Coupled Q-Learning-Based Routing Reconstruction Method for Collaborative Operation of Transmission Network and Data Network

Large language models (LLMs) are increasingly utilized in healthcare, transforming medical practice through advanced language processing capabilities. However, the evaluation of LLMs predominantly relies on human qualitative assessment, which is time-consuming, resource-intensive, and may be subject to variability and bias. There is a pressing need for quantitative metrics to enable scalable, objective, and efficient evaluation. We propose a unified evaluation framework that bridges qualitative and quantitative methods to assess LLM performance in healthcare settings. This framework maps evaluation aspects-such as linguistic quality, efficiency, content integrity, trustworthiness, and usefulness-to both qualitative assessments and quantitative metrics. We apply our approach to empirically evaluate the Epic In-Basket feature, which uses LLM to generate patient message replies. The empirical evaluation demonstrates that while Artificial Intelligence (AI)-generated replies exhibit high fluency, clarity, and minimal toxicity, they face challenges with coherence and completeness. Clinicians' manual decision to use AI-generated drafts correlates strongly with quantitative metrics, suggesting that quantitative metrics have the potential to reduce human effort in the evaluation process and make it more scalable. Our study highlights the potential of a unified evaluation framework that integrates qualitative and quantitative methods, enabling scalable and systematic assessments of LLMs in healthcare. Automated metrics streamline evaluation and monitoring processes, but their effective use depends on alignment with human judgment, particularly for aspects requiring contextual interpretation. As LLM applications expand, refining evaluation strategies and fostering interdisciplinary collaboration will be critical to maintaining high standards of accuracy, ethics, and regulatory compliance. Our unified evaluation framework bridges the gap between qualitative human assessments and automated quantitative metrics, enhancing the reliability and scalability of LLM evaluations in healthcare. While automated quantitative evaluations are not ready to fully replace qualitative human evaluations, they can be used to enhance the process and, with relevant benchmarks derived from the unified framework proposed here, they can be applied to LLM monitoring and evaluation of updated versions of the original technology evaluated using qualitative human standards.

In this letter, we consider a cache-enabled cloud radio access network with single-antenna base stations and single-antenna mobile users. Each base station can access the central processor of the network via a separate backhaul link with limited capacity. We utilize the interference alignment scheme as the transmission strategy between base stations and users. By assuming a block transmission scheme, we define a related data transmission delay. We derive the transmission delay and network power consumption. At last, we solve the problem of joint optimization of data transmission delay and network power consumption using DC programming algorithm. In our numerical results, we investigate the trade-off between delay and power consumption, and compare the results with those of a prior work that does not take the transmission delay into account in its optimization problem.

Similar to any telecommunication network, energy efficiency is a desirable feature for fiber wireless (FiWi) access networks. These networks have optical back end and wireless front end. Both ends may contribute for energy efficiency. This work focusses on front end of FiWi access network, which is IEEE 802.11a wireless local area network (WLAN). For energy saving WLAN uses power saving mode (PSM), in which sleeping opportunity of a station is increased. During sleep time station remains switched off and results in reduction in energy required. However it is also observed that during active period of transmission considerable energy is consumed, which is the function of rate of data transmission. More data rate results in more active energy consumption but less transmission delay and vice versa. In order to reduce active and hence total energy consumption, we tried to transmit the data at lower data rate, while maintaining transmission delay in tolerable limit. This paper presents an Energy Efficient Rate Adaptation Algorithm (EERAA) for the front end of fiber wireless access networks. Simulation results compare the energy efficiency and transmission delay of EERAA and various existing fixed data rate schemes. Proposed scheme offers good trade-off between energy efficiency and transmission delay.

The electricity system can be divided into power generation, transmission and distribution subsystems from the structure point of view. Electricity business is positioned as a public business and regulated by pricing and quantities due to the high publicly utilization. The power transmission system is responsible for power transmission from power generation plants to the areas of power utilization. Since there is the characteristic that electricity needs to produce and sell with immediate and instant balance, it is required to construct the complete power transmission network in charge of the power dispatching in order to provide stable electricity. The price of purchases and sales is closely related with the necessity of power supply and demand. The purpose of this paper is to introduce the optimization model of power supply and demand in the independent power transmission network for the maximization of consumer and producer's surplus in the liberalization of electricity business.We apply this model to discussing the relationships of electricity quantity and price of purchases and sales. In addition, the sensitive analysis is introduced as well. We conclude that the maximal profit of power transmission network will be decreased when quantity of power utilization, cost of power generation and maintenance cost of transmission network are increasing. Instead, the maximal profit of power transmission network will be increased when power transmission rate is increasing.

In this article, we investigate the long-term energy consumption and transmission delay (EC-TD) tradeoff in a wireless-powered body area network that consists of a multiantenna hybrid access point and a number of single-antenna sensor nodes (SNs). The beamforming technique and the simultaneous wireless information and power transfer (SWIPT) technique are adopted. Each SN is equipped with a battery and data buffer for storing harvested energy and sensory data. The long-term energy consumption minimization problem is addressed subject to the constraint of transmission delay. Meanwhile, the residual energy constraints of SNs are considered, which enable the setting up of the available energy of the SNs according to requirements. By employing the Lyapunov optimization theory, the original stochastic optimization problem is transformed into an equivalent instantaneous nonconvex problem in which the long-term EC-TD tradeoff can be adjusted using a system control parameter <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$V$ </tex-math></inline-formula> . A joint power and time allocation scheme is then proposed to solve this instantaneous problem. Moreover, based on the derived upper bounds of the long-term energy consumption and data buffer length, we reveal that the proposed resource allocation scheme achieves an EC-TD tradeoff as <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$[\mathcal {O}(1/V),\mathcal {O}(V)]$ </tex-math></inline-formula> . Since the value of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$V$ </tex-math></inline-formula> can be adjusted to achieve different energy consumption and transmission delay, the flexibility and applicability of the proposed scheme are enhanced. The simulation results validate the theoretical analysis and verify the effectiveness of the proposed scheme.

The outdoor electrical insulators are widely used in power transmission and distribution networks. They provide electrical isolation and mechanical support to conductors. Overhead insulators need to be inspected and monitored regularly to prevent faults and provide permanent electricity for consumers. The condition monitoring system for insulators is quite a challenging task due to the harsh operating conditions and the large number of insulators and their wide distribution in power transmission network. Traditional inspection methods for insulator evaluation are time-consuming, labor-intensive and costly. However, the inspection system based on deep learning model jointly with Unnamed Aerial Vehicle (UAV) can provide a remote, real-time condition evaluation in efficient and cost-effective manner. In this chapter, the frameworks of the deep neural network for insulator inspection are presented. The deep architecture including critical tasks such as insulator localization and insulator state evaluation is provided. The performance of existing deep learning models based on different architecture is also given.

The risk assessment of chemicals relies on multiple tools to quantify the ecological responses of ecosystems to existing chemical pollution. These tools are broadly categorized into three major groups: toxic pressure assessments, bioassays, and ecological monitoring. Here, we examine the strengths and limitations of these approaches, their current level of implementation for freshwater ecosystems across Europe, and their ability to evaluate the impacts of chemicals under field conditions. Additionally, we analyze the correspondence between results obtained from these tools when applied to a monitoring dataset from German streams. Our evaluation showed that no single tool can perfectly characterize the environmental impacts of chemical mixtures. However, each provides distinct lines of evidence, enabling the identification of chemicals driving ecological risks and the biological endpoints most likely to be affected, with ecological monitoring tools having the potential to show long-term ecosystem impairment. Finally, we propose recommendations to better understand the discrepancies between the outcomes of different methods and explore their potential integration into a unified water quality evaluation framework.

Discontinuous reception (DRX) is a way for user equipment (UE) to save energy. DRX forces a UE to turn off its transceivers for a DRX cycle when it does not have a packet to receive from a base station, called an eNB. However, if a packet arrives at an eNB when the UE is performing a DRX cycle, the transmission of the packet is delayed until the UE finishes the DRX cycle. Therefore, as the length of the DRX cycle increases, not only the amount of UE energy saved by the DRX but also the transmission delay of a packet increase. Different applications have different traffic arrival patterns and require different optimal balances between energy efficiency and transmission delay. Thus, understanding the tradeoff between these two performance metrics is important for achieving the optimal use of DRX in a wide range of use cases. In this paper, we mathematically analyze DRX to understand this tradeoff. We note that previous studies were limited in that their analysis models only partially reflect the DRX operation, and they make assumptions to simplify the analysis, which creates a gap between the analysis results and the actual performance of the DRX. To fill this gap, in this paper, we present an analysis model that fully reflects the DRX operation. To quantify the energy efficiency of the DRX, we also propose a new metric called a real power-saving (RPS) factor by considering all the states and state transitions in the DRX specification. In addition, we improve the accuracy of the analysis result for the average packet transmission delay by removing unrealistic assumptions. Through extensive simulation studies, we validate our analysis results. We also show that compared with the other analysis results, our analysis model improves the accuracy of the performance metrics.

The frequency instability observed in the power transmission network was mainly as a result of the per unit volts not falling within 0.95 through 1.05 P.U, volts. This has caused constant power failure in our transmission net work. This sad situation of power failure noticed in the power transmission network is contained by introducing an improvement in frequency stability of the Nigerian 330kV transmission network using fuzzy controller. It was achieved by first characterizing the 330kv transmission network by running load flow on the network, designing conventional SIMULINK model for improving frequency stability of the Nigerian 330kv transmission network, designing a rule base that makes these faulty buses to attain stability, integrating the designed rule to the conventional SIMULINK model for improving frequency stability of the Nigerian 330kv transmission network. The results obtained are conventional bus 1 per unit volts at 4s through 10s is 0.94. On the other hand, when fuzzy controller is incorporated in the system it is 1.043P.U volts. This shows that there is frequency stability when fuzzy controller is incorporated in the system since the per unit volts fall within the range of 0.95 through 1.05 P.U. volt and conventional per unit volts is 0.944 which makes the frequency unstable since the volts does not attain stability. Meanwhile, when fuzzy controller is incorporated in the system the per unit volts is 1.047. With these results, it shows that there is frequency stability when fuzzy controller is imbibed in the system. Since the per unit volt fall within the stability range of 0.95 through 1.05P.U. Volts.

With the very stringent demand for real-time transmission of wireless communication services, the requirement of sub-millisecond ultra-low end-to-end delay has been initially proposed in the sixth generation (6G) communication networks. Finite blocklength transmission is one of the potential technologies to meet such a low end-to-end delay demand for the next generation networks. However, as the finite blocklength decreases, the transmission delay decreases while the queuing delay increases, which results in the tradeoff between the transmission delay and the queuing delay. To achieve the optimal balance, in this paper we propose an adaptive blocklength transmission framework to minimize the important part of the end-to-end delay of wireless networks, where we focus on the transmission delay and queuing delay. A dynamic buffering model for variable transmission time interval (V-TTI) is introduced for the time-varying arrival of packets adaptation. Then, we propose the Flexible proximal Alternating direction method of multipliers based Blocklength Optimization (FaBo) scheme to minimize the important part of the end-to-end delay for the single user case. We also propose the Multiple deep Q-learning network based Resource Allocation (MuRa) scheme, which can efficiently balance the transmission delay and queuing delay, to minimize the important part of the end-to-end delay for the multi-user case. Numerical results show that the proposed adaptive blocklength framework can reduce the important part of the end-to-end delay compared with that of long-term evolution and the fifth generation (5G) new radio. We also show that our proposed schemes can quickly converge to the minimum end-to-end delay.

Associative reconstruction of noisy data in a neural network can be accomplished by endowing a pattern to be memorized with a basin of attraction for the system's retrieval dynamics. ' If the dynamics is governed by a Lyapunov function, a simple intuitive understanding of the global computation becomes possible: The system performs a downhill motion in an energy landscape created by the stored information. For networks with static patterns, there is a Lyapunov function if the interactions between single neurons are instantaneous and mediated by symmetric couplings. Methods of equilibrium statistical mechanics may then be applied and permit a quantitative analysis of the network's performance in terms of the retrieval quality and storage capacity. The existence of a Lyapunov function is thus of great conceptual as well as technical importance. In general, external inputs to a neural network are not limited to static memories but provide information in both space and time. To code the temporal aspects of sequences of patterns to be learned, additional asymmetric couplings with transmission delays may be introduced. This approach can be generalized to networks with a broad distribution of signal delays where Hebb's neurophysiological principle for learning naturally leads to a joint representation of spatial and temporal information. However, no description in terms of a Lyapunov function has been given so far. In this Letter such a description is developed for a certain class of networks with transmission delays. We present a Lyapunov functional for the deterministic parallel dynamics, generalize the formalism of equilibrium statistical mechanics so as to deal with thermal noise in systems with delayed interactions, and, hence, make the domain of time-dependent phenomena accessible to powerful free-energy techniques. We follow Refs. 1-3 and model single neurons by Ising spins 5;, 1 ~i ~ N. They represent a firing state for 5; =+1 and a quiescent one for 5; = — 1. The neurons are connected by synapses with modifiable efficacies J;, (r). Here r denotes a fixed time delay for the information transport from j to i. We focus on a solitonlike propagation of neural signals, characteristic for the (axonal) transmission of action potentials, and consider a model where each pair of neurons is linked by several axons with delays 0~ ~~ r, „. External stimuli are fed into the system via two-state receptors cr; = + 1. The local fields (postsynaptic potentials) are then given by N max

Low Earth Orbit Satellite Networks (LEO-SNs) have emerged as a promising paradigm for future space information networks. However, the time-varying topology, link intermittency, limited onboard resource and relatively long transmission distance imposed unprecedented challenges on guaranteeing the delay Quality of Service (QoS). In contrast with existing routing-based or resource optimization-based solutions, onboard processing provides an alternative way to reduce the transmission delay by dwindling the transmitted data size. The employment of onboard processing makes it critical to select a routing path with sufficient energy and properly allocate resources for transmission and processing. This paper studies the untouched onboard processing aided transmission delay minimization problem of LEO-SNs. A Distributed Network State Learning (DNSL) mechanism is proposed for synchronizing the network states, which induces Potential Field (PF) to model both the attraction of resources and the repulsion of transmission load. By jointly considering the channel conditions, onboard resources and transmission load, a Deep Q-network (DQN) based Intelligent In-orbit Routing (DIIR) algorithm is proposed for selecting a routing path with good channel conditions, sufficient energy and low transmission load to facilitate onboard processing. Moreover, a Deep Deterministic Policy Gradient (DDPG) based Intelligent Resource Allocation (DIRA) algorithm is provided to achieve intelligent and continuous resource allocation for exploiting onboard processing to minimize the transmission delay, while the resource and load states of satellites on the routing path are taken into consideration by including PF as an input. Extensive simulation results demonstrate that employing onboard processing with the proposed DIIR and DIRA algorithms significantly reduces the average transmission delay and packet loss rate.

Due to the Recent development in wireless technology, wireless sensor networks attract researchers’ attention because of their applicability in many fields for effective collection of sensing data with low cost. Wireless sensor networks have many applications; some of the applications are military application, environmental application and flood detection. For example, in an environmental application for forest fire detection, the sensor nodes sense the fire information, then transmit or relay the information to base station in a multi-hop way. In wireless sensor networks, energy saving is critical issue as sensor nodes are battery-powered. Here we propose, partial data aggregation as one of the energy saving technique. In this paper, we analyze the tradeoffs among communication delay, energy consumption, and data accuracy of the partial data aggregation technique and discuss the results. First, we analyze the partial data aggregation with Markovian chain; analytical result shows that, non-aggregation method suffers large energy consumption while full aggregation suffers long transmission delay. From the analysis results, we find that the proposed partial aggregation method WRP (Waterfalls Random partial aggregation) can trade off energy consumption and transmission delay. Thus, we discuss the tradeoffs among data accuracy, transmission delay and energy consumption with different criteria and parameters. The results show that we could control the significance of transmission delay, energy consumption and data accuracy by tradeoffs index (TOI). We also analyze the several applications of wireless sensor networks with different significance based on the TOI. From the observed results, we found that we could set the significance of transmission delay, energy consumption and data accuracy for different applications based on different criteria TOI. Thus, by evaluating and comparing the criteria with different data generation rate as well as aggregation factor, we get the least TOI value, which denotes the desired tradeoffs among them.

A unified benchmark for security and reliability assessment of the integrated chemical plant, natural gas and power transmission networks

Power investment and transmission network expansion in China and its neighbouring countries towards carbon neutrality