations and their results in order to detect which components influence the most on generated GAs quality in order to enhance the quality of these hyper-heuristics.

Hyper-heuristics can be applied to solve complex optimization problems. However, they need a substantial number of fitness function evaluations to discover a good approximation to the global optimum, especially for large-scale problems. Recently, surrogate-assisted algorithms have drawn increasing attention, and have shown their potential to deal with expensive complex optimization problems. This paper aims to use surrogates to approximate HHGA's (Ahmed Bacha et al., 2019) fitness functions, an efficient hyper-heuristic for solving the permutation flowshop problem, one of the most important scheduling types in modern industries. The objective is to approximate, in an online approach, the fitness function, reducing considerably the execution time of HHGA while maintaining its quality. The proposed online surrogate model is mainly designed to capture the details of the fitness function to enhance the accuracy estimation. The experimental results on Taillard's widely used benchmark problems show that the proposed fitness approximation-assisted HHGA is able to achieve competitive performance on a limited computational budget.

In this paper, we propose a hybrid Artificial Bee Colony algorithm with Simulated Annealing (ABC-SA) to address the community detection problem. SA enhances the exploitation by searching the most promising regions located by ABC algorithm. Besides, in order to accommodate the characteristics of social networks, we use locus-based adjacency encoding scheme, in which communities are identified as a graph connected components and Pearson's correlation as structural information to guide the solutions' construction. Results obtained on synthetic and real-word networks show that the proposed algorithm can discover communities more successfully in comparison with traditional ABC algorithm and other state-of-the-art algorithms.

Term Rewriting Systems (TRSs) are used in compilers to simplify and prove expressions. State-of-the-art TRSs in compilers use a greedy algorithm that applies a set of rewriting rules in a predefined order (where some of the rules are not axiomatic). This leads to a loss of the ability to simplify certain expressions. E-graphs and equality saturation sidestep this issue by representing the different equivalent expressions in a compact manner from which the optimal expression can be extracted. While an e-graph-based TRS can be more powerful than a TRS that uses a greedy algorithm, it is slower because expressions may have a large or sometimes infinite number of equivalent expressions. Accelerating e-graph construction is crucial for making the use of e-graphs practical in compilers. In this paper, we present Caviar, an e-graph-based TRS for proving expressions within compilers. The main advantage of Caviar is its speed. It can prove expressions much faster than base e-graph TRSs. It relies on three techniques: 1) a technique that stops e-graphs from growing when the goal is reached, called Iteration Level Check; 2) a mechanism that balances exploration and exploitation in the equality saturation algorithm, called Pulsing Caviar; 3) a technique to stop e-graph construction before reaching saturation when a non-provable pattern is detected, called Non-Provable Patterns Detection (NPPD). We evaluate caviar on Halide, an optimizing compiler that relies on a greedy-algorithm-based TRS to simplify and prove its expressions. The proposed techniques allow Caviar to accelerate e-graph expansion for the task of proving expressions. They also allow Caviar to prove expressions that Halide’s TRS cannot prove while being only 0.68x slower. Caviar is publicly available at: https://github.com/caviar-trs/caviar.

Availability constraints, machine condition as well as human behavior phenomena were recently introduced in the study of scheduling problems in order to get closer to the industrial reality. In this context, the permutation flowshop scheduling problem (PFSP) under flexible maintenance planning is investigated by incorporating machine deteriorating and human learning effects. The objective is to minimise the expected makespan by optimising simultaneously job sequence and maintenance decisions. To study the different problem configurations with respect to machine and human related effects, two studies are carried out. In the former study, the learning effect (human effect) is applied on maintenance activities, where durations are assumed to be time varying. While in the later, besides applying the learning effect on maintenance operations, time-dependent deteriorating jobs are also considered. Given the NP-completeness of the PFSP, an artificial bees colony algorithm (ABC) based metaheuristic is proposed, complemented with a maintenance insertion heuristic and adaptive local search procedures, to provide good solutions with reasonable CPU time. To prove the effectiveness of our proposed algorithm, intense computational experiments are carried out on Taillard's well-known benchmarks, expanded with flexible maintenance data.

This paper deals with induction machines bearing failures detection and diagnosis using vibration and temperature signals. The failure detection is managed by a clustering graphical representation creating transition classes. Motivated by the computational complexity of the problem, a Variable Neighborhood Search (VNS) metaheuristic is developed including well-designed local search algorithms for data clustering to the system diagnosis. Computational experiments carried out on the PRONOSTIA experimental platform data show that the proposed algorithm seems to be efficient and effective.

In this paper, we propose HHGA, a new hyper-heuristic for the Permutation Flowshop Problem with makespan minimization. It consists of a high-level genetic algorithm which goal is to tailor a dedicated and effective genetic algorithm for each instance. The goal of the proposed hyper-heuristic is to find among a set of genetic operators, a configuration that is suitable for solving a PFSP problem instance and compare the tailored GAs to investigate the existence of any patterns. Our experiments on well-known Taillard’s benchmark showed the performance of tailored GAs. HHGA was able to build genetic algorithms that reached optimal solutions in 50 instances out of 120 and was at least as good as state-of-the-art approaches. Through results, we show also the performance of some operators compared to others.

This paper presents a multi-objective immune memetic algorithm to the challenge of solving the Frequency Assignment Problem (FAP) in cellular networks seeking the minimization of the network’s total interference, the maximum interference and the number of used frequencies. The originality of the proposed approach lies in integrating a FAP-specific local search into its evolutionary process instead of crossover and mutation, as well as a guided diversification strategy for better performances. Moreover, the algorithm is supplemented with a clonal selection, inherited from Artificial Immune Systems (AIS), which aims to improve the algorithm exploration and exploitation abilities. Computational experiments performed over COST259 instances show the efficiency of the newly proposed evolutionary multi-objective algorithm and corroborated by the comparisons we did with the most frequently referred algorithm in the related literature. Furthermore, the effect of the main parameters and the interaction between them is analyzed using statistical tools.

This work concerns the consideration of human resource constraints in the single machine scheduling problem of both production and flexible periodic maintenance activities. We assume that a maintenance activity requires the intervention of a human resource to be treated. These human resources are characterized by a competence level and availabilities considered as strong constraints allowing or not the maintenance activities' planning. To solve this NP-hard scheduling problem, we propose a guided local search metaheuristic that embeds a post-optimization process in order to minimize both production and maintenance delays. We implemented and experimented the proposed method on two series of benchmarks. The first one focuses on small size instances. The results show that the quality of the solutions obtained by the proposed method compared to an exact one is good, and even it reaches the optimal solution in some cases. In the second one, we applied the method on large instances to show its advantages and efficiency.

We tackle in this paper the Permutation Flow-shop Scheduling Problem (PFSP) with predictive maintenance interventions. The objective is to propose an integrated model that coordinates production schedule and predictive maintenance planning so that the total time to complete the schedule after predictive maintenance insertion is minimized. Predictive maintenance interventions are scheduled based on Prognostics and Health Management (PHM) results using a new proposed heuristic. To jointly establish an integrated scheduling of production jobs and predictive maintenance actions, we propose a tailored genetic algorithm incorporating properly designed operators. Computational experiments carried out on Taillard well known benchmarks, to which we add both PHM and maintenance data, show the efficiency of the newly proposed maintenance planning heuristic and genetic algorithm.

One of the most interesting issues in the field of social network analysis is community evolution prediction in dynamic social networks. To start with, the dynamic network is split into a series of timeframes, each one containing interactions aggregated over a time period such as a month, a day or an hour. Splitting the network into timeframes is of crucial importance to capture the right communities' temporal evolution before predicting their future. Our paper investigates the problem of choosing the appropriate scale for network splitting which would improve the prediction. The experiments we conducted on Facebook and Higgs Twitter datasets offer strong empirical evidence of the usefulness of considering the appropriate network splitting as a first step in predicting community evolution in dynamic social networks.

This paper presents a hybrid multi-objective genetic algorithm which combines the main notion of game theory Nash equilibrium with Pareto-optimality to solve the multi-objective Frequency Assignment Problem (FAP) in mobile networks. The game is coupled with genetic algorithm to accelerate convergence and produce Nash equilibrium and Pareto non-dominated solutions simultaneously. The proposed hybrid approach produces high quality solutions as proved by several performed tests and corroborated by the comparison with the most referred multi-objective optimization algorithms such as NSGA-II and SPEA2 on well-known Philadelphia and COST259 FAP instances. Furthermore, the effect of some parameters is discussed.

In this paper, we study a new scheduling problem that considers both production and flexible preventive maintenance on a single machine where the human resource constraints (the availability and the competence) are taken into account. The objective function involves both the tardiness and the earliness resulting from production and maintenance tasks. We propose a mathematical formulation of the studied problem that is expressed in the constraint programming (CP) paradigm as a set of linear constraints. This CP modeling had been implemented in ILOG OPL language and the exact method Cplex is applied on it to compute the optimal solutions of relatively small instances of the problem. Further, a heuristic algorithm is provided to deal with lager instances of the problem. Computational experiments demonstrate that the proposed heuristic performs well and is able to find good solutions to instances up to 700 jobs in a reasonable CPU time.

This research focuses on the problem of scheduling jobs on a single machine that requires flexible maintenance under human resource constraints. A fuzzy genetic algorithm that integrates production, maintenance, human resource availability and competence constraints is developed. This algorithm uses fuzzy logic to deal with uncertainties. Experiments show that the consideration of human resource constraints and uncertainties in the integrated and proactive scheduling allows proposing more realistic and applicable solutions.

This paper deals with induction machines bearing failures detection and diagnosis using vibration and temperature signals. It proposes the use of a new Classical Mechanics-inspired Optimization (CMO) metaheuristic for data clustering. To ensure failure detection, transitions from a state to another is analyzed in order to form a transitional model between system states generated by the clustering. The performances of the proposed new metaheuristic are evaluated on the PRONOSTIA experimental platform data.

This study focuses on permutation flowshop scheduling problem (PFSP) under availability constraints with makespan and maintenance cost optimization criteria. Machines unavailabilities are due to predictive maintenance interventions scheduled based on Prognostics and Health Management (PHM) results. Hence, we deal with the post prognostic decision making in order to improve system safety and avoid downtime and inopportune maintenance spending. For this reason, we propose a new interpretation of PHM outputs to define machines degradations corresponding to each job. Moreover, to take into account the several sources of uncertainty in the prognosis process, we choose to model PHM outputs using fuzzy logic. Motivated by the computational complexity of the problem, Variable Neighborhood Search (VNS) methods are developed including well designed local search procedures. Computational experiments carried out on well known benchmark sets for permutation flowshop show that the proposed algorithms seems to be efficient and effective.

This work proposes a hybrid of GA and immune algorithm for permutation flowshop scheduling problems to overcome the problem of GAs early convergence during the evolutionary processes. The proposed algorithm, called VacGA, introduces vaccination into the field of GAs based on the theory of immunity in biology. VacGA employs a GA to perform global search and an artificial immune system to perform local search. VacGA has been tested on Taillard’s benchmarks, and compared with standard GA and the best existing hybrid GAs. The obtained results shed light on the efficiency of our new hybrid method. Furthermore, the effects of some parameters are discussed.

Recently, Prognostics and Health Management (PHM) reveals to be a key feature for industrials as it should improve manufacturing system availability and allow avoiding downtime as well as inopportune maintenance spending. In this context, we investigate the problem of scheduling several jobs on a single machine subjected to predictive maintenance based on PHM. We propose a new hybrid genetic immune algorithm, called IPro-HGIA, which incorporates an emulation of GA with artificial immune system, to create an integrated prognostic based scheduling for planning both production and predictive maintenance interventions under the total interventions cost minimization criterion. Furthermore, we use the principals of vaccination and receptor editing in order to strengthen search ability. Computational results show the efficiency of our hybrid scheme.

International audience

Many works refer to the scheduling problem of both preventive maintenance and production activities. Few works concern the dynamic scheduling problem of these two activities. This aspect is mainly concerned by corrective maintenance activities (equipment failure). In this regard, we propose a distributed approach using multi-agent paradigm for scheduling independent jobs and maintenance operations in the flowshop sequencing problem. The proposed multi-agent system introduces a dialogue between two communities of agents (production and maintenance) based on a two-step sequential strategy: first scheduling the production jobs then inserting the preventive maintenance operations, taking the production schedule as a mandatory constraint, to generate a joint production and maintenance schedule. The objective is then to optimize a bi-objective function which takes into account both maintenance and production criterion. It also provides a framework in order to react to the disturbances occurring in the workshop. The main point is to show how the proposed multi-agent system provides a better compromise between the satisfactions of respective objectives of the two functions.