Optimal Multicast Scheduling for Switched Beamforming Systems Leveraging Reflections

This work studies the power optimal dynamic scheduling problem in multi-channel multi-user wireless access networks. Users have quality-of-service (QoS) requirements on the minimum rates with statistical delay guarantees. Only one user is allowed to transmit over a channel in a given time slot. This work considers two scenarios: homogeneous and heterogeneous users. For the former scenario, the optimal scheduling policy can be derived, and an online scheduling algorithm for the optimal policy is proposed using online time-averaging without requiring a-priori known fading statistics. For the latter scenario, the optimal scheduling problem is combinatorially hard; hence, even when the fading statistics are available, computing the optimal policy is intractable. Consequently, this work develops a sub-optimal online scheduling algorithm with linear complexity which does not require a-priori known fading statistics. Moreover, the scheduling algorithm satisfies the QoS constraints for the users. Illustrative results demonstrate the performance of the proposed scheduling algorithms in various settings.

The scheduling at an ATM access point is modelled as a stochastic control problem and an optimal scheduling policy is obtained for equalising the input buffer contents in the case of two inputs with unequal arrival rates. The optimal policy is work conserving, and it serves the longer queue when the queue lengths are unequal and serves the queue with the larger arrival rate when the queue lengths are equal. In the case of 0-1 arrival processes, some sample path wise results are obtained.

In this paper, we study the delay optimal scheduling policy for a multi-state wireless fading channel, by taking bursty packet arrivals and automatic repeat request-based packet transmission into account. In our system, the average delay each packet experiences includes the time it waits in the queue and the time it may take to retransmit due to packet delivery failure. To reduce the average delay, we propose a joint channel-aware and queue-aware stochastic scheduling policy to determine whether and with which probability the source should transmit based on channel and buffer states, subject to an average power constraint at the transmitter. To find the optimal scheduling probabilities, we formulate a non-linear power-constrained delay minimization problem with the aid of controlled Markov decision processes. The optimization problem is then converted into an equivalent linear programming problem by introducing new variables from the steady-state probabilities of the underlying Markov chain and transmission probabilities. By analyzing its property, we derive the structure of the optimal solution, and exploit it to obtain the optimal probabilities analytically. It is found that the optimal scheduling policy has a double threshold structure, and can significantly reduce the average delay.

This paper explores optimal and suboptimal packet schedulers for time-varying flat fading channels that trade-off between minimization of the average delay and the average transmitted power. Both uncorrelated and correlated block fading channels are investigated. Extending a previous work, we formulate the trade-off as a unconstrained Markov decision processes and find the stationary deterministic optimal policy using both relative value iteration and policy iteration algorithm. As well, we present constrained Markov decision processes formulation of the problem and linear programming algorithm to solve it and show that optimal schedulers are randomized in this case. In order to alleviate the computational complexity needed, to determine the optimal scheduling policy we propose a suboptimal log-scheduling policy that has performance close to that of the optimal scheduler. The proposed policy is also robust to different channel models. It is demonstrated that log-policy is favorable to the water-filling policy for very slow fading channels.

In this paper, we investigate the transmission completion time minimization problem in a two-user additive white Gaussian noise (AWGN) broadcast channel, where the transmitter is able to harvest energy from the nature. The harvested energy is modeled to arrive at the transmitters randomly. In this paper, under a deterministic system setting, we assume that the energy harvesting times and harvested energy amounts are known before the transmission starts. The transmitter has a fixed number of packets to be delivered to each receiver. Our goal is to minimize the time by which all of the packets for both users are delivered to their respective destinations. To this end, we optimize the transmit powers and transmission rates intended for both users. We first analyze the structural properties of the optimal transmission policy. We prove that the optimal total transmit power has the same structure as the optimal single-user transmit power. We also prove that there exists a cut-off power level for the stronger user. If the optimal total transmit power is lower than this level, all transmit power is allocated to the stronger user, and when the optimal total transmit power is larger than this level, all transmit power above this level is allocated to the weaker user. Based on these structural properties of the optimal policy, we propose an algorithm that yields the globally optimal off-line scheduling policy.

Coordinated base station (BS) transmission has attracted much interest for its potential to increase the capacity of wireless networks. Yet at the same time, the sum-rate with single-cell processing (SCP) is known to scale optimally with the number of users in a Rayleigh fading environment. One may therefore ask if the value of BS coordination is limited in the many user regime from a sum-rate perspective. With this in mind we consider multicell zero-forcing beamforming (ZFBF) on the downlink of a linear cell-array. We first identify the beamforming weights and the optimal scheduling policy under a perbase power constraint. We then compare the number of users m and n required per-cell to achieve the same mean SINR, after optimal scheduling, with SCP and ZFBF respectively. Specifically, we show that the ratio m/n grows logarithmically with n. Finally, we demonstrate that the difference in sum-rate between ZFBF and SCP is significant for all practical values of number of users.

Integrated connection-level and packet-level QoS controls over wireless mesh networks

Multi-task model training has been adopted to enable a single deep neural network model (often a large language model) to handle multiple tasks (e.g., question answering and text summarization). Multi-task training commonly receives input sequences of highly different lengths due to the diverse contexts of different tasks. Padding (to the same sequence length) or packing (short examples into long sequences of the same length) is usually adopted to prepare input samples for model training, which is nonetheless not space or computation efficient. This paper proposes a dynamic micro-batching approach to tackle sequence length variation and enable efficient multi-task model training. We advocate pipelineparallel training of the large model with variable-length micro-batches, each of which potentially comprises a different number of samples. We optimize micro-batch construction using a dynamic programming-based approach, and handle micro-batch execution time variation through dynamic pipeline and communication scheduling, enabling highly efficient pipeline training. Extensive evaluation on the FLANv2 dataset demonstrates up to 4.39x higher training throughput when training T5, and 3.25x when training GPT, as compared with packing-based baselines. DynaPipe's source code is publicly available at https://github.com/awslabs/optimizing-multitask-training-through-dynamic-pipelines.

Heterogeneous traffic types (interactive messages, file transfers, facsimile, etc.) compete for access to a shared resource (satellite channel, bus, etc.). If a packet is not immediately given access to the resource, it waits in a buffer. We assume that the buffer capacity is infinite, that the traffic types arrive according to independent Poisson processes and that the period over which a packet occupies the resource has an arbitrary type-dependent distribution. The traffic types are partitioned into two groups: interactive and noninteractive. The average delay of each of the interactive types is required to below given thresholds. The problem of finding an optimal scheduling policy that minimizes a linear combination of the average delays for the noninteractive types while meeting the design constraints is considered. Simple necessary and sufficient conditions are derived for the existence of a policy that satisfies the constraints. An algorithm is given that decomposes the traffic types into an ordered arrangement of groups, and the existence of a policy that gives strict priority accordingly is established. Under weak conditions on the costs and rates, it is shown that all optimal policies must have this structural property. Sensitivity and aggregation analyses are given. Finally, exploiting the above decomposition, an optimal policy is constructed and is shown to have many appealing properties.

The increasingly complex residential microgrids (r-microgrid) consisting of renewable generation, energy storage systems, and residential buildings require a more intelligent scheduling method. Firstly, aiming at the radiant floor heating/cooling system widely utilized in residential buildings, the mathematical relationship between the operative temperature and heating/cooling demand is established based on the equivalent thermodynamic parameters (ETP) model, by which the thermal storage capacity is analyzed. Secondly, the radiant floor heating/cooling system is treated as virtual energy storage system (VESS), and an optimization model based on mixed-integer nonlinear programming (MINLP) for r-microgrid scheduling is established which takes thermal comfort level and economy as the optimization objectives. Finally, the optimal scheduling results of two typical r-microgrids are analyzed. Case studies demonstrate that the proposed scheduling method can effectively employ the thermal storage capacity of radiant floor heating/cooling system, thus lowering the operating cost of the r-microgrid effectively while ensuring the thermal comfort level of users.

The operation of the gas–steam–electricity multi-energy coupling system in iron and steel enterprises faces critical challenges: conflicts between energy efficiency and economic objectives, insufficient scheduling accuracy, and low energy utilization caused by source–load fluctuations. To address these issues, this paper proposes a hybrid scheduling model based on condition awareness and multi-objective optimization. The model integrates three key components. First, an energy fluctuation prediction technology based on working condition changes is developed. By acquiring real-time production signals and gas flow data, combined with a condition definition management module, it enables automatic identification and tracking of equipment operation status. A working condition sample curve superposition method is used to calculate energy medium imbalances, generating visual prediction curves for key parameters such as blast furnace, coke oven, and converter gas holder levels, achieving an average prediction accuracy of ≥95%. Second, a peak-shifting and valley-filling scheduling model for gas holders is designed, leveraging time-of-use electricity prices. During valley price periods, power purchases are increased and surplus gas is stored; during peak price periods, gas power generation is increased to reduce purchased electricity. A nonlinear model capturing the load–efficiency relationship of boilers and generators is established to dynamically optimize scheduling strategies. This reduces the proportion of peak hour power purchases by 10.3%, energy costs by 3.12%, and system energy consumption by 2.16%. Third, a multi-period and multi-medium energy optimization scheduling model is formulated as a mixed-integer nonlinear programming (MINLP) problem, with dual objectives of minimizing operating cost and energy consumption. Constraints include energy supply–demand balance, equipment operating limits, gas holder capacity, and generator ramp rates. The Pareto optimal solution set is obtained using the AUGMECON2 method and efficiently computed with the IPOPT solver. Application results demonstrate that the model achieves zero gas emissions, a dispatching instruction accuracy of 95%, and a 0.8% increase in the proportion of peak–valley-level self-generated power, outperforming comparable technologies. It provides technical support for the safe, efficient, and economic operation of multi-energy systems in iron and steel enterprises.

Optimal economic scheduling of microgrids with photovoltaic (PV) and wind generation has gained increased attention during recent years. Integration of renewable energy resources in microgrids requires increasingly active control and management of energy storages and demand response (DR). In this paper, a risk-based stochastic optimal energy management model is developed for microgrid with renewables, energy storage and load control by time-of-use-based DR programs. Microgrid includes PV system, wind system, micro-turbine, fuel cell, electric vehicle (EV), and energy storage. Information-gap decision theory (IGDT) is employed to address the uncertainty of loads and to provide the operating strategies for the microgrid controllable energy resources. This proposed model has been solved as a mixed-integer non-linear programming (MINLP) in General Algebraic Modeling System (GAMS) software and simulation results in different conditions are studied and discussed. Three different risk management strategies have been studied such as risk-averse, risk-neutral and risk-seeker mode. The simulation results indicate that the impacts of risk-averseness or risk-seeker of the decision maker affect the system operation. For instance, the results showed the DR program's role in risk-averse and risk-taking strategies, impacting consumption and costs. The proposed model ensures the risk-averse decision-maker that if the uncertain parameter deviates within the optimum robustness region, the final cost will not exceed the critical cost. On the other hand, the risk-seeking decision-maker can reach lower final costs by accepting the risks if the uncertain parameter deviates favorably within the opportunity region. Decision-makers can manage risks by adjusting consumption. Thus, considering the cost of risk management is crucial, as it increases with robust or opportunistic approaches.

Increasing population, rapid urbanization and hasty industrialization are assisting gradual shift in human residence from rural to urban. Any city trying to become a smart and sustainable one must provide a better quality of life for its citizens and address the problem of degrading air quality and increasing pollutant emissions. The solution for these problems requires selection and decision-making among a number of candidate emission-control-alternatives that need to satiate a number of technical constraints, policy criteria and regulations. For a given pollutant and emission source, a number of control technologies are available; hence, it is coveted to choose the best combination among them to reduce emissions to a desired standard. Because of its applicability, flexibility and ease of computation in solving large-scale practical problems, dynamic programming-based approach appears to be the appropriate and feasible choice for optimal air pollution control technology selection for an urban metropolitan area. Current study develops a dynamic programming (DP) model that determines the optimal selection strategy, after defining different parameters, at a minimized total cost. The usage and applicability of the proposed model were illustrated with a representative case study of a simulated city with three major sources of pollution. It is inferred that DP is ideal for the ‘multiple sources—multiple control technologies—single air pollutant’ optimization problem.

A semi-automatic and an automatic segmentation algorithm to remove the internal organs from live pig CT images

Microgrids (MG) are considered as interconnected networks of distributed energy sources, energy storage systems, and loads, which are able to work in the mode connected to the upstream network or independently. This paper presents is a more comprehensive model of optimal operation scheduling taking into account different constraints for an MG in the connected mode and for a 24-h period. The purpose of planning is to minimize the cost of exploitation and the amount of line losses by taking demand response programs (DRPs) and uncertainty. In planning with uncertainty, wind speed, MG load, and market energy price are characterized through a stochastic programming formulation. The main problem is formulated as a mixed integer nonlinear programming, which solved intelligent algorithm binary particle swarm optimization. The application of DRPs in deterministic and stochastic programming and their impact on the optimal cost of operation, losses, and other parameters are investigated in these cases.