Reduced environmental effect, lower operating costs, and a stable and sustainable energy supply for current and future generations are the main reasons why power optimization is important. Power optimization makes ensuring that energy is used more effectively, cutting down on waste and optimizing the utilization of resources.In today's world, power optimization and artificial intelligence (AI) integration are essential to changing the way energy is produced, used, and distributed. Real-time monitoring and analysis of power usage trends is made possible by AI-driven algorithms and predictive analytics, which enable dynamic modifications to effectively satisfy demand. Efficiency and sustainability are increased when power consumption is optimized in different sectors thanks to the use of intelligent systems. This survey paper comprises an extensive review of the several AI techniques used for power optimization as well as a methodical analysis of the literature for the study of various intelligent system application domains across different disciplines of power consumption.This literature review identifies the performance and outcomes of 17 different research methods by assessing them, and it aims to distill valuable insights into their strengths and limitations. Furthermore, this article outlines future directions in the integration of AI for power consumption optimization.

Network slicing enables industrial Internet of Things (IIoT) networks with multiservice and differentiated resource requirements to meet increasing demands through efficient use and management of network resources. Typically, the network slice orchestrator relies on demand forecasts for each slice to make informed decisions and maximize resource utilization. The new generation of Industry 4.0 has introduced digital twins to map physical systems to digital models for accurate decision-making. In our approach, we first use graph-attention networks to build a digital twin environment for network slices, enabling real-time traffic analysis, monitoring, and demand forecasting. Based on these predictions, we formulate the resource allocation problem as a federated multi-agent reinforcement learning problem and employ a deep deterministic policy gradient to determine the resource allocation policy while preserving the privacy of the slices. Our results demonstrate that the proposed approaches can improve the accuracy of demand prediction for network slices and reduce the communication overhead of dynamic network slicing.

Reducing operation and maintenance costs is a key objective for advanced reactors in general and microreactors in particular. To achieve this reduction, developing robust autonomous control algorithms is essential to ensure safe and autonomous reactor operation. Recently, artificial intelligence and machine learning algorithms, specifically reinforcement learning (RL) algorithms, have seen rapid increased application to control problems, such as plasma control in fusion tokamaks and building energy management. In this work, we introduce the use of RL for intelligent control in nuclear microreactors. The RL agent is trained using proximal policy optimization (PPO) and advantage actor-critic (A2C), cutting-edge deep RL techniques, based on a high-fidelity simulation of a microreactor design inspired by the Westinghouse eVinci\textsuperscript{TM} design. We utilized a Serpent model to generate data on drum positions, core criticality, and core power distribution for training a feedforward neural network surrogate model. This surrogate model was then used to guide a PPO and A2C control policies in determining the optimal drum position across various reactor burnup states, ensuring critical core conditions and symmetrical power distribution across all six core portions. The results demonstrate the excellent performance of PPO in identifying optimal drum positions, achieving a hextant power tilt ratio of approximately 1.002 (within the limit of $<$ 1.02) and maintaining criticality within a 10 pcm range. A2C did not provide as competitive of a performance as PPO in terms of performance metrics for all burnup steps considered in the cycle. Additionally, the results highlight the capability of well-trained RL control policies to quickly identify control actions, suggesting a promising approach for enabling real-time autonomous control through digital twins.

General-purpose agents require fine-grained controls and rich sensory inputs to perform a wide range of tasks. However, this complexity often leads to intractable decision-making. Traditionally, agents are provided with task-specific action and observation spaces to mitigate this challenge, but this reduces autonomy. Instead, agents must be capable of building state-action spaces at the correct abstraction level from their sensorimotor experiences. We leverage the structure of a given set of temporally-extended actions to learn abstract Markov decision processes (MDPs) that operate at a higher level of temporal and state granularity. We characterize state abstractions necessary to ensure that planning with these skills, by simulating trajectories in the abstract MDP, results in policies with bounded value loss in the original MDP. We evaluate our approach in goal-based navigation environments that require continuous abstract states to plan successfully and show that abstract model learning improves the sample efficiency of planning and learning.

Deep Reinforcement Learning (DRL) is regarded as a promising tool for optical network optimization. However, the flexibility and efficiency of current DRL-based solutions for optical network optimization require further improvement. Currently, generative models have showcased their significant performance advantages across various domains. In this paper, we introduce OpticGAI, the AI-generated policy design paradigm for optical networks. In detail, it is implemented as a novel DRL framework that utilizes generative models to learn the optimal policy network. Furthermore, we assess the performance of OpticGAI on two NP-hard optical network problems, Routing and Wavelength Assignment (RWA) and dynamic Routing, Modulation, and Spectrum Allocation (RMSA), to show the feasibility of the AI-generated policy paradigm. Simulation results have shown that OpticGAI achieves the highest reward and the lowest blocking rate of both RWA and RMSA problems. OpticGAI poses a promising direction for future research on generative AI-enhanced flexible optical network optimization.

We study the problem of Distributionally Robust Constrained RL (DRC-RL), where the goal is to maximize the expected reward subject to environmental distribution shifts and constraints. This setting captures situations where training and testing environments differ, and policies must satisfy constraints motivated by safety or limited budgets. Despite significant progress toward algorithm design for the separate problems of distributionally robust RL and constrained RL, there do not yet exist algorithms with end-to-end convergence guarantees for DRC-RL. We develop an algorithmic framework based on strong duality that enables the first efficient and provable solution in a class of environmental uncertainties. Further, our framework exposes an inherent structure of DRC-RL that arises from the combination of distributional robustness and constraints, which prevents a popular class of iterative methods from tractably solving DRC-RL, despite such frameworks being applicable for each of distributionally robust RL and constrained RL individually. Finally, we conduct experiments on a car racing benchmark to evaluate the effectiveness of the proposed algorithm.

In reinforcement learning, specifying reward functions that capture the intended task can be very challenging. Reward learning aims to address this issue by learning the reward function. However, a learned reward model may have a low error on the training distribution, and yet subsequently produce a policy with large regret. We say that such a reward model has an error-regret mismatch. The main source of an error-regret mismatch is the distributional shift that commonly occurs during policy optimization. In this paper, we mathematically show that a sufficiently low expected test error of the reward model guarantees low worst-case regret, but that for any fixed expected test error, there exist realistic data distributions that allow for error-regret mismatch to occur. We then show that similar problems persist even when using policy regularization techniques, commonly employed in methods such as RLHF. Our theoretical results highlight the importance of developing new ways to measure the quality of learned reward models.

Federated learning (FL) is a viable technique to train a shared machine learning model without sharing data. Hierarchical FL (HFL) system has yet to be studied regrading its multiple levels of energy, computation, communication, and client scheduling, especially when it comes to clients relying on energy harvesting to power their operations. This paper presents a new two-phase deep deterministic policy gradient (DDPG) framework, referred to as ``TP-DDPG'', to balance online the learning delay and model accuracy of an FL process in an energy harvesting-powered HFL system. The key idea is that we divide optimization decisions into two groups, and employ DDPG to learn one group in the first phase, while interpreting the other group as part of the environment to provide rewards for training the DDPG in the second phase. Specifically, the DDPG learns the selection of participating clients, and their CPU configurations and the transmission powers. A new straggler-aware client association and bandwidth allocation (SCABA) algorithm efficiently optimizes the other decisions and evaluates the reward for the DDPG. Experiments demonstrate that with substantially reduced number of learnable parameters, the TP-DDPG can quickly converge to effective polices that can shorten the training time of HFL by 39.4% compared to its benchmarks, when the required test accuracy of HFL is 0.9.

Autonomous race driving poses a complex control challenge as vehicles must be operated at the edge of their handling limits to reduce lap times while respecting physical and safety constraints. This paper presents a novel reinforcement learning (RL)-based approach, incorporating the action mapping (AM) mechanism to manage state-dependent input constraints arising from limited tire-road friction. A numerical approximation method is proposed to implement AM, addressing the complex dynamics associated with the friction constraints. The AM mechanism also allows the learned driving policy to be generalized to different friction conditions. Experimental results in our developed race simulator demonstrate that the proposed AM-RL approach achieves superior lap times and better success rates compared to the conventional RL-based approaches. The generalization capability of driving policy with AM is also validated in the experiments.

Databases are fundamental to contemporary information systems, yet traditional rule-based configuration methods struggle to manage the complexity of real-world applications with hundreds of tunable parameters. Deep reinforcement learning (DRL), which combines perception and decision-making, presents a potential solution for intelligent database configuration tuning. However, due to black-box property of RL-based method, the generated database tuning strategies still face the urgent problem of lack explainability. Besides, the redundant parameters in large scale database always make the strategy learning become unstable. This paper proposes KnobTree, an interpertable framework designed for the optimization of database parameter configuration. In this framework, an interpertable database tuning algorithm based on RL-based differentatial tree is proposed, which building a transparent tree-based model to generate explainable database tuning strategies. To address the problem of large-scale parameters, We also introduce a explainable method for parameter importance assessment, by utilizing Shapley Values to identify parameters that have significant impacts on database performance. Experiments conducted on MySQL and Gbase8s databases have verified exceptional transparency and interpretability of the KnobTree model. The good property makes generated strategies can offer practical guidance to algorithm designers and database administrators. Moreover, our approach also slightly outperforms the existing RL-based tuning algorithms in aspects such as throughput, latency, and processing time.