Ichiro Nishizaki’s research while affiliated with Hiroshima University and other places

... Nishizaki et al. [19] addressed two-stage stochastic linear production planning with partial cooperation, involving resource pooling, technology transfer, and product transshipment. Manufacturers determine production levels individually in the first stage, and then collaborate to produce products using pooled resources in the second stage. ...

Reference:

A Review of Game Theory Models to Support Production Planning, Scheduling, Cloud Manufacturing and Sustainable Production Systems

... The shared energy storage takes advantage of its scale, the spatiotemporal complementarity of different users' energy storage needs, and time-sharing multiplexing to effectively improve the flexibility and economy of energy storage (Sekizaki et al., 2023). Xie et al. (2022b) proposed a method of applying shared energy storage on the power generation side to improve the flexibility and economy of energy storage resources in each wind farm through the sharing of energy storage. ...

Reference:

A novel framework for photovoltaic energy optimization based on supply–demand constraints

... Figure 2 illustrates the proposed hierarchical framework with production control at the upper level and distribution planning at the lower level. Notably, our proposed hierarchical framework differs from the conventional bi-level optimisation structure (Nishizaki et al. 2022;Zhao et al. 2023), nor the integrated learning and optimisation problem . In those approaches, the lower-level problem is typically treated as an embedded optimisation problem for the upper-level agent. ...

Reference:

Hierarchical production control and distribution planning under retail uncertainty with reinforcement learning

... The key advantage of the microservice design is its flexibility to scale and independent modification of functionality. The data analytics platform embedded in the system features two main processes: artificial neural networks (ANNs) [9,10] and particle swarm optimization (PSO) [11,12]. The ANNs serve for parameter predictions by analyzing ambient conditions, the air conditioner's usage behavior, and the air conditioner's specific performance data. ...

Reference:

Optimal control of cooling management system for energy conservation in smart home with ANNs-PSO data analytics microservice platform

... In Sekizaki et al. (2021) propose a novel methodology to tackle a many-objective engineering problem in the area of network reconfiguration of an electric distribution system. The challenge in the application considered is to determine how best to downsize equipment (distribution lines) such that costs are reduced while feasibility of the network reconfigurations (due to maintenance and/or replacement of distribution lines) is guaranteed. ...

Reference:

Multiobjective optimization and decision making in engineering sciences

... In Yano and Nishizaki (2021) focus on the application of MO concepts to twolevel programming problems, also known as Stackelberg games. In these games, a leader (e.g. ...

Reference:

Multiobjective optimization and decision making in engineering sciences

... The identification of the language of a speech is often done by selecting and analyzing a piece of this speech as reported in [8] and [18]. As reported in [11]- [13] and [19], this identification may be done by a classification algorithm based on the automatic learning of a "deep neural network" trained using a multi-language speeches dataset recorded for several speakers. ...

Reference:

Human-Robot Multilingual Verbal Communication – The Ontological knowledge and Learning-based Models

... Some examples of evolutionary computing models that are often used and can still be developed include Genetic algorithm, particle swarm optimization, ant colony optimization, and bee algorithm (Abidin, 2018). (Hayashida et al., 2019) The 0-1 multidimensional Knapsack problem is a combinatorial problem of selecting items to be stored in a place with capacity constraints. The selection of a small number of items is very easy to do manually, but if the number of items is large and must meet several capacity constraints, it will make a lot of combinatorial choices and difficult to do manually. ...

Reference:

Multidimensional Knapsack 0-1 Solution With Algorithm Evolution Pso-Ga

... Note that the five objectives (4)-(8) include discrete values, i.e., (5) (8). To avoid the numerical instability and find extreme points due to the discrete objective values, we employ an adaptive normalization proposed in our previous research (Sekizaki et al. 2019). ...

Reference:

Distribution line downsizing based on a set of non-dominated solutions for a network reconfiguration problem of an electric distribution system with many objectives

... Thus, these can be an effective means of improving the resilience of power grids. The performance of the digital controller for the SSI under development has been verified using hardware-in-the-loop simulations [9] and demonstration experiments while connected to the grid, along with the independent operation of single-phase microgrids [8,10,11]. The grid stabilization effect is the most important factor to consider when evaluating GFM inverters, and previous research has evaluated the effect of the output current phase of the GFM inverter on the critical fault clearing time in the event of a grid fault [12], along with the deterioration of the transient stability due to a P-f droop controller [13]. ...

Reference:

Single‐phase Synchronous Inverter with Overcurrent Protection using Current Controller with Latched Limit Strategy